US20040249778A1

Movatterモバイル変換

Info

Publication number: US20040249778A1
Application number: US10/827,192
Authority: US
Inventors: Edwin Iliff
Original assignee: Individual
Current assignee: Clinical Decision Support LLC
Priority date: 1993-12-29
Filing date: 2004-04-16
Publication date: 2004-12-09
Also published as: US6725209B1

Abstract

A system and method for providing computerized, knowledge-based medical diagnostic and treatment advice. The medical advice is provided to the general public over a telephone network. Two new authoring languages, interactive voice response and speech recognition are used to enable expert and general practitioner knowledge to be encoded for access by the public. “Meta” functions for time-density analysis of a number of factors regarding the number of medical complaints per unit of time are an integral part of the system. A semantic discrepancy evaluator routine along with a mental status examination are used to detect the consciousness level of a user of the system. A re-enter feature monitors the user's changing condition over time. A symptom severity analysis helps to respond to the changing conditions. System sensitivity factors may be changed at a global level or other levels to adjust the system advice as necessary.

Description

RELATED APPLICATIONS

This application is a continuation of prior application Ser. No. 09/588,881, filed Jun. 6, 2000, which is a divisional of prior application Ser. No. 09/088,940, filed Jun. 2, 1998, now U.S. Pat. No. 6,071,236, issued Jun. 6, 2000, which is a divisional of prior application Ser. No. 08/176,041, filed Dec. 29, 1993, now U.S. Pat. No. 5,660,176, issued Aug. 26, 1997.[0001]

BACKGROUND OF THE INVENTION

1. Field of the Invention[0002]

The present invention relates to medical knowledge systems and, more particularly, to systems for giving medical advice to the general public over a telephone network.[0003]

2. Description of the Related Technology[0004]

Health care costs currently represent 14% of the United States Gross National Product and are rising faster than any other component of the Consumer Price Index. Moreover, usually because of an inability to pay for medical services, many people are deprived of access to even the most basic medical care and information.[0005]

Many people delay in obtaining, or are prevented from seeking, medical attention because of cost, time constraints, or inconvenience. If the public had universal, unrestricted and easy access to medical information, many diseases could be prevented. Likewise, the early detection and treatment of numerous diseases could keep many patients from reaching the advanced stages of illness, the treatment of which is a significant part of the financial burden attributed to our nation's health care system. It is obvious that the United States is facing health-related issues of enormous proportions and that present solutions are not robust.[0006]

One prior attempt at a solution to the health care problem is called Ask-A-Nurse, wherein a group of nurses provide health information by telephone around-the-clock. A person with a medical problem calls an 800 number and describes the problem to the nurse. The nurse uses a computer for general or diagnostic information on the ailment or complaint mentioned by the caller. The nurse may then refer the caller to a doctor from a computerized referral list for a contracting hospital or group of hospitals. Client hospitals contract with Ask-A-Nurse to provide patient referrals. A managed care option called Personal Health Advisor is similar and adds the capability for the caller to hear prerecorded messages on health topics 24 hours a day. Several problems exist with these prior medical advice systems. First, these systems have high costs associated with having a nurse answer each telephone call. Second, the caller may have to belong to a participating health plan to utilize the service. Third, if for some reason all nurses on a particular shift happen to be busy and the caller has an emergency condition (that is not known by the caller to be an emergency), precious time in getting emergency services may be lost during the delay.[0007]

Another prior health system was developed by InterPractice Systems which provides a computerized service that answers health care questions and advises people in their homes. A health maintenance organization (HMO) may provide this service to its members in a particular geographic area. To get advice at home, an HMO member connects a toaster-sized box to a telephone and calls a toll-free 800 number. Using a keyboard that is part of the box, the user answers questions displayed on a screen of the box relating to the user's symptoms. Depending on the answers, the user might be told to try a home remedy, be called by a nurse or doctor, or be given an appointment to be examined. A limitation of this system is the additional expense of the electronics box, which could either be purchased by the user for approximately $300 or purchased by the health organization with the expense to be passed on to the users. Another limitation is that this service is directed to members of a particular contracting health organization, such as an HMO. What is desired is a system that does not require additional hardware for the basic service, but that utilizes the existing communication network. The desired system should be available for use by any person, not just members of a certain organization.[0008]

A prior attempt at a health care solution for a limited set of conditions is described in U.S. Pat. No. 4,712,562. A patient's blood pressure and heart rate are measured and the measurements are sent via telephone to a remote central computer for storage and analysis. Reports are generated for submission to a physician or the patient. U.S. Pat. No. 4,531,527 describes a similar system, wherein the receiving office unit automatically communicates with the physician under predetermined emergency circumstances.[0009]

U.S. Pat. No. 4,838,275 discloses a device for a patient to lay on or sit in having electronics to measure multiple parameters related to a patient's health. These parameters are electronically transmitted to a central surveillance and control office where a highly trained observer interacts with the patient. The observer conducts routine diagnostic sessions except when an emergency is noted or from a patient-initiated communication. The observer determines if a nonroutine therapeutic response is required, and if so facilitates such a response. As previously mentioned, highly trained people are needed by this system along with the special measurement apparatus (embedded in a bed or chair).[0010]

Other prior attempts at a health care solution are typified by U.S. Pat. No. 5,012,411 which describes a portable self-contained apparatus for measuring, storing and transmitting detected physiological information to a remote location over a communication system. The information is evaluated by a physician or other health professional. As before, highly trained people are necessary to utilize such an apparatus.[0011]

Several services to provide medical or pharmaceutical advice are now available via “1-900” telephone numbers, e.g., “Doctors by Phone.” These services are available 24 hours a day and 7 days a week. A group of doctors, including some specialties, is available to answer questions about health care or medical conditions for people anywhere in the United States who call the “1-900” telephone of one of the services. A group of registered pharmacists answers questions about medications for the “1-900” pharmaceutical service.[0012]

SUMMARY OF THE INVENTION

The present solution to the health care problem is a computerized medical diagnostic and treatment advice (MDATA) system that is a medical knowledge-based system designed to give medical advice to the general public over the telephone network. The goal of the MDATA system is to provide everyone with equal access to high quality, 100%-consistent medical advice at a reasonable cost. The MDATA system provides callers with extremely fast and virtually unlimited access to health care information, twenty-four hours a day, from any location around the world. Health care advice is made available to an entire spectrum of users, from elderly patients confined to their homes to travelers in a foreign country with telephones in their cars.[0013]

The central ideas leading to the development of the MDATA system are based on the following assumptions:[0014]

Nearly 90% of all patient complaints are confined to approximately 100 medical problems.[0015]

Almost all primary care decisions involved in these 100 problems can be made based upon information learned solely by obtaining a detailed medical history. The results of the physical examination, laboratory, and imaging studies only tend to confirm a diagnosis.[0016]

The minimal amount of information that many doctors believe can only be obtained from the physical examination can actually be directly acquired from the patient when given appropriate instructions.[0017]

In most cases, a face-to-face interaction between the doctor and patient is not necessary. A detailed and well-constructed history, along with physical findings elicited from the patient, can be obtained over the telephone.[0018]

Medicine is basically diagnosis and treatment. Although treatment recommendations change frequently, the fundamental principles of making the diagnosis do not.[0019]

There is a significant delay between the time a new therapy is recognized as safe and effective and the time physicians are able to provide it to their patients.[0020]

These central ideas are utilized in the implementation of the MDATA system.[0021]

A goal of the MDATA system is to give better medical advice than a family practitioner who is unfamiliar with a patient, e.g., an on-call physician. A person seeking medical advice frequently will not be able to see or speak with his or her personal physician in a timely manner. The MDATA system provides medical advice whenever desired by the caller—seven days a week/24 hours a day.[0022]

All previous medical algorithms, including those used in the military, are designed for face-to-face interactions. Self-help books generally do not consider age and sex in their algorithms. Furthermore, a book cannot take into account how many times a person has consulted the same algorithm within a short period of time for the same problem. The medical algorithms used by the MDATA system are designed for use in a telecommunications setting and overcome the deficiencies of self-help books.[0023]

Previous medical advice systems do not do a time-density analysis for a number of factors with regard to the number of complaints per unit of time. The MDATA system uses “meta” functions to perform these analyses.[0024]

Previous medical advice algorithms do not have a way of detecting the consciousness level of the person seeking consultation. The MDATA system invokes a “mental status examination” whenever a complaint or problem has the possibility of an altered level of consciousness. In addition, the MDATA system uses “semantic discrepancy evaluator loops” which allow the system to invoke the mental status exam if there are differences in answers to the parallel threads of thought that are woven or embedded into the system.[0025]

Other medical advice systems do not have a “re-enter” feature to monitor a patient's progress or worsening over time. The MDATA system checks for and responds to changing conditions over time.[0026]

Prior medical advice systems suffer from the inability to be nearly instantly up-dated as new medical information is made available. The MDATA system regularly and frequently updates the treatment aspect of the system.[0027]

The computerized medical diagnostic and treatment advice (MDATA) system is a medical knowledge-based system designed to give medical advice to the general public over the telephone network. Using a new authoring language, interactive voice response and speech recognition technology, the MDATA system encodes a highly useful core of expert and general practitioner diagnostic and treatment knowledge into a computerized system for access by non-medically trained personnel.[0028]

The MDATA system does not provide advice for every medical problem, nor does it make an exhaustive study of one vertical cross-section of medicine. Instead, the MDATA system provides up-to-date medical advice for approximately one hundred of the most commonly encountered problems in general practice and emergency medicine. It also provides valuable information to the public on any number of other medical topics.[0029]

As another embodiment of the MDATA system, a person desiring medical advice and having access to a personal computer (PC) loads a program into the PC to produce a stand-alone medical diagnostic and treatment advice (SA-MDATA) system. Rather than listening to questions and responding via touch tone keypresses or via voice, the user responds to questions and directions displayed on the computer screen via a computer input device, such as a keyboard or mouse. The diagnosis and/or treatment recommendations provided by the MDATA system are the same as that provided by the SA-MDATA system. The user of the SA-MDATA system can procure updates by contacting the MDATA system sponsor/administrator to obtain the most current treatment table information for a particular diagnosis.[0030]

In one embodiment of the invention, there is a method of mental status examination while performing an automated diagnostic consultation using an automated medical advice or diagnostic system including a computing device and input and output devices, the method comprising prestoring a plurality of questions and corresponding expected answers in a computing device memory, automatically asking a patient a one of the plurality of prestored questions, automatically comparing the answer to a corresponding prestored expected answer, automatically ascribing a score to a result of the comparison, and automatically comparing the score to a predetermined threshold value so as to determine a mental status of the patient.[0031]

In another embodiment of the invention, there is an automated medical advice or diagnostic system configured to conduct a mental status examination while performing an automated diagnostic, the system comprising storage means for prestoring a plurality of questions and corresponding expected answers, means for automatically asking a patient a one of the plurality of prestored questions, means for automatically comparing the answer to a corresponding prestored expected answer, means for automatically ascribing a score to a result of the comparison, and means for automatically comparing the score to a predetermined threshold value so as to determine a mental status of the patient.[0032]

In another embodiment of the invention, there is an automated medical advice or diagnostic system configured to conduct a mental status examination while performing an automated diagnosis, the system comprising a computing device, a storage associated with the computing device configured to prestore a plurality of questions and corresponding expected answers, and a software program executed on the computing device and configured to automatically ask a patient a one of the plurality of prestored questions, automatically compare the answer to a corresponding prestored expected answer, automatically ascribe a score to a result of the comparison, and automatically compare the score to a predetermined threshold value so as to determine a mental status of the patient.[0033]

In another embodiment of the invention, there is a method of mental status examination, using an automated medical advice or diagnostic system including a computing device and input and output devices, the method comprising automatically providing a patient an item of information prestored in a computing device memory, automatically waiting a predetermined time interval, automatically asking the patient about the item of information, automatically comparing an answer from the patient to a prestored expected answer, and automatically evaluating a mental status of a patient based on the comparison.[0034]

In another embodiment of the invention, there is a method of mental status examination, using an automated medical advice or diagnostic system including a computing device and input and output devices, the method comprising automatically asking a patient for an item of information, wherein a first request for the item of information is prestored in a computing device memory; automatically receiving a first answer; automatically waiting a predetermined time interval; automatically asking the patient about the item of information in a different manner, wherein a second request for the item of information is prestored in the computing device memory; automatically receiving a second answer; automatically comparing the first answer to the second answer; and automatically evaluating mental status of a patient based on the comparison.[0035]

In another embodiment of the invention, there is an automated medical advice or diagnostic system configured to conduct a mental status examination while performing an automated diagnosis of a patient, the system comprising storage means for automatically providing a patient an item of prestored information, means for automatically waiting a predetermined time interval, means for automatically asking the patient about the item of information, means for automatically comparing an answer from the patient about the item of information to the prestored information, and means for automatically evaluating a mental status of a patient based on the comparison.[0036]

In another embodiment of the invention, there is an automated medical advice or diagnostic system configured to conduct a mental status examination while performing an automated diagnosis of a patient, the system comprising a computing device, a storage associated with the computing device configured to prestore an item of information, and a software program executed on the computing device and configured to automatically provide a patient the item of prestored information, automatically wait a predetermined time interval, automatically ask the patient about the item of information, automatically compare an answer from the patient about the item of information to the prestored information, and automatically evaluate a mental status of a patient based on the comparison.[0037]

In another embodiment of the invention, there is an automated medical advice or diagnostic system configured to conduct a mental status examination while performing an automated diagnosis of a patient, the system comprising means for automatically asking a patient for an item of information, wherein a first request for the item of information is prestored in a computing device memory; means for automatically receiving a first answer; means for automatically waiting a predetermined time interval; means for automatically asking the patient about the item of information in a different manner, wherein a second request for the item of information is prestored in the computing device memory; means for automatically receiving a second answer; means for automatically comparing the first answer to the second answer; and means for automatically evaluating mental status of a patient based on the comparison.[0038]

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram illustrating the components of a presently preferred embodiment of the computerized medical diagnostic and treatment advice (MDATA) system of the present invention;[0039]

FIG. 2 is a diagram of the off-line process used in producing the speech files shown in FIG. 1;[0040]

FIG. 3 is a diagram of the Node Translation process used in creating files for use by the system of FIG. 1;[0041]

FIG. 4 is a diagram of some of the files and components of FIGS. 1 and 3 that are utilized at run time;[0042]

FIG. 5[0043]ais a diagram of the utilization of the files shown in FIG. 3 at run time;

FIGS. 5[0044]b-5gare an exemplary sequence of data structures of the system shown in FIG. 1 at run time;

FIG. 6 is a block diagram illustrating a conceptual view of the database files and processes of the system of FIG. 1;[0045]

FIGS. 7[0046]a,7b,7cand7dare a top-level flow diagram of the MDATA system of FIG. 1;

FIGS. 8[0047]aand8bare a flow diagram of thepatient login process250 defined in FIG. 7a;

FIGS. 9[0048]aand9bare a flow diagram of thepatient registration process252 defined in FIG. 7a;

FIGS. 10[0049]aand10bare a flow diagram of theevaluation process254 defined in FIG. 7d;

FIGS. 11[0050]aand11bare a flow diagram of themeta function500 defined in FIG. 10b;

FIGS. 12[0051]aand12bare a flow diagram of theassistant login process272 defined in FIG. 7b;

FIGS. 13[0052]aand13bare a flow diagram of the assistedpatient login process276 defined in FIG. 7b;

FIGS. 14[0053]aand14bare a flow diagram of theassistant registration process274 defined in FIG. 7b;

FIGS. 15[0054]aand15bare a flow diagram of the assistedpatient registration process278 defined in FIG. 7b;

FIGS. 16[0055]aand16bare a flow diagram of the mentalstatus examination function508 defined in FIG. 10b;

FIG. 17 is a flow diagram of the semantic discrepancy evaluator routine (SDER)[0056]510 defined in FIG. 10b;

FIG. 18 is a flow diagram of the past[0057]

medical history routine

512 defined in FIG. 10b;

FIG. 19 is a flow diagram of the physical[0058]

self examination function

514 defined in FIG. 10b;

FIG. 20 is a flow diagram of the patient[0059]

medical condition routine

516 defined in FIG. 10b;

FIG. 21 is a flow diagram of the symptom[0060]

severity analysis function

518 defined in FIG. 10b;

FIG. 22 is a flow diagram of the[0061]

treatment table process

256 defined in FIG. 7d; and

FIG. 23 is a flow diagram of the menu-driven[0062]

treatment selection process

864 defined in FIG. 22.

FIG. 24 is Table 3, a two dimensional array of causes of diseases plotted against anatomical systems.[0063]

FIG. 25 is Table 4, an exemplary plot of symptom severity versus time.[0064]

FIG. 26 is Table 5, another exemplary plot of symptom severity versus time.[0065]

FIG. 27 is Table 9, a plot of sensitivity and selectivity versus time.[0066]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT

The following detailed description of the preferred embodiments presents a description of certain specific embodiments to assist in understanding the claims. However, the present invention can be embodied in a multitude of different ways as defined and covered by the claims.[0067]

For convenience, the following description will be outlined into the following 22 principal sections: Introduction, System Overview, Operating Features of the MDATA System, Authoring Language, Run-Time Operation, Software Structure, Top-Level Flow, Login Process, Registration Process, Evaluation Process, The Meta Function, Mental Status Examination, Semantic Discrepancy Evaluator Routine, Past Medical History Routine, Physical Self Examination, Symptom Severity Analysis, Treatment Table, The MDATA System Paradigm, Video Imaging, Benefits of the MDATA System, Optional System Configuration, and Summary of Advantages of the Present Invention.[0068]

I. Introduction

A consultation for a person seeking medical advice begins with a telephone call to the medical diagnostic and treatment advice (MDATA) system of the present invention. The MDATA system asks the caller specific questions and then analyzes each response.[0069]

Voice recognition and interactive voice response technology allow callers to respond to yes/no and multiple choice questions either by speaking directly into the telephone or by using the touch tone pad of their telephone.[0070]

Easy access to the information in the MDATA system is made possible by a natural user interface. The computer-driven dialogue consists of simple yes/no and multiple choice questions. The questions and treatment recommendations are very simply worded yet skillfully designed to reflect the accumulated experience of many physicians in conducting patient interviews.[0071]

Although all the MDATA system's questions are designed to be easily understood, unforeseen situations will inevitably arise. For this reason, hierarchical staffing is implemented. As an example, for every 10 telephone lines, one operator fully trained in triage and the MDATA system will be available. For every 10 operators there will be one registered nurse in attendance; and for every 10 registered nurses, there will be one physician in attendance. Staffing requirements are adjusted as the system is refined toward optimal efficiency. The MDATA system does not require the operator or the registered nurse to make any medical decisions.[0072]

II. System Overview

Referring to FIG. 1, the components of a presently preferred embodiment of the computerized medical diagnostic and treatment advice (MDATA)[0073]

system

100 of the present invention are shown. A personal computer (PC)102 includes a plurality of components within anenclosure104. A plurality oftelephone lines106 interface thepublic telephone network108 to thecomputer102. As an example, one oftelephone lines106 is shown to be switched vianetwork108 to connect with atelephone110 that is used by a person desiring medical advice (user)112. Throughout this document, the words user, caller and patient are used interchangeably. However, it will be understood that the caller may be acting as a proxy for the patient. If this is the case, the caller will be registered as an assistant for the patient.

The hardware and system software were assembled with two basic concepts in mind: portability to other operating systems and the use of industry standard components. In this way, the system can be more flexible and will allow free market competition to continuously improve the product, while, at the same time, decrease costs. While specific hardware and software will be referenced, it will be understood that a panoply of different components could be used in the present system.[0074]

The system currently runs on the[0075]

PC

102 with anIntel 80486 microprocessor. “Telephony” functions use Dialogic Corporation's D/41Dvoice processing board122 based on a digital signal processor (DSP). The voice processing (VP)board122 performs several functions including interfacing the telephone lines, decoding touch tone signals, speech recording and speech playback. Touch tone signals are also known as “dual tone multiple frequency” (DTMF) signals. A group of one to fourtelephone lines106 connect to theVP board122. Thecomputer102 may include a plurality ofVP boards122 based on how many phone line connections are desired for thesystem100. Speech recognition is achieved using Voice Processing Corporation's speech recognition VPRO-4 board124 (also DSP based). The voice recognition (VR)board124 performs several functions including recognizing utterances and returning an index number of a recognition confidence level. TheVR board124 and theVP board122 both connect to an industry standard architecture (ISA)bus126. TheISA bus126 interconnects themicroprocessor120 with a plurality of peripherals through controller circuits (chips or boards).

The[0076]

VP board

122 also connects to a VPRO-Adapt board128 via ananalog audio bus130 that is called Analog Extension Bus. Four simultaneous channels provide a 96 kbit/second data transfer rate. Each channel corresponds to a telephone line connected to theVP board122 and is associated with a current patient consultation. TheAdapt board128 further connects to adigital audio bus132. TheVR board124 also connects to thedigital audio bus132. TheAdapt board128 performs analog to digital signal conversion to a VPC-proprietary digital pulse code modulation (PCM) format. Thedigital bus132 can accommodate 32 channels and has a data transfer rate of 2.048 Mbits/second.

The[0077]

computer ISA bus

126 has a plurality of peripherals connected to it through adapters or controllers. Avideo adapter board136, preferably at VGA or better resolution, interconnects to avideo monitor138. Aserial communication circuit140 interfaces a pointing device, such as amouse142. A parallel communication circuit may be used in place ofcircuit140 in another embodiment. Akeyboard controller circuit144 interfaces akeyboard146. A small computer systems interface (SCSI) adapter, such asmodel 1542C made by Adaptec, provides aSCSI bus150 to which a 500 Mb or greaterhard disk drive152 anddual Bernoulli 150 Mb disk drives are preferably attached. Thehard drive152 stores database files such as the patient files, speech files, and binary support files.

A[0078]

main memory

156 connects to themicroprocessor120. In the presently preferred embodiment, theMDATA system100 operates under DOS version 5.0operating system158. The system software is written in Microsoft C\C++ version 7.0 using structured programming techniques. Analgorithm processor160 includes a parser and supporting functions that manipulate a memory variable symbol table and a run time stack, which will be described hereinbelow. Sequiter Software Inc. Codebase 5.0 allows access to X-base compatible database records stored on thehard drive152. TheMDATA system100 also includes two new authoring languages (one each is used in two embodiments of the system), which will be discussed hereinbelow.

The system software includes the following code modules:[0079]

A. main.c—a collection of functions that mostly deal with telephony functions, such as answering the phone line, speech file playback, and DTMF tone collection. Global data structures are defined here.[0080]

B. base.c—functions that invoke the CodeBase revision 5.0 library to perform xbase file manipulation.[0081]

C. pars.c—the parse function, and supporting functions that manipulate the memory variable symbol table and run time stack.[0082]

D. regi.c—an on-line patient registration module.[0083]

E. resp.c—gets the caller's responses, either DTMF or voice, and figures out what to do next by obeying a command (e.g., “repeat” or “backup”), or traversing through the algorithm node map.[0084]

F. term.c—a useful collection of text phrases for Dialogic and VPC board termination events and error codes.[0085]

G. user.c—“non-diagnostic” portions of the caller session: initial screening questions, caller login, and the next node playback initiator.[0086]

H. util.c—a collection of general purpose functions shared by a run time executable, a node editor and ASCII translator tools.[0087]

I. view.c—a module that controls the graphics system display.[0088]

J. x10.c—an X-10 computer interface routine for fault recovery.[0089]

K. xlat.c—a module linked with pars.c and util.c object modules to build xlat.exe, a stand-alone translation executable for offline ASCII text file translation.[0090]

The application is compiled with the Microsoft graphics, Dialogic board, VPC board and CodeBase database libraries.[0091]

The Voice Processing Corporation (VPC) VPro-4 VR board has eight voice recognition channels, which by default are associated one-to-one with the Dialogic D/41D channels. VPC's pioneering work in the voice processing field is in the area of continuous speech. This allows a person to speak a multiple digit number in a natural manner, without pausing after each digit. VPC supplies two continuous speech vocabularies: one vocabulary contains the[0092]digits 1 through 9, plus “zero” and “oh”, and the other contains just the two words “yes” and “no”. The vendor-supplied digits continuous speech vocabulary is used by thesystem100. In the presently preferred embodiment, if the score is 75% or better, the response is unconditionally accepted. If the score is between 20% and 74%, the digits recognized are read back, and the caller is asked to accept or reject the digits. In another embodiment of thesystem100, the above score thresholds are implemented as tunable parameters. The scoring parameters are stored in a configuration file that is manipulated off-line by a utility program and is read by the run-time system at initialization.

VPC also provides a few discrete vocabularies. Discrete vocabularies contain one or two word utterances. The vendor-supplied discrete speech vocabulary of the months of the year is used in the on-line patient registration process. A speaker-independent discrete speech vocabulary consisting of the words “yes”, “no”, “backup”, “continue”, “help”, “operator”, “pause”, “quit” and “repeat” has been developed using a very powerful set of utilities supplied by VPC, Scripter and Trainer. These utilities are for collecting samples and training the vocabulary.[0093]

The[0094]

VR board

124 has the minimum of two MB memory installed. The default memory configuration has a partition for both continuous vocabularies and a partition for one discrete vocabulary. Additional discrete vocabularies may be downloaded if the on-board memory is reconfigured.

The[0095]

VR board

124 has four digital signal processors (DSP's) from which VPC derived eight voice recognition channels. Each of these eight recognition resources is referred to as a VPro Speech Processor (VSP). Discrete vocabulary recognition requires one VSP; continuous vocabulary recognition requires two adjacent VSP's. TheMDATA system100 has a VSP resource manager in the resp.c software module. This resource manager allocates VSP's in a dynamic manner toVP board122 channels on a demand basis. As soon as the system receives a response, voice or DTMF, it releases the VSP's associated with the caller'sVP board122 channel.

The[0096]

MDATA system

100 uses VPC's application programming interface (API) for the C programming language. This makes the application vendor specific to VPC, but also allows thesystem100 to utilize all the powerful API features, e.g., on-line creation of discrete speaker dependent vocabularies used for voice pattern matching or voice printing.

The VPC API supports both continuous speech vocabulary (CSV) and discrete speech vocabulary (DSV) recognition.[0097]

The voice processing (VP)[0098]

board

122 supports speech recording and playback, as well as touch tone (DTMF) signal detection and decoding. A device driver, associated with theVP board122, is loaded into system memory during load operations. The device driver supports communications between theVP board122 and the application code at run time (e.g., when a person is seeking medical advice). Through a shared memory segment, the device driver sends event and status data to the application code in real-time as events occur on the associated telephone line. These events include the ring of an incoming call, touch tone key pressed by the caller, and the hang-up signal. TheVP board122 plays back speech messages that are stored on thehard drive152. Thealgorithm processor160 sends a selected speech file having an encoded speech message that is retrieved from thehard drive152 to theVP board122 at the appropriate time for speech message playback. A speech message can be of variable length with a typical message about one to two minutes in length. Several speech messages may be chained together to produce an extended spoken message, e.g., giving instructions to the patient. During speech file playback, theVP board122 is monitoring touch tone response from the caller. TheVP board122 may be configured to interrupt speech file playback when a touch tone signal is detected.

System Operating Contexts[0099]

The system has an activity flag in the port status block for each patient currently using the system to keep track of which state the associated VP board channel is in:[0100]

a. Idle Mode—an idle channel waiting for a telephone call;[0101]

b. Login Mode—a condition where a patient is in the login process;[0102]

c. Registration Mode—a condition where a patient is in the registration process;[0103]

d. Real Mode—a condition where a patient is consulting for an actual medical problem;[0104]

e. Info (Information) Mode—a condition where a patient is consulting for information or a hypothetical situation;[0105]

f. Pause Mode—a patient-initiated pause condition;[0106]

g. Pending Mode—similar to Real mode except that new medical information gathered for a patient is not automatically added to the patient's medical record, but rather written to a “Pending” file where it will be verified off-line by a staff person.[0107]

Voice Keywords and DTMF Command Keys[0108]

The system is responsive to the following voice keywords and DTMF keys when it is in a prompting state, i.e., not in response to a menu message:[0109]



Voice	DTMF

yes	1	Useful for answering yes/no questions.
no	2
backup	#	Causes the system to back up to the “predecessor”
		message (see below), then resume playback.
help	*	Plays helpful information: either the node's help
		message list, or the DTMF command explanation
		message.
operator	0	Causes the system to transfer the caller to a live
		person.
pause	7	Transitions to pause mode. The system default
		pause period is 30 seconds.
quit	9	Quits the current algorithm, and takes the caller to
		node 110, which asks the caller if (s)he wishes to
		select another algorithm.
repeat	3	Repeats the current node's play message list. If
		this command is given in the middle of a long play
		list, then playback restarts with the first message in
		the list.

Pause Mode Commands

yes	1	Extends the pause period by one default pause
		interval (30 seconds).
continue	2	Ends pause mode. If this occurs at a Yes/No
		node, the system will repeat the question. If this
		occurs at a Link node, the system will resume
		playback with the “current” message. The
		system resolves the DTMF digit “2” ambiguity,
		“no” versus “continue” , by examining the pause
		mode flag.

FIG. 2 illustrates how speech files are created. A person programming medical algorithms uses speech messages to communicate with the person seeking medical advice. As previously mentioned, these speech messages are of variable length. The programmer typically writes a script for the speech message. Then using the handset of the[0110]

telephone

110, a speakerphone feature, or other voice-input device, e.g., a microphone, the programmer reads the script into the voice-input device which is connected to theVP board122. The VP board converts the speech into a digital format and records the digitized speech to a file that is stored on thehard drive152. In the presently preferred embodiment, a subdirectory named vox contains the system speech files, and subdirectories for each medical algorithm. System speech files are of the form sysxxx, where xxx is some arbitrarily assigned number. The system messages are used by the “fixed” parts of the system, e.g., greeting, login process, registration process. There are a few speech files of the form msgxxx. These are the past medical history questionnaire messages, and response acknowledgements. There are additional speech files of the form msgxxxx in each of algorithm subdirectories, where xxxx generally matches the node number, which will be explained hereinbelow. Node messages include information, question, menu and help messages.

III. Operating Features of the MDATA System

One of the MDATA system's main objectives is to bring together highly-qualified medical experts, encode their knowledge in a central location, and make it available to everyone. A new and unique authoring language is used by the MDATA system to help accomplish this objective.[0111]

Each day, specialists perform the same tasks over and over. They enact the same diagnostic ritual of solving a familiar problem. At the same time, however, primary care physicians attempt to find the best path through the diagnostic maze of an unfamiliar problem. This process is inefficient and fraught with error.[0112]

In medicine, there is generally one best way to do things. Instead of physicians spending valuable time duplicating tasks, the MDATA system utilizes medical experts from each medical specialty who write detailed algorithms for the treatment of the 100 or so most commonly encountered complaints in family practice and emergency medicine. These algorithms are carefully and specifically designed to elicit historical data and physical findings over the telephone, rather than in face-to-face interactions.[0113]

Several experts could work together to thoroughly research one particular complaint as well as to anticipate the full spectrum of possible problems and patient responses. These experts could also provide and maintain the MDATA system treatment table as well as the imaging modality of choice and laboratory test of choice tables. These concepts will be described hereinbelow.[0114]

Carefully crafted questions, used in the taking of a medical history, are the main tools that the NDATA system uses to assess the problems of patients. The key to getting a good history is to ask the right questions. In a sense, in the diagnostic process questions are like tests. It is important to note that the right questions are basically always right; they don't change. Although they may be refined over time, in general, once excellent and well-crafted questions are developed they are good for a very long time. Of course, as new diseases are discovered, e.g., toxic shock syndrome and AIDS, new sets of diagnostic questions are developed that are disease specific.[0115]

The questions used by an earlier generation of physicians, who did not have any of the latest imaging modalities (types or methods), are far more sensitive and precise in diagnosing a patient's problem than the questions used by doctors today. The MDATA system makes use of fine nuances of language to diagnose patients as well as to determine when certain tests or imaging studies are necessary.[0116]

The MDATA system's statistic generating capabilities enable the system to analyze the effectiveness of the questions used in the diagnostic process. As a result, physicians benefit from the immense amount of statistical information that is gathered regarding the wording of questions asked in taking medical histories. For example, exactly what percentage of patients who answer “yes” to the question, “Is this the worst headache of your life?” actually have a subarachnoid hemorrhage? Although this is a classic description of this problem, the exact probability of having this kind of brain hemorrhage after answering “yes” to this question is not presently known. Currently, doctors can only estimate the probability of certain conditions based on history. By applying the statistical information that is generated, the MDATA system not only provides the patient with advice that is continually improving, but it will also be able to pass along these probabilities to the entire medical community.[0117]

To function optimally, the MDATA system tries to gain as much medical information about its patients as possible. Although a first-time caller is given excellent advice, more specific advice can be given if the system has more information. Therefore, the MDATA system asks patients for their complete medical history. The MDATA system can either obtain the patient's medical record over the telephone or it can mail or fax a detailed questionnaire to each patient. The patient can then gather the necessary information at their convenience. The MDATA system will always be available by telephone to clarify any questions the patient may have.[0118]

The MDATA system uses the “International Classification of Diseases” (ICD□9□CM) codes to help summarize the information it has about a patient. This world standard is a comprehensive numerical system used to classify the entire spectrum of medical diseases. ICD□9□CM codes are also used to classify specific procedures performed (e.g., appendectomy) as well as the morphology of neoplasm (i.e., tissue diagnosis of a cancer).[0119]

In addition, the[0120]

MDATA system

100 uses ICD□9□CM “E-Codes” to classify environmental events, circumstances, and conditions as the cause of injury, poisoning, and other adverse effects. These codes are particularly helpful for storing information about what drugs the patient has taken or is currently taking, as well as the context (e.g., therapeutic use, accident, poisoning, suicide attempt) in which they were or are being taken. For example, E942.1 is the code for the therapeutic use of digoxin. Medications are also cross-categorized according to the classification done by the American Hospital Formulary Service List (AHFS) Numbers. TheMDATA system100 also uses “V-Codes” to classify other types of circumstances or events such as vaccinations, potential health hazards related to personal and family history, and exposure to toxic chemicals.

It is estimated that the alphanumeric component of a patient's medical history will not exceed 1,000 atoms or pieces of information. An atom is considered herein to be a separate identifiable data item or point. With this assumption, the medical records of every person on the planet could currently be stored on approximately 1,000 optical disks.[0121]

While a patient interacts with the MDATA system, the system is constantly determining what questions to ask, based upon the information it has about the patient. Just as a physician gathers relevant pieces of information from his or her dialogue with a patient, the MDATA system flags and later stores all pertinent pieces of information that it learns from each interaction with its patient. Therefore, certain questions, because their answers remain the same, need not be repeated. For example, if the MDATA system learns that a patient's mother has suffered from migraine headaches, it will never have to ask for this information again.[0122]

Again, the more information the MDATA system has about a patient, the more specific is its advice. It is not uncommon for the MDATA system to give different advice to different patients calling for the same complaint. In other words, the advice given is patient-specific. Not only can the MDATA system's advice be different for different patients, but there are times when the advice given to the same patient (calling for the same complaint but at different times) is different. For example, one of a group of functions called “meta” keeps track of the number of times the MDATA system has been consulted for the same problem. Once a threshold is reached, the MDATA system advises the patient that the number of consultations alone, for the same complaint, may signify a problem. The system then makes an appropriate recommendation.[0123]

Before the MDATA system stores any information, the system verifies its accuracy. To accomplish this task, “confirmation loops” are used. Any piece of information that will become a part of the patient's medical record is sent through a confirmation loop where the system asks the patient to verify the accuracy of the information that the system has collected. The confirmation loop enables the system to verify new patient information and make corrections before it enters this information into the patient's medical record.[0124]

IV. Authoring Language

The MDATA system uses a new authoring language that is specifically designed to allow medical knowledge to be encoded into a usable computer program. The presently preferred voice response or telephony version of the MDATA system is written in object-oriented Microsoft C\C++ version 7.0. This allows the MDATA system to easily interface with industry-standard database programs, including those that are SQL-based, as well as to be portable to other operating systems. The operating system is transparent to the user.[0125]

Before the development of the MDATA system's authoring language, there was no practical way for medical experts to encode their knowledge into a meaningful, useful, and accessible structure. Although other computer languages have been used to build medical expert systems, they have almost always required a knowledge engineer and a programmer to be involved. Quite often, the knowledge encoded in these systems could only be accessed and fully understood by physicians. Typically, the programmer would try to translate the doctor's diagnostic skills and treatment rules into computer code. This separation of the physician's knowledge from the encoded treatment recommendations often engendered anxiety in the physician and has, at times, led to inaccurate treatment recommendations.[0126]

The MDATA system's authoring language, however, is designed to allow physicians to transfer their knowledge into a computer program that can be directly accessed by non-medically trained personnel. Recursive and iterative techniques are used to acquire the knowledge from the expert and assemble it in a way that allows it to be immediately transposed into the MDATA system's algorithms. Because of the simple interface of the language, and because a formula for writing the algorithms has already been developed, physicians who are not computer literate can encode their knowledge as well as understand exactly how that process takes place.[0127]

The MDATA system's authoring language allows flat information to be restructured into a hierarchical or layered format in which the arrangement of the knowledge conveys meaning. Thus, a textbook description of a disease can be transposed into a form that allows useful treatment recommendations to be made.[0128]

The new language also allows the formation of a structure in which multiple overlays of screening questions, combined with the application of recursive techniques, sequentially exclude some diagnoses while at the same time reaching treatment recommendations. The MDATA system's simplicity and elegance would not be possible without the new language.[0129]

The MDATA system's authoring language allows an algorithm programmer to retrieve information from a patient's medical record, request additional information from the patient, and guide the flow of algorithm execution based on medical history and the patient's responses. The language allows the programmer to implement an algorithm in a natural scripted style.[0130]

The course of an algorithm is determined by caller responses to questions that the MDATA system asks. For simple “yes/no” questions, the flow of interaction can be described by a binary tree. Multiple-choice questions (e.g., menus) provide multiple branches in the tree. Each question can be considered a node, and the acceptable responses to this question are branches leading to the next question (node). Using this abstraction of an algorithm, one can draw a directed graph (also known as a node map) of the nodes and branches of an algorithm, beginning with the initial question, and ending with all possible terminal points.[0131]

The node table is built in this manner:[0132]

1. An author develops an algorithm.[0133]

2. The algorithm is broken up into separate nodes.[0134]

3. A directed graph is drawn up, which is a flow chart of the algorithm's operation.[0135]

4. Each node's definition is entered into the MDATA system, either by:[0136]

a. using an ednode utility to write each node's definition into the system's machine readable node table, or[0137]

b. using an xlat utility to translate an ASCII file of human-readable node definitions into the system's machine readable node table.[0138]

Referring to FIG. 3, a process for translating a medical algorithm written in the authoring language will be described. FIG. 3 illustrates an ASCII (American Standard Code for Information Interchange)[0139]

format text file

170 as an input to atranslation utility172. An ASCII file can be created by use of a text editor or a word processing program (may need to export to the ASCII format). TheASCII file170 contains node definitions conforming to the syntax briefly described hereinbelow.

The purpose of the ASCII node definition translator utility[0140]172 (xlat.exe, along with functions in pars.c and util.c) is to convert a human-readable document into a machine readable format that the MDATA system reads at run time to process an algorithm. Thisutility172 may be considered to be a preprocessor; the translation must be accomplished prior to run time.

The output of the[0141]

utility

172 is a set of binary (NOD_BLK) records written to a node table174 (filename of node.fos), and a set of binary list files176 (in a subdirectory \list\listxx\xxyy, where xx is the first two digits of the node number, and yy are the last two digits). Fourlist files176a-176dare shown as an example. Each “list” file, e.g.,176a, contains a “next” table (i.e., the ‘next node after this one’), a message play list for this node, and a “work” list (i.e., one or more “things to do” at this node before beginning speech playback). The binary record written to the node table174 (node.fos) has fields containing the node number (which is redundant; the record's position in this file also indicates the node number), the node's “type” attribute (Menu, Link, Prompt, Yes/No, Return, Hangup) and a parent node number.

The node table[0142]174 is a table of 10,000 NOD_BLK records. This table174 is indexed by a node number, e.g., the fiftieth record corresponds tonode50. The contents of the individual node records may be viewed by selecting “Display Node” while running the ednode utility. The node records are modified by either using the ednode utility, or when translating node definitions from ASCII to the node file with the xlat utility.

One of the following keywords is necessary as the first item on each line, but only one keyword is accepted per line; any excess information will be discarded.[0143]

Node The Node keyword denotes the beginning of a new node and defines the node number.[0144]

Parent The Parent keyword defines the parent of the node being defined.[0145]

Type The Type keyword defines the class of the node being defined. Acceptable type names are:[0146]

Menu This node presents a multiple choice question.[0147]

YesNo This node presents a simple Yes/No type question.[0148]

Link No caller response is required at this node, algorithm processing will continue at a predetermined node.[0149]

Prompt This node requests some numeric information from the caller. The information is placed in a DTMF buffer which is then stored in the next node.[0150]

Return Returns from a subroutine call (e.g., after configuring a past medical history object).[0151]

Hangup The system will release this caller after it finishes speech file playback, or if the caller interrupts playback with a DTMF key press.[0152]

Wait nn This node will play the message list, then pause for the specified nonzero number of seconds before continuing.[0153]

@ The @ keyword defines the action to be taken for a response to either a Menu or YesNo type node.[0154]

Digits The Digits keyword is used in conjunction with Type Prompt to indicate the maximum number of DTMF digits to collect from the caller.[0155]

Play The Play keyword defines a play list of one or more messages to be played at this node.[0156]

Help The Help keyword defines a play list of one or more messages containing useful hints for interacting with the system. These messages provide helpful instructions for a new or confused caller.[0157]

Next The Next keyword defines the next node to jump to after the node being defined. It is used in conjunction with node types Link and Prompt.[0158]

Work The Work keyword indicates a sequence of one or more operations to perform when arriving at the node being defined. This processing occurs before speech playback begins.[0159]

A select set of math functions, relational operators, and nested if-then-else statements are supported. A pound sign (‘#’) or a hyphen (‘-’) in the first position on a new line will cause the translator to skip over the rest of the line. This is useful for inserting comments, or delimiting between individual node definitions. The translator also disregards blank lines.[0160]

In order for a node to be properly defined, a minimum number of keywords must be present for each node, and other keywords must be included depending on the node type. The minimum keyword set for a properly defined node is:[0161]

Node, Parent, Type, and Play.[0162]

Dependency rules:[0163]

(1) The Menu type requires at least an @ 1 line and an @ 2 line.[0164]

(2) The YesNo type requires an @ 1 and an @ 2 line (@ 3, etc. are ignored).[0165]

(3) The Link type requires a Next line.[0166]

(4) The Prompt type requires a Digits line and a Next line.[0167]

The first keyword in a node definition must be Node. The other keywords may be given in any order. The next occurrence of the Node keyword will invoke a completeness test. If the completeness test is successful, then the node definition is saved in machine readable (binary) format, and translation continues with the new Node line. A set of reserved language keywords is listed in Table 1.[0168]

TABLE 1


Reserved language keywords (case insensitive):

	@
	and
	digbuf
	digits
	else
	essf
	flush
	hangup
	help
	if
	keep
	link
	menu
	meta
	next
	node
	parent
	play
	pop
	prompt
	push
	reenter
	return
	test
	then
	type
	wait
	write
	work
	xor
	yesno

V. Run-Time Operation

Referring to FIG. 4, the run time interaction among the hardware and software components of the[0169]

MDATA system

100 will be described. As previously mentioned,algorithm processor160 includes the parser and supporting functions that manipulate the memory variable symbol table and the run time stack. For a selected medical algorithm, a node record is read from the node table174 and a list file is read from the plurality of list files176. The algorithm processor also interacts with the Vpro voice recognition (VR)board124 for speech recognition and with the Dialogic voice processing (VP)board122 for speech playback and DTMF detection. TheVP board122 further is interconnected with a set of speech files180 that are stored on a portion ofhard disk152 and with one of thetelephone lines106 that connects via the telephone network108 (FIG. 1) to the patient'stelephone110. TheVR board124 further connects with thevoice print vocabularies182, previously described, also stored on a portion ofhard disk152. Thealgorithm processor160 utilizes the speech recognition, speech playback, and DTMF detection resources as directed by the medical algorithm that is retrieved from the node table174 and the list files176.

Referring to FIGS. 4, 5[0170]aand5b, several data structures are utilized at run time. These data structures are described as follows:

A. Port Status Block (PSB). A port status block is created at run time for each[0171]

VP board

122 channel. The PSB contains flags, buffers and tables that hold the state information of the channel, retain responses from the caller, and keep track of where to transfer control in response to voice recognition and telephony events. The PSB keeps track of whether the caller prefers to use spoken or touch tone responses, the caller's last response, the number of consecutive errors the caller has made, and other context sensitive parameters.

B. Node Block. This[0172]

structure

196 contains the node number, the type attribute (link, menu, yes/no, hangup, prompt, wait, return) and pointers to:

a. Help list—a Play list of help information;[0173]

b. Play or Message list—a list of one or more messages or speech files to play in sequence at each node;[0174]

c. Next table or list—contains entries for each possible response to a yes/no or menu node that are evaluated at run time to determine the next node to branch to; and[0175]

d. Work list—things to do before message playback starts.[0176]

The load_node( ) routine[0177]194 in util.c builds thenode block structure196 in memory by first reading in anode record190 from the node table174. Then linked lists are attached to the pointers help, play, next and work. These lists come from the list files176, in subdirectory path \list\listxx\xxyy, where xxyy is the node number, wherein eachlist file192 is associated with a unique node.

C. Symbol Table. Each patient has their own associated symbol table. A portion of a symbol table[0178]212 is shown in FIG. 5b. The symbol table is loaded at run time with memory variables that hold patient specific data (age, sex, and items from medical history) and algorithm specific data. The items in the symbol table can be flagged for storage to the patient's medical history.

D. Run Time Stack (RTS). Each[0179]

Dialogic VP board

122 channel has a RTS associated with it. The RTS is used by the parser. The algorithm programmer can push to and pop from the RTS, e.g. to temporarily store a value of a variable.

The work list has the non-playback tasks that are performed at each node. There is one work list for each node, and it is identified with the work keyword in the ASCII node definition file. The work list may be empty. Each time the system transits to a new node, it will execute the work list. If the patient repeats a node, the system will not execute the work list again; it will simply replay the message(s). If the patient requests the[0180]

system

100 to back up the node map, the system will execute the work list of the node it backs up to. Typical tasks in the work list involve manipulating objects on the run time stack or in the symbol table, testing for the presence of memory variables, configuring past medical history or current medical condition objects, or writing database records. An example of a complex work list follows:

“Test OBJECT2; Phone=DIGBUF; Push Age”[0181]

This example tests for the presence of a patient record object labelled “OBJECT2”, loads the contents of the digit buffer into memory variable Phone, and pushes the value of memory variable Age onto the run time stack.[0182]

Each node has the “next” table or list. The next list indices range from 1 to 9, inclusive. The next list contains either a single node number, or an if expression. For all node types, except the Hangup node, there will be at least one next list:[0183]

Link and Prompt nodes: the next node is stored at[0184]table index 1.

Yes/No node: the next node for the Yes response is stored at[0185]table index 1, and the No response is stored atindex 2. This corresponds to the prompt, “if the answer is yes,press 1; if no,press 2.”

Menu node: the response number and the table index are the same. Even though the actual data structure has a ‘0’ index in the C programming language, this index is not used in the next table because a ‘0’ response is reserved for operator assistance.[0186]

Following is an example of a next list:[0187]

“If Male and Age >55 then 100 else 200” is interpreted as:[0188]

If the patient is both male and over 55 years old then go to[0189]

node

100 else go to node200.

Speech files[0190]180 may be of an arbitrary length. A message may be informational, a list of menu options, or a yes/no question. A “two paragraph” or “under one minute” limit has been adopted as a style convention for the presently preferred embodiment. Typically, a node is programmed as a sequence of Yes/No nodes, with “informational” Link nodes interspersed as needed. When there is a lengthy discussion, the speech is recorded in multiple files. To simplify algorithm programming and enhance readability (viz., eliminate long chains of link nodes), the Link node's play list may contain up to ten message numbers.

Upon arrival at a Link node, the system positions a “current message” pointer at the beginning of the play list (trivial case: single message play list; interesting case: multiple message play list). As playback proceeds, the current message pointer moves down the play list. After the system plays the last message on the list, it moves on to the next node.[0191]

If the caller issues a “backup” command, the system will move the current message pointer back one message, and resume playback. If the pointer was at the beginning of the list (e.g., trivial case), the system backs up to the previous node and places the current message pointer at the beginning of the play list. If there is more than one message in the list, the system cues the pointer to the last message in the list. The system then resumes playback. In the “pause” mode, when the caller issues the “continue” command, the system will resume playback at the current message.[0192]

The[0193]

MDATA system

100 uses three basic operating modes:

A. Real Mode—involves an actual medical problem. In this mode the[0194]

system

100 loads the past medical history, saves new past medical history objects, and writes a meta record for each algorithm consulted. The medical algorithm programmer is responsible for providing code to jump past meta analysis in Information mode.

B. Information Mode—involves a “what if” scenario. In the Information mode the[0195]

system

100 disregards past medical history, does not save newly configured past medical history objects, does not write a meta record for each algorithm consulted, and does not perform meta analysis. The patient has an option in Information mode to change the age and sex parameters to emulate a hypothetical patient.

C. Pending Mode—handles the situation when a patient's voice sample does not match the patient's reference sample. Pending mode is utilized also when an assistant is interacting with the[0196]

MDATA system

100 on behalf of a patient and both the assistant's and the patient's voice samples fail the voice printing test. In the case where the assistant's voice sample fails the voice printing test but the patient's voice sample passes the test, Pending mode is not utilized. In Pending mode, theNDATA system100 considers the patient's medical history and performs meta analysis during this consultation. However, a meta record is not written for this consultation and any new medical information gathered on this patient will not be written to the patient's medical record. The new medical information is written to a “Pending” file. The Pending file is verified off-line by a system administrator or staff person, and then is added to the patient's medical record only if the information can be verified.

One of the drawbacks of the traditional doctor-patient relationship is the short amount of time that physicians are able to spend with patients. The[0197]

MDATA system

100, however, allows patients as much time as they wish to learn about their problem as well as to obtain information on any number of other medical topics.

Through the “Information mode” feature of the[0198]

MDATA system

100, callers can learn about a disease process, an illness or the latest treatment for any disease, without adding any information to their personal medical record. Although thesystem100 keeps track of the interaction, it is labeled as an “Information mode session.” The record of the caller's path through the system is not used as the basis for any future advice, nor is it considered in generating system statistics.

The Information mode is not limited to complaints for which the[0199]

MDATA system

100 offers medical advice. Information about early detection and treatment of many other diseases as well as the latest advances in medicine can be made available through the Information mode.

Referring to FIGS. 5[0200]bthrough5g, as an example, a run time sequence of steps of how a patient may traverse a main menu node map several steps into a chest pain algorithm node map will be described. Six nodes with a portion of an associated symbol table will be discussed.

At FIG. 5[0201]b, thealgorithm processor160 loads thefirst node #100, represented bynode block210. The variables for Age, Sex, and Real mode were loaded into the symbol table212 during the login process (which will be described hereinbelow). Throughout this example, the help list is empty, i.e., no help information is played for the patient. The work list sets the Problem variable of the symbol table212 to be Menu. Then thesystem100 begins playback of message#100. This message gives the patient a menu of choices to choose from. The Digits entry equal to one means that a one digit response is expected from the patient. The patient may respond by pressing a touch tone (DTMF) key on the telephone or speak the choice response into the telephone handset microphone. In this example, the patient selects menu option “1”. The parser evaluates the Next list based on the patient selection and branches tonode #101.

At FIG. 5[0202]c, thealgorithm processor160

loads node #

101, represented bynode block214. The work list is empty, so thesystem100 goes right to playing back message#101 which presents another menu of choices to the user. The Next list has four nodes for possible branch points. In this example, the patient selects menu option “1” for a chest pain complaint. The parser evaluates the Next list based on the patient selection and branches tonode #2200.

At FIG. 5[0203]d, thealgorithm processor160

loads node #

2200, represented bynode block218. The work list command is to update the value of Problem in symbol table220 to CCHP (chest pain). Then thesystem100 begins playback of message#2200. No response is required from the patient for a Link type node. The Next list has two nodes for possible branch points depending on the value of symbol table variable Real. The parser evaluates the If expression in the Next list for the value of Real and, in this example, branches tonode #2201.

At FIG. 5[0204]e, thealgorithm processor160

loads node #

2201, represented bynode block222. The work list command is to write a Meta consultation record for future use by a Meta function. The play list is empty so no message is played. No response is required from the patient for a Link type node. The main purpose of this node is to write the Meta consultation record (because the system is currently in Real mode for this patient). The Next list has only one node so no decisions are necessary by the parser which, in this example, branches tonode #2205.

At FIG. 5[0205]f, thealgorithm processor160

loads node #

2205, represented bynode block226. The work list is empty in this node so thesystem100 goes right to playing back message#2205 which presents a yes/no type of question to the user. The Next list has two nodes for possible branch points depending on the response of the patient. In this example, the patient responds “no”, and the parser evaluates the Next list based on the patient selection and branches tonode #2210.

At FIG. 5[0206]g, thealgorithm processor160

loads node #

2210, represented bynode block230. The work list is empty in this node so thesystem100 goes right to playing back message#2210 which presents a yes/no type of question to the user. The Next list has two nodes for possible branch points depending on the response of the patient. If the patient answers “yes” to the question, the parser branches to node #2211, but if the patient answers “no” to the question, the parser branches to node #2215.

VI. Software Structure

Referring to FIG. 6, the system utilizes eight principal, separate processes and seven related databases. A[0207]

patient login process

250 is used by thesystem100 to identify a patient who has previously registered into the system by prompting for a patient identification number (PIN). Anassistant login process272 is used by thesystem100 to identify an assistant who has previously registered into the system by prompting for an assistant identification number (AIN). An assistedpatient login process276 is used by thesystem100 to identify a patient who has previously registered into the system by prompting for the patient identification number. If the caller is the patient, apatient registration process252 is used by the system to register new or first-time patients. If the caller is not the patient, anassistant registration process274 is used by the system to register new or first-time assistants. Then, if the patient is not already registered, an assistedpatient registration process278 is used by the system to register the patient. These processes will be further described hereinbelow.

Once a caller has logged in or registered, the system provides a choice of two other processes in the current embodiment. The first of these processes is the[0208]

evaluation process

254 that performs a patient diagnosis. The second of these is atreatment table process256 to obtain current treatment information for a particular disease or diagnosis. In another embodiment, other choices are added to access other medical information processes.

Associated with these eight processes are a patient and[0209]

assistant enrollment database

260, aconsultation history database262, apatient response database264, a medical history objectsdatabase266, a patientmedical history database268, a pendingdatabase269, and apatient medication database270 that are described as follows:

A. The master patient and[0210]

assistant enrollment database

260 is created at run-time by one of the registration processes252,274, or278. Thisdatabase260 is read by thepatient login process250 or the assistedpatient login process276 to validate a patient's identity at login time and by theassistant login process272 to validate an assistant's identity at login time. Thedatabase260 is essentially a master file of all registered patients and assistants indexed by their patient ID number or assistant ID number, respectively. The patient ID or assistant ID, date of birth and gender fields are entered by the on-line registration process; the system administrator manually enters the name of the patient or assistant in an off-line manner.

The patient and[0211]

assistant database

260 contains one record for each patient or assistant. Thisdatabase260 is indexed by the identification number. The system appends theenrollment database260 after a caller is successfully registered. The “next ID number” is stored in a binary file, config.fos, and is incremented after each successful registration. Each record has the following fields:



Field Name	Data Type	Width	Usage

ID	Numeric	10	IDnumber
TYPE	Character
	1	User type: “P”-patient, “A”-
			assistant
ASST_PERM	Boolean
	1	Permanent assistant flag
ASST_EXP	Date	8	Expiration for
			permanent assistant
RELATIONS	Pointer	20	Pointers to related patients/
			assistants
ORGZTN	Character	8	Organization
			alphanumeric code
NAME	Character	20	Patient/Assistantname
SEX	Character
	1	Gender
YEAR	Numeric
	4	Year ofbirth
MONTH	Numeric
	2	Month ofbirth
DAY	Numeric
	2	Day of birth
ACCESS	Date	8	Last access
RV_PATH	Character	20	Path name of recorded
			voice file

B. The consultation history or[0212]

meta database

262 is created at run-time by theevaluation process254. A consultation record contains alpha-numeric codes for the patient's complaint, the affected anatomic system and the diagnosed cause of the patient's complaint. When the meta function is invoked at run-time, it compares alphanumeric strings provided by the evaluation process with the fields of all the patient's meta records that fall within a time window specified by the evaluation process. The meta function returns the number of matches found, and an indication of the frequency of the patient's complaint.

Each patient has an individual meta file that is part of the[0213]

consultation history database

262. At the conclusion of the evaluation process and dependent on the run-time operating mode flag, the system will create a new meta record, populate its fields with the information gathered during the evaluation process, and append this record to either theconsultation history database262 or thePending file269. For example, information used in the new meta record may come from a “Write Meta” command in a node Work list. Each record has the following fields:



Field Name	Data Type	Width	Usage

DATE	Date	8	Datestamp
PROBLEM	Character
	5	Patient
			complaint/symptom
SYSTEM	Character
	5	Anatomical system affected
CAUSE	Character		5	Diagnosed cause of complaint

C. The[0214]

patient response database

264 is created at run-time by theevaluation process254. Theresponse database264 is an audit trail: each record is time stamped and registers the patient's response to each question. Thisdatabase264 can later be analyzed off-line with a database program such as FoxPro/FoxBase to reveal how the patient responded to questions during theevaluation process254, or a database program can be developed to gather response patterns and statistics and generate appropriate reports.

Each patient has a response trace file that is part of the[0215]

patient response database

264. Thesystem100 appends this response trace file with a response record every time the patient answers a question or provides algorithm-requested data. For human readability, the system also inserts “Begin Call” and “End of Call” records in this file. Each record has the following fields:



Field Name	Data Type	Width	Usage

DATE	Date	8	Date stamp MM/DD/YY
TIME	Character	8	Time stamp HH:MM:SS
NODE	Numeric	6	Current nodenumber
TYPE	Character
	5	Response type: DTMF orVOICE
RESP	Character
	5	Response command or digitstring
MODE	Character
	1	Consultation operating context
VERSION	Character	20	Version or
			Begin/End call comment
SENS_FACT	Character	20	Current sensitivity factor settings

D. The medical history objects[0216]

database

266 is an auxiliary database that supports a key feature of the MDATA system100: past medical history. The medical history objects database is a catalog of unique alphanumeric codes, each code corresponding to a medical condition or diagnosis that is not expected to change during the life of the patient (e.g., a diagnosis for asthma is coded as “RWHZAST”).

In addition to the alphanumeric codes, the[0217]

MDATA system

100 uses the “memo” field in a Foxpro database to store binary objects. Currently, these binary objects are clinical sounds obtained from the patient over the telephone.

It is anticipated, that as database technology gets more sophisticated (moving toward multi-media and so forth), it will allow storing of larger and more complicated binary files such as the following: a digitized x-ray, a digitized CAT scan, a digitized MRI scan. In addition, as video-telephone technology advances, it is anticipated that the[0218]

system

100 will store video images or even holographic images of the patient.

For every past medical condition there is a record in the medical history objects database that contains the attributes of the medical condition, and contains a pointer into the past medical history questionnaire. The attributes of a medical condition include its data type (e.g., boolean or numeric) and the number of digit positions needed to store the value of a numeric value associated with this condition (not applicable to boolean type).[0219]

The pointer field is useful for obtaining medical history at run-time. If a patient has an incomplete medical history questionnaire on file with the[0220]

MDATA system

100, then the pointer field allows the evaluation process to momentarily suspend the evaluation, go to the medical questionnaire and ask an individual question, collect and verify the patient's response, and then resume the evaluation process. This “ask-when-you-need-it” approach relieves the new patient of going through an exhaustive medical history questionnaire before the first consultation of the diagnostic process.

Each record of the medical history objects database has the following fields:[0221]



Field Name	Data Type	Width	Usage

LABEL	Character	8	Object codename
TYPE	Character
	1	Object data type
DIGITS	Numeric	3	Maximum number of digits in
			response
CALL	Pointer	6	Identifies question(s) to be asked
			to configure this object
AUDIO	Binary	N/A	Voice print
IMAGERY	Binary	N/A	Face print
RFU	Character	20	(For future use)

E. The patient medical history (PMH)[0222]

database

268 is created at run-time by theevaluation process254 or by use of a past medical history questionnaire. ThePMH database268 is read by the evaluation process during run-time. Thisdatabase268 contains each patient's individual medical history. A new patient has an option to go through the entire medical questionnaire at one time, thereby configuring all the past medical history objects listed in theobjects database266. Alternately, the new patient can bypass the questionnaire and go right into the diagnosis of a medical complaint. Then, if a medical algorithm requires a past medical history object that has not yet been configured, theevaluation process254 invokes a past medical history function before it continues with the algorithm.

Each patient has their own past medical history file, which is part of the[0223]

PMH database

268, that contains records which describe medical events or conditions from the patient's life. Thesystem100 appends a record to this file each time a past medical history object is configured for the patient. The contents of this file are installed in the symbol table when the patient logs in to thesystem100. The medical algorithm programmer is responsible for using a TEST command to verify that necessary items are present in the symbol table before algorithm execution. A side effect of a negative TEST result is that thesystem100 prompts the patient to provide that information. Thesystem100 flags any new or modified items, and asks the patient to confirm these values during an Exit Confirmation Loop which will be described hereinbelow. Each record has the following fields:



Field Name	Data Type	Width	Usage

LABEL	Character	20	The object'slabel
TYPE	Character
	1	Object data type
VALUE	Character	10	Object's configuredvalue
CERT	Numeric
	3	Certainty of object's value
DATE	Date	8	Object
			configurationdate
ICD9A	Float
	5	First ICD-9 code
.	.	.	.
.	.	.	.
.	.	.	.
ICD9E	Float		5	Fifth ICD-9 code

F. The “Pending”[0224]

database file

269 holds medical information gathered during Pending mode for offline verification. The Pending database record structure is the same as that used for the past medical history (PMH)database268. The evaluation process writes to the Pending database at run-time when it configures a new past medical history object for a patient during a Pending mode interaction. The contents of the Pending database are reviewed off-line by a staff person, and if the information is verified, the staff person appends the information to the patient's past medical history file.

G. An optional[0225]

patient medication database

270 contains a file for each patient containing information about medication they are taking, or have taken in the past. Themedication database270 is created by theevaluation process254 at run time. A “Write Drug” command builds a record and fills its fields with same-named memory variables from the symbol table. Theevaluation process254 may read themedication database270 during run time as needed. The treatment table256 optionally reads themedication database270 to determine the medication(s) being used by the patient.



Field Name	Data Type	Width

GENERIC_NAME	Character	20
TRADE_NAME1	Character	20
TRADE_NAME2	Character	20
TRADE_NAME3	Character	20
ICD-9-CM_CODE	Character	10
ICD-9-CM_ECODE	Character	10
ICD-9-CM_VCODE	Character	10
OTHER	Character	20
DOSAGE	Character	20
ROUTE_OF_—	Character	10
ADMINISTRATION
FREQUENCY	Character	10
USE	Character	20
START_DATE	Date	8
STOP_DATE	Date	8
OTHER1	Character	20
OTHER2	Character	20

VII. Top-Level Flow

Referring to FIGS. 7[0226]a,7b,7cand7d, thetop level flow300 of theMDATA system100 software will be described. The telephone number used to access theMDATA system100 may vary in various embodiments of the system. If the sponsoring agency or hospital wishes to provide access to theMDATA system100 at no cost to the caller, then a toll-free 800 service number can be used. If the sponsoring agency or hospital wishes to recover the costs of running theMDATA system100 from the caller, it may use a pay-per-call or premium charge number (e.g., 900 service). “Current Procedural Terminology” (CPT-4) codes are available to describe and bill third party payers for telephone consultations. They are a listing of the descriptive terms and identifying codes for reporting medical services and procedures. CPT-4 codes are the most widely accepted nomenclature for reporting physician services to insurance companies.

Beginning at a[0227]

start state

302, a person112 (FIG. 1) desiring medical advice calls the telephone number for theMDATA system100 on atelephone line106. The caller may be the patient or may be an “assistant”, e.g., parent, relative, or friend, that is helping the patient. Moving tostate304, thesystem100 answers the call automatically and greets thecaller112 with an introductory greeting message by playing back a speech file stored on thehard drive152 by use of theVP board122. Proceeding atstate306, theMDATA system100 asks each patient who calls the system a series of “initial screening questions.” These questions are designed to identify patients who are critically ill; they are not designed to identify the patient's problem. The initial screening questions enable the system to filter out patients who require immediate medical attention.

Moving to[0228]

decision state

308, any patient found to be critically ill is instructed to dial the emergency response telephone number “911” atstate309 or will be automatically connected to the nearest emergency medical services system in the patient's area. The telephone call is terminated by thecomputer102 atstate310. The following are examples of initial screening questions:

IS THIS A MEDICAL EMERGENCY?[0229]

ARE YOU HAVING DIFFICULTY BREATHING?[0230]

ARE YOU EXPERIENCING SEVERE PAIN OR PRESSURE IN YOUR CHEST?[0231]

If the system determines that the patient is experiencing a medical emergency, it may provide the patient with a menu of emergency medical procedures at[0232]

state

311. In situations where the patient or the caller for the patient is far from the nearest emergency help, e.g., a rural setting, the caller may need to initiate emergency procedures immediately. The menu of emergency medical procedures provides several choices to the caller. If the caller presses touch tone key “1” or speaks the word “one” into the telephone mouthpiece, thecomputer102 branches tostate312 wherein well known CPR (cardiopulmonary resuscitation) information is recited. If the caller has a speakerphone capability associated with thetelephone110 being used, the caller may be able to listen to and perform the instructions given by thesystem100 in a hands-free manner away from the telephone. If the caller presses touch tone key “2” or speaks the word “two” into the telephone mouthpiece, thecomputer102 branches tostate313 wherein well known Heimlich Hug information for choking is recited. At the completion of eitherstate312 orstate313, the telephone call ends atstate314.

If the patient is determined at[0233]

state

308 not to have a medical emergency, i.e., theMDATA system100 is satisfied that no immediately life threatening condition is present, thecomputer102 moves to adecision state315 to determine if the caller is the actual patient. If so, thecomputer102 proceeds to adecision state316 to determine if the patient has previously registered or ever consulted with thesystem100, i.e., is not a new or first-time caller. If so, thesystem100 verifies the patient's identification and retrieves their medical record at thepatient login process250, which will be further described hereinbelow. At the completion ofprocess250, thecomputer102 proceeds through off-page connector C317 to state344 (FIG. 7d). If the patient is not registered, theMDATA system100 proceeds to thepatient registration process252 for a new patient, which will be described hereinbelow. At the completion ofprocess252, thecomputer102 proceeds through off-page connector C317 tostate344 on FIG. 7d.

If the caller is not the patient, as determined at[0234]

state

315, thecomputer102 proceeds through off-page connector A318 tostate320 on FIG. 7b. There will be times when the patient may not be able to use theMDATA system100 directly, e.g., due to injury, weakness or altered level of consciousness. In these cases, an “assistant” may interact with the system on behalf of the patient.

An assistant registers with the system through the[0235]

assistant registration process

274 which will be described hereinbelow. The assistant registration record is identical to the patient registration record in structure, but three fields have special significance for an assistant: ASST_PERM, ASST_EXP, and RELATIONS. The ASST_PERM field is a boolean flag that can only be set true off-line by the system administrator who has verified, through separate means, that a relationship exists between a patient and an assistant. The relationships are one-to-many, i.e., a patient may have one or more assistants, and an assistant may be related to more than one patient. The ASST_PERM flag may also be constrained by the ASST_EXP field, which contains a timestamp for the expiration of the ASST_PERM attribute. If the ASST_PERM flag is true, then the RELATIONS pointers will point to one or more patient records for whom this assistant is a “permanent assistant;” otherwise the RELATIONS field will be empty.

The medical information gathered during an assisted consultation is written to the patient's medical record only if the following three conditions are met:[0236]

(a) the assistant's ASST_PERM flag is True[0237]

(b) the ASST_EXP timestamp has not been reached[0238]

(c) the assistant has a relationship pointer to the patient record[0239]

If any of these conditions are not met, then any new medical information gathered on this patient will be saved to the[0240]

Pending file

269 for off-line verification by the system administrator.

The[0241]

system

100 establishes atstate315 whether the caller is the patient, or an assistant. If the caller is not the patient, then the system asserts that the caller is an assistant and, at adecision state320, determines if the assistant is registered. If the assistant is not already registered with the system, the system enrolls the new assistant at theassistant registration process274. If the assistant is already registered with thesystem100, thecomputer102 performs theassistant login process272. At the completion of eitherprocess272 orprocess274, thecomputer102 advances to adecision state321.

If the patient is not already registered with the[0242]

system

100, as determined atdecision state321, then the system allows the assistant to register a new patient at the assistedpatient registration process278. However, if the patient is already registered with thesystem100, as determined atstate321, thecomputer102 performs the assistedpatient login process276. At the completion ofprocess278 orprocess276, thecomputer102 proceeds through off-page connector B327 to adecision state334 on FIG. 7c.

At[0243]

decision state

334, thecomputer102 determines if the patient's date of birth is in the patient's medical record. If so, the computer proceeds through off-page connector C317 tostate344 on FIG. 7d. If not, thesystem100 attempts to get the patient's date of birth. Moving tostate335, thesystem100 asks the assistant if the patient's date of birth is known. If so, thecomputer102 advances tostate336 to request the patient's date of birth. Atstate337, thesystem100 recites the patient's date of birth obtained atstate336. At adecision state338, the assistant determines if the date of birth is correct as recited by thesystem100. If not, thecomputer102 loops back tostate336 to request the patient's date of birth again. If the patient's date of birth is correct, as determined atstate338, thecomputer102 flags the date of birth for saving in the patient's medical record atstate339, and proceeds tostate344 on FIG. 7d.

If the patient's date of birth is not known, as determined at[0244]

state

335, thecomputer102 proceeds tostate340 wherein the system requests the assistant to provide an approximate age of the patient. The age is an important parameter used in theevaluation process254 and treatment table256. Atstate341, thesystem100 recites the patient's approximate age obtained atstate340. At adecision state342, the assistant determines if the age is correct as recited by thesystem100. If not, thecomputer102 loops back tostate340 to request the patient's approximate age again. If the patient's approximate age is correct, as determined atstate342, thesystem100 advises the assistant atstate343 to get the patient's actual date of birth before the next consultation, and proceeds tostate344 on FIG. 7d. Thesystem100 uses the approximate age in the consultation during theevaluation process254 and the treatment table256.

At[0245]

state

344 on FIG. 7d, thesystem100 presents the caller with a system selection menu. Here, the caller is asked to select from among four choices: diagnostic system, treatment table, a future process/function, or end call as described below:

A. Diagnostic System: The system starts the[0246]

evaluation process

254 at a menu, where it asks the patient to begin identification of the complaint.

B. Treatment Table: The system takes the patient to the[0247]

treatment table process

256 at a menu, where it asks the patient to select a treatment selection method.

C. Future Process/Function: A future process or function[0248]280, undefined in the present embodiment, that reads and/or writes the databases shown in FIG. 6.

D. End Call: The system performs several steps and then terminates the telephone call.[0249]

In either[0250]

process

254 or256, thecomputer102 functions as an interpreter as performed byalgorithm processor160 in following the node map created by the algorithm programmer. At the exit point of theevaluation process254, thesystem100 gives the patient the option of selecting another complaint. At the end of thetreatment table process256, the system gives the patient the option of selecting another treatment.

At the completion of the[0251]

evaluation process

254,treatment table process256, orfuture process280, thesystem100 loops back tostate344 and recites the system selection menu to the caller. If the caller chooses the End Call selection atstate344, theMDATA system100 moves to adecision state345. Atdecision state345, thesystem100 determines ifprocess254,process256, orprocess280 did not occur in Information mode, i.e., did occur in either Real mode or Pending Mode, and examines the patient's symbol table to determine if any of the configured memory variables are past medical history conditions that need to be saved to the patient's medical history file. If both conditions are true atstate345, thesystem100 advances to adecision state346 to determine if the consultation is being performed in Real mode. If not, the consultation is being performed in Pending mode, and thesystem100 then writes any new patient information obtained during the consultation to thePending file269. Ifstate346 proves to be true, i.e., Real mode, for each past medical condition that needs to be saved, theMDATA system100 asks the patient atstate348 to grant permission to save the datum to the patient's medical history file and to confirm that the datum is correct. For example, during a consultation for cough, theMDATA system100 learned that the patient has been diagnosed as being HIV positive. Thesystem100 will ask, “May I record the information about your HIV diagnosis in your medical record?” If the patient responds “yes”, then thesystem100 will ask, “Please verify that your diagnosis for HIV was positive, is this correct?” If the patient responds “yes”, then thesystem100 writes this fact to the patient's medical history file. After confirmation, each data item is stored in the patient's file in the patient medical history database268 (FIG. 6).

At the completion of either updating the[0252]

history database

268 atstate348,state345 proves to be false, or at the completion ofstate347, thesystem100 moves to adecision state349. Before theMDATA system100 ends the consultation with the patient, it presents a summary of all the advice it has given. The patient is asked to write down and repeat back the key points. TheMDATA system100 then gives the patient the option of receiving a summary of the consultation session and specific recommendations provided by the system by either facsimile or first class mail. If a fax is desired, thesystem100 asks the patient for a fax number atstate350. The patient also has the option to send a summary of the consultation to his or her health care provider or specialist. Proceeding tostate351, thecomputer102 adds the transcript of the current telephone session to a fax queue for subsequent transmission. At the completion ofstate351 or if thesystem100 determined atstate349 that the session transcript was not to be faxed, the telephone call is terminated atstate352.

VIII. Login Process

Referring now to FIGS. 8[0253]aand8b, thepatient login process250 defined in FIG. 7awill be described. Thisprocess250 is called if the patient has previously called and registered with thesystem100. Beginning at astart state358, thecomputer102 moves tostate359 and initializes a match flag to true. The match flag is checked later in thisprocess250 in conjunction with setting the mode of the consultation. Proceeding tostate360, thecomputer102 prompts the patient for the patient ID (identification) number (PIN) that is assigned during the registration process. Thepatient registration process252 will be described in conjunction with FIGS. 9aand9b. Proceeding to adecision state361, thecomputer102 determines whether the PIN is valid. If not, thecomputer102 determines, at adecision state362, if less than three tries at entering the PIN have been attempted. If so, thecomputer102 loops back tostate360 to repeat the request for the PIN. However, if three attempts at entering the PIN have been made, as determined atstate362, thecomputer102 plays a polite message that advises the patient that the login attempt failed and terminates the call atstate363. Thecomputer102 reports the failed login attempt to the system administrator at the sponsoring agency, hospital or other organization. The patient is allowed to reregister as a new patient, however, to permit access to the needed medical information. The system administrator resolves this type of situation off-line.

If the patient has correctly entered a valid PIN, as determined at[0254]

state

361, thecomputer102 moves to adecision state364 to determine if the patient identified by the PIN has a voice print or sample voice waveform on file in thesystem100. If not, thecomputer102 proceeds tostate365 to record the voice print of the patient, e.g. the patient's pronunciation of his or her full name. The patient's voice print may not be on file, for example, if the patient could not provide a voice print during the assistedpatient registration process278 in a prior consultation. At the completion of recording the voice print atstate365, thecomputer102 advances tostate366 wherein the match flag is set to false to indicate that the patient's voice print was recorded during the current login.

If the patient identified by the PIN has a voice print on file in the[0255]

system

100, as determined atstate364, thecomputer102 proceeds tostate367 and prompts the patient to pronounce his or her full name. Moving to adecision state368, thecomputer102 determines whether the voice sample obtained atstate367 passes the matching criteria. If not, the computer proceeds tostate369 and recites a message that the current voice sample does not pass the matching criteria. In the presently preferred embodiment, the current voice sample is compared to the reference voice sample recorded during thepatient registration process252 or the assistedpatient registration process278. Because the voice samples did not match, as determined atstate368, thecomputer102 sets the match flag to false atstate370. In this case, the match flag is set to false to indicate that one of the security checking methods has failed. However, theprocess250 continues atstate372 after the match flag is set to false at either

state

366 or370.

If the voice sample passed the matching criteria at[0256]

state

368, thecomputer102 advances tostate371 and recites a message that the current voice sample passed the matching criteria. This security check condition is now satisfied, and the match flag remains set to true. At the completion ofstate371 thecomputer102 moves tostate372. Atstate372, thecomputer102 verifies the sex and age of the patient by reciting the sex and age, as stored in the enrollment database260 (obtained during the patient registration process252), to the patient. At adecision state373, the patient responds to the correctness of the recited information. If the sex or birth date information is not correct, thecomputer102 moves tostate374 to request the correct information. Thecomputer102 then proceeds back tostate372 to verify the information received atstate374. If the result of thedecision state373 is true, i.e., the sex and age are correct, the computer moves through off-page connector A375 to adecision state376 on FIG. 8bto determine if the patient desires to conduct the telephone session in Real mode or Information mode. If Information mode is desired, thecomputer102 moves to adecision state377 to determine if the patient's sex and age are to be used during the Information mode consultation. If not, thecomputer102 moves tostate378 to request an age and sex to use in a hypothetical situation during the Information mode session. Moving to adecision state379, thecomputer102 recites the sex and age obtained atstate378, and asks the patient to confirm that this information is correct. If not, thecomputer102 moves back tostate378 to request the age and sex again. Whendecision state379 is true or the patient's age and sex are to be used during this consultation, as determined atstate377, thecomputer102 moves tostate380 and sets the operating mode to be Information mode.

If[0257]

decision state

376 is determined to be Real mode, thecomputer102 moves to adecision state381 to check if the match flag is true. If not, thesystem100 advises the patient, atstate382, that the current consultation is to be performed in Pending mode. The operating mode is set to be Pending mode atstate383. If the match flag is true, as determined atstate381, thecomputer102 sets the operating mode to be Real mode atstate384.

At the completion of setting the operating mode at either[0258]

state

380,state383, orstate384, the computer moves to adecision state386. Atdecision state386, thecomputer102 determines if the patient desires to review the touch tone commands described during the registration process. If so, thecomputer102 advances tostate388 and recites the touch tone commands. At the completion ofstate388 or if the patient did not wish to review the touch tone commands, thecomputer102 proceeds to adecision state390 wherein thecomputer102 determines if the patient desires to review the voice keywords described during the registration process. If so, thecomputer102 advances tostate392 and recites the voice keywords. At the completion ofstate392 or if the patient did not wish to review the voice keywords, thecomputer102 proceeds to adecision state394 wherein thecomputer102 determines if the patient desires to enable prompting. If so, thecomputer102 advances tostate396 and enables prompting. If not, prompting is disabled atstate398. To “enable prompting” means that the patient would like to be prompted for responses. This is referred to as “hard” prompting, since this will remain in effect for the duration of the call. If hard prompting is off, and thesystem100 has difficulty recognizing patient responses, thecomputer102 turns on “soft” prompting. After the next successful recognition, thecomputer102 turns off soft prompting. At the completion of

state

396 or398, thecomputer102 returns atstate400 to the top level flow (FIG. 7).

Referring now to FIGS. 12[0259]aand12b, theassistant login process272 defined in FIG. 7bwill be described. Thisprocess272 is called if the assistant has previously called and registered with thesystem100. Beginning at astart state940, thecomputer102 moves to astate942 and prompts the assistant for the assistant ID (identification) number (AIN) that is assigned during the registration process. Theassistant registration process274 will be described in conjunction with FIGS. 14aand14b. Proceeding to adecision state944, thecomputer102 determines whether the AIN is valid. If not, thecomputer102 determines, at a decision state946, if less than three tries at entering the AIN have been attempted. If so, thecomputer102 loops back tostate942 to repeat the request for the AIN. However, if three attempts at entering the AIN have been made, as determined at state946, thecomputer102 plays a polite message that advises the assistant that the login attempt failed and terminates the call atstate948. Thecomputer102 reports the failed login attempt to the system administrator at the sponsoring agency, hospital or other organization.

If the assistant has correctly entered a valid AIN, as determined at[0260]

state

944, thecomputer102 proceeds tostate950 and prompts the caller to pronounce his or her full name. Moving to adecision state951, thecomputer102 determines whether the voice sample obtained atstate950 passes the matching criteria. If not, the computer proceeds tostate952 and recites a message that the current voice sample does not pass the matching criteria. In the presently preferred embodiment, the current voice sample is compared to the reference voice sample recorded during theassistant registration process274. Because the voice samples did not match, as determined atstate951, thecomputer102 sets the operating mode to Pending atstate953. In this case, Pending mode is set to indicate that one of the security checking methods has failed. However, theprocess272 continues atstate960 on FIG. 12bafter Pending mode is set atstate953.

If the voice sample passed the matching criteria at[0261]

state

951, thecomputer102 advances tostate954 and recites a message that the current voice sample passed the matching criteria. This security check condition is now satisfied. Next, three additional checks are performed on the assistant identified by the AIN obtained atstate942. At adecision state955, thecomputer102 determines if the permanent assistant flag is true, as stored in the patient andassistant enrollment database260. If so, thecomputer102 advances to adecision state956 to determine if the expiration date for the permanent assistant is in the future, i.e., the expiration date has not been reached yet. If so, thecomputer102 advances to adecision state957 to determine if a relationship exists between the assistant and a patient, i.e., the assistant has a relationship pointer to the patient record. If so, the operating mode is set to Real atstate958, and then thecomputer102 advances through off-page connector A959 tostate960 on FIG. 12b. However, if any of the decision states955,956, or957 prove to be false, thecomputer102 moves tostate953 wherein the operating mode is set to Pending.

[0262]

States

960 through964 are similar tostates372 through374 of the patient login process250 (FIG. 8). Because of this similarity, only significant differences are discussed in the interest of avoiding repetitiveness.

States

960,962 and964 verify the assistant's age and sex, rather than the patient as in

states

372,373 and374.States966 through980 are similar tostates386 through400 of the patient login process250 (FIG. 8b). The main distinction is that states966-980 pertain to the assistant and states386-400 pertain to the patient.

Referring now to FIGS. 13[0263]aand13b, the assistedpatient login process276 defined in FIG. 7bwill be described. Thisprocess276 is called if both the patient and the assistant have previously called and registered with thesystem100. This process allows the patient flexibility by permitting the assistant to provide help during the login and subsequent consultation. Beginning at astart state990, thecomputer102 moves astate992 and prompts the assistant for the patient ID (identification) number (PIN) that is assigned during the registration process. As previously defined in FIG. 7, the assistedpatient registration process278 is called if the patient is not already registered.Process278 will be described in conjunction with FIGS. 15aand15b. Proceeding to adecision state994, thecomputer102 determines whether the PIN is valid. If not, thecomputer102 determines, at adecision state996, if less than three tries at entering the PIN have been attempted. If so, thecomputer102 loops back tostate992 to repeat the request for the PIN. However, if three attempts at entering the PIN have been made, as determined atstate996, thecomputer102 plays a polite message that advises the caller that the login attempt failed and terminates the call atstate998. Thecomputer102 reports the failed login attempt to the system administrator at the sponsoring agency, hospital or other organization. If the assistant doesn't know the PIN and the patient cannot provide it, the assistant is allowed to reregister the patient as a new patient atprocess278 to permit access to the needed medical information. In this case, the assistant may have to estimate the age of the patient if the patient has, for example, an altered state of consciousness. The system administrator resolves the record-keeping in this situation off-line.

If the assistant has correctly provided a valid PIN to the[0264]

system

100 atstate994, thecomputer102 moves to adecision state993 to determine if the patient identified by the PIN has a voice print or sample voice waveform on file in thesystem100. If not, thecomputer102 moves to adecision state1003 to determine if the patient can provide a voice sample. If not, thecomputer102 proceeds through off-page connector B997 tostate1008 on FIG. 13b. If the patient can provide a voice sample, as determined atstate1003, thecomputer102 moves tostate995 to record the voice print of the patient, e.g. the patient's pronunciation of his or her full name. The patient's voice print may not be on file, for example, if the patient could not provide a voice print during the assistedpatient registration process278 in a prior consultation. At the completion of recording the voice print atstate995, the computer proceeds through off-page connector B997 tostate1008 on FIG. 13b.

If the patient identified by the PIN has a voice print on file in the[0265]

system

100, as determined atstate993, thecomputer102 proceeds tostate999 and asks whether the patient can provide a voice sample to the system. If not, thecomputer102 proceeds through off-page connector B997 tostate1008 on FIG. 13b.

States

1000,1002,1004,1006 are similar to

states

367,368,369,371, respectively, of the patient login process250 (FIG. 8). Because of this similarity, only significant differences are discussed in the interest of avoiding repetitiveness. At the completion ofstate1004, i.e., the patient's voice sample does not pass the matching criteria, thecomputer102 proceeds through off-page connector B997 tostate1008 on FIG. 13b. At the completion ofstate1006, i.e., the patient's voice sample does pass the matching criteria, thecomputer102 proceeds through off-page connector A1001 tostate1005 on FIG. 13b.

At the completion of[0266]

state

995, i.e., the patient's voice print is recorded,state999 orstate1003, i.e., the patient cannot provide a voice sample, orstate1004, i.e., the voice sample match fails, the system continuesprocess276 atstate1008 on FIG. 13b. For the three situations just described in thisprocess276, thecomputer102 sets the operating mode to Pending atstate1008. Thesystem100 then advises the caller atstate1009 that new patient information will not be saved to the patient's medical record because the consultation is in Pending mode until the information is verified off-line.

At the completion of[0267]

state

1006, i.e., the voice sample passes, thecomputer102 continuesprocess276 atstate1005 wherein the operating mode is set to Real. Thesystem100 then advises the caller atstate1007 that new patient information will be saved to the patient's medical record.

At the completion of[0268]

state

1009 orstate1007, thecomputer102 moves tostate1010.

States

1010,1012 and1014 verify the patient's age and sex, similar to

states

372,373 and374 (FIG. 8).States1016 through1030 are similar tostates386 through400 of the patient login process250 (FIG. 8). The main distinction is that states1016-1030 are directed to the assistant and states386-400 are directed to the patient.

IX. Registration Process

Referring now to FIGS. 9[0269]aand9b, thepatient registration process252 defined in FIG. 7awill be described. Thisprocess252 is called if the patient has not previously called and registered with thesystem100. During the first consultation, theMDATA system100 obtains the patient's age and sex. This is the minimum amount of information that the MDATA system requires in order to give medical advice. The more information the MDATA system has about a patient, however, the more specific is its advice.

The[0270]

MDATA system

100 assigns each of its patients a unique patient identification number. In addition, when a patient initially registers, the patient's own pronunciation of his or her name is recorded, digitized and saved to their medical record. Then, when the patient calls back, the previous recording is retrieved and the patient is asked to repeat their name exactly as they did during registration. The two recordings are then compared to see if they match. This use of “voice printing” helps to further ensure the security and confidentiality of a patient's medical record.

Beginning at a[0271]

start state

420, thecomputer102 proceeds tostate422, requests the sex of the patient, and verifies by repeating the response given by the patient. Moving to adecision state424, the patient responds by indicating to thesystem100, via touch tone key or a voice response, whether the repeated information is correct. If not, thecomputer102 loops back tostate422 to request the information again. When the information is correct atstate424, thecomputer102 proceeds to

states

426 and428 to request and verify the birth date of the patient in a similar fashion to

states

422 and424.

When the[0272]

decision state

428 is determined to be true, thecomputer102 proceeds tostate427 and requests the patient to pronounce his or her full name. Moving tostate429, the full name is digitized and stored in a subdirectory on the hard drive152 (FIG. 1) indexed by a Patient Identification Number (PIN). File names are of the form: <PIN>.vox. Thecomputer102 accesses a file to retrieve the next available PIN. The path name to the recorded voice file is saved in the patient's record in theenrollment database260. In subsequent telephone sessions with thesystem100, the patient's voice waveform will be compared to the recorded voice waveform for security and other optional purposes. When the voice waveform is stored, thecomputer102 moves tostate431 and provides the PIN to the patient. The patient is informed of the importance to save the PIN for use in future consultations with thesystem100.

At the completion of[0273]

state

431, thecomputer102 moves to adecision state430 to determine if the patient has a MDATA system user pamphlet available. If so, thecomputer102 moves tostate436 and requests the patient to turn to the pamphlet page that documents the touch tone keys, voice keywords, and modes. If not, thecomputer102 moves to adecision state432 to determine if the patient would like thesystem100 to pause to enable the patient to get paper and a writing instrument for writing user instructions. If so, thecomputer102 pauses atstate434 for 30 seconds. At the completion of the pause atstate434, if the user did not desire a pause atstate432, or after the patient is instructed to turn to the proper page of the pamphlet, thecomputer102 proceeds tostate440 of FIG. 9bvia the off-page connector A438.

At[0274]

state

440, thesystem100 provides an explanation of the touch tone keys to the patient. These keys were described above in relation to the discussion on Voice Keywords and DTMF Command Keys. Moving tostate442, thecomputer102 asks if the patient desires to hear the explanation of keys again. If so, thecomputer102 repeatsstate440. If not, thecomputer102 advances tostate444 wherein an explanation of the voice keywords is provided to the patient. These keywords were previously described above. Moving tostate446, thecomputer102 asks if the patient desires to hear the explanation of keywords again. If so, thecomputer102 repeatsstate444. If not, thecomputer102 advances tostate448 wherein an explanation of Real and Information modes is provided to the patient. These modes were previously described above. Moving tostate450, thecomputer102 asks if the patient desires to hear the explanation of the modes again. If so, thecomputer102 repeatsstate448. If not, thecomputer102 advances tostate452 wherein a summary of new user information is recited to the patient. The summary includes a recap of the two methods of controlling the system: voice key words and DTMF, and the two interaction modes: Real and Info. Thecomputer102 returns atstate454 to the top level flow (FIG. 7).

Referring now to FIGS. 14[0275]aand14b, theassistant registration process274 defined in FIG. 7bwill be described. Thisprocess274 is called if the caller is not a registered patient and has not previously called and registered as an assistant with thesystem100.States1050 through1090 are similar tostates420 through454 of the patient registration process252 (FIG. 9). Because of this similarity, only significant differences are discussed in the interest of avoiding repetitiveness.

States

1052,1056,1060,1062 and1064 pertain to the assistant rather than the patient as in

states

422,426,427,429 and431 (FIG. 9a), respectively.State1060 records the assistant's pronunciation of his or her full name andstate1062 saves it in the patient andassistant enrollment database260. Thesystem100 provides an assistant identification number (AIN) atstate1064. The AIN is used similarly to the PIN in the access of files or records. The remaining states1066-1090 are directed to the assistant also.

Referring now to FIGS. 15[0276]aand15b, the assistedpatient registration process278 defined in FIG. 7bwill be described. Thisprocess278 is evoked if the caller is not the patient and the patient has not previously called and registered with thesystem100.States1110 through1150 are similar tostates420 through454 of the patient registration process252 (FIG. 9). Because of this similarity, only significant differences are discussed in the interest of avoiding repetitiveness. The main difference is that the assistant is interacting with thesystem100 on behalf of the patient during thisprocess278, and therefore, the operating mode is set to Pending atstate1111.

States

1112 and1116 obtain the patient's sex and age, respectively. If the patient cannot provide the age to the assistant and the system, the assistant provides an estimated age. The estimated age can be corrected during a subsequent consultation with thesystem100. Atstate1119, thesystem100 asks whether the patient can provide a voice sample of his or her full name. If so, the voice waveform is recorded and saved in enrollment database260 (FIG. 6) at

states

1120 and1122. If the patient cannot provide a voice sample atstate1119, thesystem100 informs the assistant, atstate1121, that the patient's voice sample will be requested during the subsequent consultation. Then, whether or not a voice sample is recorded, thesystem100 provides a patient identification number (PIN) of the patient to the assistant and the patient (if coherent) atstate1123. The caller is instructed to safeguard the PIN for future consultations by either the patient or the assistant on behalf of the patient. If the assistant and/or patient desires to hear the PIN again, as determined at adecision state1124, thecomputer102 repeats the PIN atstate1123. Thecomputer102 proceeds through off-page connector A1125 to adecision state1126 on FIG. 15b. The remaining states1126-1150 inprocess278 are directed to the assistant rather than the patient, as in states430-454 of process252 (FIG. 9).

X. Evaluation Process

Referring now to FIGS. 10[0277]aand10b, theevaluation process254 defined in FIG. 7dwill be described. Thisprocess254 is called if the patient has selected the Diagnostic System choice in the system selection menu (FIG. 7d, state344). Beginning at astart state470, the computer moves tostate471 and recites a identification method menu to request complaint identification. After the initial screening questions (state306, FIG. 7a) are completed and a medical record (registration function252) has been opened, theMDATA system100 asks the patient to describe the complaint. The identification of the patient's problem is one of the most important steps in the evaluation process. Thesystem100 has built-in safeguards to ensure that the patient understands the questions and that theMDATA system100 understands the patient's complaint. For example, the system keeps tables of synonyms so that any problem regarding the semantics of a question or a response can be quickly resolved. The complaint may be identified in one of four ways: byanatomic system472, bycause476, byalphabetic groups480 or bycatalog number482.

The easiest and most frequently used way to identify the complaint is by anatomic system, i.e., “what system is your problem in?”.[0278]

Anatomic system

472 refers to basic body systems such as cardiovascular, respiratory, nervous system, digestive, ear/nose/throat, ophthalmology, gynecology/obstetrics, urology, blood/hematology, skin, and endocrine. After the patient has identified the anatomic system of their complaint, they are asked a series of “System Screening Questions” atstate473. For each anatomic system, there are some symptoms or combinations of symptoms that, if present, would mandate immediate intervention, such that any delay, even to go any further through the menuing process, could cause harm. For example, if the patient has identified the cardiovascular system as the anatomic system in which his or her complaint lies (i.e., chest pain), theMDATA system100 will ask the cardiovascular system screening questions. For example, the patient would be asked, “Do you have both pressure in your chest and shortness of breath? If these symptoms are present together, immediate intervention is necessary. With the thrombolytic agents that are available today, time is critical in order to save myocardial cells. Just a few minutes can mean the difference between being able to resuscitate a patient or not.

Therefore, at[0279]

state

474, thesystem100 determines if a serious medical condition exists. If so, thesystem100 moves tostate486, plays a message that advises the patient to seek immediate medical attention and ends theevaluation process254 at aterminal state488. If it is determined atstate474 that a serious medical condition does not exist, thesystem100 proceeds to a complaint menu atstate475 and recites a list of algorithms dealing with the problem that corresponds to the anatomic system selected. The patient then selects an algorithm from the list.

If the patient is not sure of the anatomic system, the[0280]

system

100 attempts to identify the problem by requesting the cause. Cause476 refers to a cause for an illness or disease such as trauma, infection, allergy/immune, poisoning, environmental, vascular, mental, genetic, endocrine/metabolic, and tumor. Once the patient has identified what they think is the cause of their problem (e.g., trauma, infection), theMDATA system100 asks the “Cause Screening Questions” atstate477. These questions are asked to make sure that the patient is not suffering from an immediate life-threatening problem. For example, if infection were chosen as the cause, the system would first rule out the possibility of epiglottitis or meningitis before proceeding. Therefore, atstate478, thesystem100 determines if a serious medical condition exists. If so, thesystem100 moves tostate486, plays a message that advises the patient to seek immediate medical attention and ends theevaluation process254 at aterminal state488. If it is determined atstate478 that a serious medical condition does not exist, thesystem100 proceeds to a complaint menu atstate479 and recites a list of algorithms dealing with the problem that corresponds to the cause selected. The patient then selects an algorithm from the list.

[0281]

Alphabetic groups

480 lists the items in the anatomic system group and the cause group together in alphabetic order. Moving tostate481, the system determines if the selected item is from the cause subgroup of the combined alphabetic groups. If so, thesystem100 proceeds to the “Cause Screening Questions” atstate477. If not, the system moves to the “System Screening Questions” atstate473.

Enter[0282]

Catalog number state

482 refers to the ability of the patient to select and enter an individual medical algorithm from a catalog of medical algorithms listed in the patient guide distributed to all patients. At the completion of

state

475,479, or482, the complaint has been identified, and thecomputer102 proceeds tostate483 wherein a series of “initial” problem screening questions are presented to the patient. There is a different set of problem screening questions for every complaint for which advice is offered.

For the purpose of this discussion, “Headache” will be used as an example to describe how the system approaches the diagnosis of a problem and provides treatment recommendations. As with many problems, there are some causes of headache that require immediate medical attention. Quite often, when a problem is very serious, any delay, even to discuss it further, can adversely affect the patient's outcome. The problem screening questions identify, at a[0283]

decision state

484, the subset of patients whose headaches may require immediate medical care. If a serious medical condition exists, the patient is advised to seek immediate medical attention atstate486. Thecomputer102 then ends the evaluation process atstate488 and returns tostate344 in FIG. 7d.

The following is an example of a problem screening question for headache:[0284]

ARE YOU CONFUSED, LETHARGIC, OR LESS ORIENTED THAN USUAL?[0285]

By asking a question about the patient's level of consciousness, a dilemma has been confronted. What does the[0286]

MDATA system

100 do about the patient whose problem itself prevents them from appropriately responding to questions or following advice?

There are some conditions that, by their very nature, may prevent patients from answering questions correctly. For this reason, the[0287]

MDATA system

100 utilizes a “mental status examination”function508. The mental status examination is a series of questions used to assess the patient's orientation. Thisfunction508 allows theMDATA system100 to assess the patient's ability to respond to questions and to follow advice. Although only shown in FIG. 10b, the mentalstatus examination function508 is incorporated into the dialogue of any problem whose presentation could include an altered level of consciousness.Function508 will be further described in conjunction with FIG. 16.

The[0288]

MDATA system

100 will, of course, be accessed by patients in whom an altered level of consciousness is not expected based on the problem that the patient has. Thesystem100 does anticipate the possibility of the patient having an altered level of consciousness in some problems, e.g., when a patient consults the system for striking his or her head, and invokes the mentalstatus exam function508. However, an intoxicated patient, calling for some other complaint, e.g., a sprained ankle, is one example where the patient may not be able to understand instructions from thesystem100. For this reason, the MDATA system also utilizes a “semantic discrepancy evaluator routine” (SDER)function510. The SDER function provides information to the patient and then, after a predetermined period of time, asks the patient to repeat or select the information. The patient's answer is then evaluated withinsystem100. If discrepancies are determined, the system automatically invokes the mentalstatus examination function508. In another embodiment, thesystem100 asks the patient for some information in different ways at different times, and then compares the patient's responses to determine if they are consistent. If not, the system automatically invokes the mentalstatus examination function508. Although only shown in FIG. 10b, theSDER function510 is embedded throughoutsystem100, and is randomly evoked by thecomputer102.Function510 will be further described in conjunction with FIG. 17.

Continuing with the headache example at[0289]

state

483, theMDATA system100 asks the next problem screening question in order to help exclude the possibility of meningitis, a very serious infection of the central nervous system.

IS BENDING YOUR NECK FORWARD SO THAT YOUR CHIN TOUCHES YOUR CHEST EITHER PAINFUL OR NOT POSSIBLE?[0290]

If the answer to this question is “yes”, a serious medical condition exists at[0291]

state

484 and thesystem100 instructs the patient to seek immediate medical attention atstate486.

The initial screening questions ([0292]

state

306, FIG. 7a) and the problem screening questions (state483) can usually be completed within a minute or so. Once theMDATA system100 has excluded the causes of headache that require immediate medical attention, the system becomes a little less formal and more conversational in the subsequent states. The examples given, of course, do not represent all the initial or problem screening questions.

If no serious medical condition exists, as determined at[0293]

state

484, thecomputer102 proceeds to adecision state490 wherein thesystem100 identifies those patients who are “re-entering” the system from an earlier consultation. This occurs most frequently when thesystem100 needs to monitor a patient's symptom over time, or if the system is initially unable to make a specific diagnosis and would like the patient to re-enter the system again, typically within a few hours. The system sets an internal re-enter flag to identify the situation where a patient is calling again for the same complaint. If the flag is set atstate490, thecomputer102 proceeds tostate492 and branches to a re-enter point in the evaluation process depending on which medical algorithm has been evoked. Thecomputer102 moves via off-page connector A494 to state506 (FIG. 10b) to the appropriate re-enter point.

If the re-enter flag is not set, as determined at[0294]

state

490, thecomputer102 moves via off-page connector B496 to adecision state499 to determine if the consultation is being performed in Real mode or Pending mode. If not (i.e., the consultation is in Information mode), the computer proceeds tostate506 to continue the evaluation process. If the consultation is in Real or Pending mode, thecomputer102 calls a “meta”function500 wherein patients are subjected to several “meta” analyses. This concept will be explained in conjunction with FIG. 11, but, in general, it refers to the system's ability to evaluate the patient's present problem in the context of their past use of the system. The Meta function500 matches various parameters against a predetermined meta threshold. When theMDATA system100 opens a patient's consultation history file in database262 (FIG. 6), it calculates how many times the patient has consulted the system for the same complaint. For each problem, theMDATA system100 allows a specified number of system consultations, per unit of time, before it takes action. If the meta threshold is reached, as determined at adecision state502, theMDATA system100 makes a recommendation based on this fact alone atstate504. For example, let us assume that the threshold was set at five headaches in two months. If the patient consulted theMDATA system100 for headache more than four times in two months, the threshold would be reached and the system would make an appropriate recommendation. The threshold, of course, is different for each complaint, and may be modified by a set of sensitivity factors that will be described hereinbelow. Alternately, thesystem100 uses a time density ratio (TDR) calculated by themeta function500 to determine if a recommendation should be given to the patient.

At the completion of[0295]

state

504, or if the meta threshold was not reached atstate502, thecomputer102 proceeds tostate506 to continue the evaluation process.State506 includes a medical algorithm as selected by the patient in

states

475,479, or482. Although not necessarily a complete list, other types of medical algorithms include: Chest Pain, Heatstroke, Altered Level of Consciousness, Tremor, Dizziness, Irregular Heartbeat, Fainting, Shortness of Breath, Chest Injury, Depression, Head Injury, Cough, Croup, High Blood Pressure, Hyperventilation, Numbness, Wheezing, Inhalation Injury, and Strokes. In addition to meta and past medical history functionality, at least some of the listed medical algorithms rely upon knowledge of age and/or sex of the patient as provided in the presently describedsystem100 at time of registration (see FIGS. 9aand13a).

Depending on the medical algorithm and the exact patient condition, one or more auxiliary functions may be called by[0296]

state

506 as follows: the mentalstatus examination function508, theSDER function510, a pastmedical history function512, a physicalself examination function514, a patientmedical condition function516, and a symptomseverity analysis function518. These functions will be described hereinbelow.

Returning to the headache example, after the meta analyses (function[0297]500) are completed, theMDATA system100 assesses the severity of the patient's headache on a one-to-ten scale. The importance of this purely subjective quantization of the symptom's severity will become apparent later in this description.

Although the MDATA system's paradigm is fundamentally an algorithmic one, the underlying logic of the diagnostic process for headache will be described. The[0298]

MDATA system

100 begins the diagnostic process for headache by referring to three lists stored internally in thecomputer102.

The first list is a ranking of the most common causes of headache in the general population. The most common cause is ranked first, the second most common is ranked second, and so on. In other words, the first list ranks all the causes of headache in the general population in decreasing frequency of occurrence.[0299]

The second list is a ranking of the various causes of headache according to the seriousness of the underlying cause. The more serious causes are positioned toward the top of the list, the less serious toward the bottom. For example, meningitis, brain tumor, and subarachnoid hemorrhage would be the top three causes on the second list.[0300]

The third list is quite similar to the second list. It ranks the causes of headache according to the rapidity with which intervention is necessary. The causes of headache that require immediate intervention, such as meningitis and subarachnoid hemorrhage, are toward the top. The problem screening questions (state[0301]483) were developed from this list.

During the[0302]

evaluation process

254, theMDATA system100 asks the patient a series of “diagnostic screening questions.” From the answers to these questions, along with any physical signs elicited from the patient (from function514), under the direction of theMDATA system100, the system establishes the most likely cause of the patient's headache.

The following are examples of diagnostic screening questions for headache:[0303]

DO YOU EXPERIENCE MORE THAN ONE KIND OF HEADACHE?[0304]

DO YOU, OR DOES ANYONE ELSE, KNOW THAT YOU ARE GOING TO GET A HEADACHE BEFORE THE ACTUAL PAIN BEGINS?[0305]

DO YOUR HEADACHES FREQUENTLY WAKE YOU UP AT NIGHT?[0306]

DO YOUR HEADACHES USUALLY BEGIN SUDDENLY?[0307]

Based upon the answers to the diagnostic screening questions, the[0308]

MDATA system

100 reorders the first list. The first list then becomes a list of the possible causes of headache in decreasing levels of probability in the patient seeking consultation. The first list is now patient specific. If theMDATA system100 concludes that migraine is the most likely cause of the patient's headache, then migraine will now be ranked at the top of the first list.

The[0309]

MDATA system

100 is knowledgeable about the difference between classic, common, and all other variants of migraine, but for this discussion the general term “migraine” will be used. After reordering the first list and placing migraine at the top, theMDATA system100 then asks several questions related specifically to migraine headaches. These are called the “migraine screening questions.” The probability that the patient actually has a migraine headache is calculated from the answers to these questions. Each cause of headache has its own set of screening questions, physical examination signs, and, if the patient has the MDATA system's Home Diagnostic and Treatment Kit, appropriate laboratory tests.

The following are examples of migraine screening questions:[0310]

IS EITHER NAUSEA OR VOMITING ASSOCIATED WITH YOUR HEADACHE?[0311]

ARE VISUAL DISTURBANCES ASSOCIATED WITH YOUR HEADACHE?[0312]

After obtaining the answers to the migraine screening questions, if the probability that the patient is suffering from a migraine headache does not reach an established threshold, the next cause of headache on the reordered first list is considered and pursued as a diagnosis.[0313]

If the probability of having a migraine headache does reach the threshold, the[0314]

MDATA system

100 asks the patient several more questions designed to confirm the presence of migraine, given the fact that the system has already determined that it is the most likely diagnosis. These are called the “migraine confirmation questions.” Just as each cause of headache has a set of screening questions, each cause of headache also has a set of confirmation questions.

The following are examples of migraine confirmation questions:[0315]

DOES ANYONE WHO IS RELATED TO YOU BY BLOOD HAVE MIGRAINE HEADACHES?[0316]

WHEN YOU HAVE A HEADACHE DO YOU FEEL MORE LIKE LYING DOWN OR WALKING AROUND?[0317]

From the answers to the migraine confirmation questions, the[0318]

MDATA system

100 calculates the probability of confirmation of migraine. In Bayes' terms (which refer to the probability of certainty of a diagnosis) this is called a “conditional probability.”

If the probability of migraine headaches reaches threshold, but the probability of confirmation of migraine does not reach threshold, then, as mentioned, the system pursues the next diagnostic cause of headache on the patient specific list.[0319]

If the probability of the second cause of headache (say cluster) reaches threshold, then the “cluster confirmation questions” are asked. If they reach threshold, then again the serious causes of headache are excluded as a diagnosis.[0320]

The[0321]

MDATA system

100 stores the scores of all the screening and confirmation questions in what are called “session memory variables” that are installed in the symbol table. It is, in part, these scores that are then used to determine the probability of one diagnosis versus another.

For example, if the answers to the cluster confirmation questions do not reach threshold, then the scores of the screening and confirmation questions of migraine and cluster are compared to see which cause is the more probable.[0322]

Whichever has the higher score, or exceeds the other by a predetermined threshold, is then assumed to be the more probable cause. The list is, if necessary, again reordered. This time it becomes the final diagnostic list which is a list of differential diagnoses in decreasing levels of probability for this patient.[0323]

All of the headache scoring thresholds are modified or modulated by a series of sensitivity factors as are all aspects of the system in which scalar thresholds are used. The sensitivity factors are discussed hereinbelow in section XVIII. For example, if it was found that a subset of patients in which the diagnosis of meningitis was not being made as early as it should be, then the sensitivity factor modifying the temperature threshold could be decreased so that now, a patient with a lower temperature would be instructed to seek an immediate evaluation.[0324]

Before discussing the results with the patient, however, the[0325]

MDATA system

100 must again rule out the serious causes of headache. The problem screening questions have already filtered out those patients who have a serious cause of headache, such as meningitis, that requires immediate medical intervention.

The[0326]

MDATA system

100 now proceeds to eliminate those causes of headache that, although serious, do not require immediate medical attention. For example, although a brain tumor is a serious cause of headache, it is not as immediately life threatening as meningitis or subarachnoid hemorrhage. To accomplish this task, theMDATA system100 sequentially analyzes the serious causes of headache that are located at the top of the second list. TheMDATA system100 again asks the patient the set of screening questions associated with each of the serious causes of headache. This time, however, theMDATA system100 makes sure that the probability of having any of the serious causes of headache is sufficiently low in order to exclude them from diagnostic consideration. Only after this is accomplished will the system discuss its conclusion and recommendations with the patient.

The discussion that the MDATA system would have with the migraine headache patient would include the following:[0327]

Its diagnostic impression, or its diagnostic impressions in decreasing levels of probability.[0328]

Its estimate of the level of probability of migraine.[0329]

Whether or not the system feels it has excluded the serious causes of headache to a level of certainty that satisfies the system.[0330]

What tests, if any, should be obtained to confirm or exclude a diagnosis.[0331]

How soon to see a physician.[0332]

What kind of physician to see (e.g., family practitioner, internist, or neurologist).[0333]

What kind of information to bring to the physician when a consultation is obtained.[0334]

Questions to ask the physician.[0335]

The latest treatment for migraine.[0336]

Even if the[0337]

MDATA system

100 cannot determine with sufficient certainty what is causing the headache, it can still provide patients with valuable information and advice. For example, the patient may be told the following:

“At this time, the MDATA system is unable to pinpoint a particular cause of your headache with the degree of certainty required to make specific recommendations. The MDATA system, however, suggests a consultation with a neurologist. You can either call your family practitioner or internist and ask for a referral.[0338]

“While you are waiting to be seen by the neurologist, there are many things that you can do in order to help the physician diagnose your headache. Many headache experts have found that a record of when their patients' headaches occur and how bad they are is very helpful in finding both the cause of the headache as well as the best treatment.[0339]

“In order to assist you, the MDATA system will send you a blank calendar on which you can record the time and severity of your headaches. In addition, there is space for you to record what seems to bring on the headaches, makes them worse, or makes them better. The MDATA system will also send you a questionnaire to fill out and give to your doctor, containing a list of questions asked by some of the world's leading headache experts when they are trying to arrive at a diagnosis.”[0340]

A full set of instructions will be provided.[0341]

The MDATA system is able to customize the information given to patients to accommodate the individual needs of a sponsoring agency or group such as a Health Maintenance Organization (HMO) or a Managed Care Plan. For example, if the system finds that the patient should see a physician, the MDATA system can determine from a patient's medical record whether they have an established relationship with an appropriate specialist. If they do, the specialist's name and phone number, or a list of participating specialists for their HMO or Managed Care Plan and any specific instructions, will be given to the patient with the recommendation to make an appointment within a specific time frame.[0342]

At the conclusion of[0343]

state

506, the system may or may not have a reasonably certain diagnosis available. For example, the headache algorithm provides a diagnosis of migraine in response to a particular set of patient symptoms. In situations where theMDATA system100 cannot determine with sufficient certainty what is causing a particular problem (no diagnosis) or in a situation where a diagnosis is available but additional information is desirable, e.g., to determine a trend, a re-enter flag may be set by thesystem100. At adecision state520, thecomputer102 determines if re-enter criteria are met for the current algorithm and patient situation. If so, the computer sets the re-enter flag atstate522 for this problem so a subsequent telephone consultation by the patient will allow for additional information to be added to the patient record by the system in full knowledge of the previous call. This additional information may yield a better diagnosis.

If the re-enter criteria were not met, as determined at[0344]

state

520, thecomputer102 proceeds to adecision state524 to determine if the patient desires to hear treatment information for the current problem. If so, thecomputer102 calls thetreatment table process256, which will be described in conjunction with FIGS. 22 and 23. If the patient does not wish to hear treatment information at this time, thecomputer102 advances to adecision state528 to determine if the patient would like to investigate another complaint through theevaluation process254. If so, thecomputer102 moves via off-page connector C530 tostate471 on FIG. 10ato repeat theprocess254. However, if the patient does not wish to pursue another complaint, the computer returns atstate532 to the top level flow (FIG. 7d).

XI. The Meta Function

Referring now to FIGS. 11[0345]aand11b, themeta function500 defined in FIG. 10bwill be described. One of the many ways theMDATA system100 is qualitatively different from prior ways of providing medical advice is in its use of the “meta function.” As mentioned earlier, “meta” refers to the system's ability to evaluate the patient's present problem in the context of his or her past use of the system. The meta function allows thesystem100 to make an inference based upon the number and frequency of previous patient consultations (or, “medical complaints”) and the system's previous diagnostic assessments. Every patient who has previously used theMDATA system100 undergoes the meta analysis.

Input Parameters[0346]

The[0347]

meta function

500 has five input parameters listed atstate540 as follows:

i. Problem String (PS)—a four character alphanumeric string indicating the patient's complaint. The first character of this string is taken from the Systems column of Table 2. For example, ‘N’ denotes the nervous system. The second through fourth characters identify an individual complaint, e.g., “NHDA” identifies headache. Other examples:[0348]

CCHP Chest Pain[0349]

NINJ Head injury[0350]

RINH Inhalation of toxic fumes[0351]

ii. System String (SS)—a four character alphanumeric string that indicates the affected anatomic system. The first character is taken from the Systems column of Table 2. The second through fourth characters are encoded with subsystem identification, or filled with the ‘*’ wildcard character. For example, “N***” will match all cases that involve the nervous system.[0352]

iii. Cause String (CS)—a ten character alphanumeric string that indicates the cause of the patient's complaint. The first character is taken from the Causes column of Table 2. The second through tenth characters are filled in as needed to more closely specify the cause of interest. A very broad example is “I*********” which denotes any infection. Other examples which illustrate how the cause string can become very specific:[0353]

IV******** Viral infection[0354]

IB******** Bacterial infection[0355]

IBN*******Gram negative bacterial infection[0356]

IBNM******Meningococcal gram negative bacterial infection[0357]

iv. Beginning Time (T[0358]₁)—a timestamp value which indicates the date and time to be used for the beginning of the time window under consideration.

v. Ending Time (T[0359]₂)—a timestamp value which indicates the date and time to be used for the end of the time window.

Table 2 lists code letters used as the first letter of the meta string parameter:[0360]

	TABLE 2


	Causes	Systems

	A—allergy	B—bones/orthopedics
	E—environment	C—cardiology
	I—infection	D—gastro—intestinal
	M—mental	G—gynecology
	P—poison	H—hematology (blood)
	T—trauma	L—larynx (ENT)
	V—vascular	N—nervous
	X—genetic (chromosomal)	O—opthamology
	Y—nutritional/metabolic/endocrine	R—respiratory
	Z—tumor (cancer)	S—skin
		U—urology

A set of meta function analyses involves the identification of trends in the patient's medical history. For example, if a patient went to his or her doctor with a history of gradually worsening headaches (either more painful, more frequent, or both) the physician would consider this worsening trend in his or her management of the case. The[0361]

MDATA system

100 also does this.

Meta Analysis[0362]

The algorithm author passes input parameters to the meta function by using the keyword Meta, followed by the input parameters enclosed in parentheses. The format for the meta function is:[0363]

Meta(PS, SS, CS, T[0364]₁, T₂)

Two types of analysis are performed by the meta function:[0365]

i. Pattern Matching[0366]

ii. Time density[0367]

i. Pattern Matching[0368]

In pattern matching analysis, the meta function compares the input strings with the record fields in the patient's[0369]

consultation history database

262. The use of the ‘*’ wildcard character in the input string will cause the meta function to ignore the corresponding character position in the record field, thereby enabling the meta function to examine only the fields of interest. By providing input strings that are either general or specific, the fields of interest for analysis are selected. For example,

Meta(“NHDA”, “****”, “**********”, T[0370]₁, T₂)

will cause the meta function to only consider past consultations for the problem of headache, regardless of the anatomic system and cause involved.[0371]

Through the use of a common syntax, the meta process supports four types or modes of pattern matching analysis, shown here through examples:[0372]

(a) Problem analysis:[0373]

Meta(“HDA”, “****”, “**********”, 06/01/93, 12/31/93)[0374]

Here the meta function will find the number of complaints of headaches that occurred between Jun. 1, 1993 and Dec. 31, 1993.[0375]

(b) Anatomic System analysis:[0376]

Meta(“****”, “D***”, “***********”, 06/01/93, 12/31/93)[0377]

Here the meta function will find the number of complaints involving the gastro-intestinal system between Jun. 1, 1993 and Dec. 31, 1993. For example, if a patient consulted the[0378]

MDATA system

100 once for abdominal pain, once for vomiting, and once for diarrhea, but each on a different occasion, the system would recognize that these are all problems involving the gastrointestinal tract.

(c) Cause analysis:[0379]

Meta(“****”, “****”, “IB*********”, 06/01/93, 12/31/93)[0380]

Here the meta function will find the number of complaints that were found to be caused by bacterial infection between Jun. 1, 1993 and Dec. 31, 1993. The problems (complaints) caused by bacterial infection could be in different parts of the body.[0381]

(d) Combination analysis:[0382]

Meta(“NHDA”, “****”, “I**********”, 06/01/93, 12/31/93)[0383]

Here the meta function will find the number of complaints of headache that were found to be caused by infection between Jun. 1, 1993 and Dec. 31, 1993.[0384]

ii. Time Density[0385]

If the pattern matching analysis finds at least three matching records in the patient's[0386]

consultation history database

262, then the meta function performs a time density analysis. Time density refers to the amount of time between each consultation. If the amount of time between consultations is getting shorter, then the frequency of consultation suggests that the nature of the complaint is getting worse. Time density analysis reveals when a problem is getting better, and when it is getting worse.

Time density analysis uses the meta records that matched the pattern matching criteria. The computer designates the most recent meta record ‘n’, the next most recent is record ‘n−1’, and the second most recent is record ‘n−2’. The time stamp of each meta record is examined, and two time difference values, X and Y, are determined according to the formula:[0387]

X=time difference (n−2, n−1)

Y=time difference (n−1, n)

The ratio of these time differences produces the time density ratio (TDR):[0388]

Time Density Ratio=X/Y

The significance of the time density ratio value can be seen through the following examples:[0389]

EXAMPLE 1Time Between Consultations is the Same

[0390]



Consultation	Date of Consultation

n − 2	Jun. 01, 1993
n − 1	Jun. 08, 1993
n	Jun. 15, 1993

Calculate:[0391]

X=time difference (06/01/93, 06/08/93)=7 days

Y=time difference (06/29/93, 06/15/93)=7 days

Time Density Ratio=7 days/7 days=1.0

EXAMPLE 2Time Between Consultations is Getting Shorter

[0392]



	Consultation	Date of Consultation

	n − 2	Jun. 1, 1993
	n − 1	Jun. 22, 1993
	n	Jun. 29, 1993

Calculate:[0393]

X=time difference (06/0/93, 06/22/93)=21 days

Y=time difference (06/29/93, 06/22/93)=7 days

Time Density Ratio=21 days/7 days=3.0

When consultations are occurring at even intervals, then the TDR value is close to unity. If the frequency of consultations is decreasing, then the TDR value will be less than 1.0. This would be typical of a problem that is resolving itself. If the frequency of consultations increases, then the TDR value will be greater than one. In the second example, the TDR value of 3.0 indicates a consultation rate increase of three times during the analysis period. This would be typical of a problem that is rapidly getting worse.[0394]

Return Values[0395]

After the meta function returns, two local memory variables are installed in the symbol table and contain the results of the meta analysis:[0396]

i. Match Counter (MC)—an integer that contains the number of meta string matches found within the time window.[0397]

ii. Time Density Ratio (TDR)—a floating point value that expresses whether the frequency of meta string matches is increasing or decreasing.[0398]

After calling the meta function, the algorithm author can then make decisions based upon the values returned in these two memory variables.[0399]

For example:[0400]

Meta(“NHDA”, “****”, “**********”, 06/01/93, 12/31/93)[0401]

If MC>=3 then 100 else 101[0402]

The meta function counts the number of complaints of headache between Jun. 1, 1993 and Dec. 31, 1993. If the number of complaints found (MC) is greater than or equal to 3, then the evaluation process branches to[0403]

node

100; otherwise it branches tonode101.

Another example:[0404]

Meta(“****”, “****”, “I*********”, 06/01/93, 12/31/93)[0405]

If TDR>=2.0 then 200 else 201[0406]

The meta function is invoked to count the number of diagnoses attributed to a cause of infection. If the infection caused diagnoses found have a time density ratio greater than or equal to 2.0, then the evaluation process branches to node[0407]200; otherwise it branches to node201.

Referring again to FIG. 11[0408]a, themeta function500 initializes atstate540 by popping the input parameters off the run-time stack and storing them in local memory variables: PS for problem string, SS for anatomic system string, CS for cause string, T₁for the beginning date and T₂for the ending date. After thestart state542, the computer moves tostate544 and initializes the pattern match counter to zero.

The[0409]

computer

102 then moves tostate546 wherein it begins the pattern matching analysis. Thecomputer102 reads the first meta record in the patient'sconsultation history database262 and moves to adecision state548 wherein it examines the record's timestamp. If the timestamp falls within the time window established by the input parameters T_{1 and T}₂, then the computer will move tostate550; otherwise it moves tostate554. Atstate550, thecomputer102 compares the contents of the meta record problem field with the input string PS, the meta record anatomic system field with the input string SS and the meta record cause field with the input string CS. If all these fields match the respective input strings, then the computer moves tostate552 wherein the match counter MC is incremented, and then the computer moves tostate554. If there is any mismatch between a meta record field and its respective input string, then the computer moves tostate554 and does not increment MC.

At[0410]

decision state

554, thecomputer102 determines if there are more meta records to process. If so, thecomputer102 moves tostate556 wherein it reads the next record and then moves back tostate548 to perform the time window determination. The meta function iterates through this pattern matching until all of the meta records have been read. When there are no more meta records to be processed, the computer moves through off-page connector A558 to adecision state560 on FIG. 11bwherein a determination is made if the value of the match counter MC is greater than or equal to 3. If so, then the computer moves tostate564 wherein it begins the time density analysis.

At[0411]

state

564, thecomputer102 locates the three most recent meta records whose fields matched the input strings. The computer designates the most recent meta record ‘n’, the next most recent is record ‘n−1’, and the second most recent is record ‘n−2’. The computer then moves tostate566 wherein it calculates X, the time difference between the timestamps of records n−2 and n−1, and Y, the time difference between records n−1 and n. Thecomputer102 then moves tostate568 wherein it calculates the time density ratio (TDR) as the time X divided by time Y.

If the[0412]

computer

102 determined atstate560 that there were less than three matches, then it would move tostate562 wherein it sets the value of the time density ratio (TDR) to 0.0, which indicates that the time density analysis could not be performed. At the completion of establishing the value of TDR at either

state

562 or568, thecomputer102 moves toterminal state570 wherein the meta process terminates, returns the match counter MC and the time density ratio TDR, and returns control to the evaluation process254 (FIG. 10).

The interaction of the meta analyses for cause and for anatomic system can be conceptualized by means of a simple geometric metaphor. Consider a two dimensional array in which the causes of disease (trauma, infection, allergy/immune, and so forth) are placed on the “Y” axis, or ordinate, and the anatomic systems of the body (cardiac, respiratory, nervous system, and so forth) are placed on the “X” axis or abscissa. Disease then can be represented by, or is produced at, the intersection of the lines drawn from the applicable cause and the anatomic system.[0413]

As a very simple illustration, consider the two-dimensional array shown in Table 3 (FIG. 24). The array of Table 3 shows an infection in the central nervous system represented at the intersection of the cause of disease (infection) and the anatomic system involved (the nervous system).[0414]

Of course, each cause of disease can be further divided into subcauses. For example, infection would be broken down (or subdivided) into bacterial and viral, and bacterial would be further broken down into gram positive and gram negative, and gram positive would be further yet broken down into streptococcus, and so on. The anatomic systems could be broken down in a similar way.[0415]

As a patient uses the[0416]

system

100, and as the meta analyses for cause and for anatomic system attribute causes to disease processes and record the anatomic systems involved, a three-dimensional cube (a “meta cube”) is produced composed of these stacked two-dimensional arrays. The “Z” axis coordinate of each layer is the time of the patient's consultation obtained from the system clock (i.e., the moment that the actual intersection of the cause and anatomic system occurs indicating the diagnosis).

The “meta cube” then represents a summation of the patient's interaction with the[0417]

system

100 through time. Although much of the patient's past history is stored using ICD□9□CM codes as well as conventional text strings in fields of the patient's medical record, the “meta cube” technique allows very useful analyses to be done.

Using the same modeling metaphor, the “Z” axis coordinate can be used to represent the practice of medicine. Here the “Z” coordinate is again time, but in this representation, time refers to a spectrum of ages from pediatrics to geriatrics. Thus, each coronal plane represents specialties by time, e.g., pediatrics, adolescent medicine, adult, geriatric. A vertical plane describes a specialty by anatomic site, such as neurology or cardiology, while a horizontal plane describes a specialty which practice is bounded (subsumed) by (on) cause, such as oncology or infectious disease. To further this metaphor, the rapidity with which intervention is necessary could be a fourth dimension of the model, and the frequency of an occurrence of a disease is the fifth dimension. Ethical and moral responsibility could be a sixth dimension of the model.[0418]

Node Map Traverse Analysis[0419]

The[0420]

MDATA system

100 uses a “neural net emulator” program to determine if patterns produced by patients, as they traverse down the nodes (creating “node tracks” of the algorithms in the course of a consultation, may be early predictors of disease. Somewhat like the “meta cube,” the “node tracks” can be superimposed, rather than stacked, upon one another to create a two-dimensional array. This time, however, the pattern produced represents the sum of the patient's previous consultations. In theMDATA system100, this is called a “node track traverse analysis.”

For example, the[0421]

MDATA system

100 may discover that the pattern that is produced when a patient consults the system, at different times, for episodes of diarrhea, cough, and oral candidiasis may be predictive of AIDS. Or, that the pattern produced when a patient consults the system for increased frequency of urination and weight loss may be predictive of diabetes mellitus.

XII. Mental Status Examination

Referring to FIGS. 16[0422]aand16b, the mentalstatus examination function508 defined in FIG. 10bwill be described. The mental status examination is a series of questions used to assess the patient's orientation that allows thesystem100 to determine the patient's ability to respond to questions and to follow advice. The examination is automatically incorporated into the dialogue of any problem whose presentation could include an altered level of consciousness. If an operator or nurse monitoring a telephone consultation at any time feels there may be a problem with the caller's ability to understand or respond to questions, the mental status examination may also be manually invoked.

If the[0423]

MDATA system

100 determines that the patient is not sufficiently oriented based on the results of the mental status examination, thesystem100 will ask to speak to someone other than the patient. If no one else is available, theMDATA system100 can contact the emergency medical services system in the patient's area if the system knows the patient's present geographic position.

Beginning at a[0424]

start state

680 of FIG. 16a, thecomputer102 initializes the value of a variable Score to be zero. Moving tostate682, the computer asks thepatient Question #1. In the presently preferred embodiment, the question is “what day of the week is it?” If the person answers the question correctly, as determined by adecision state684, thecomputer102 increments the value of Score by one. After Score is incremented or if the patient did not answer the first question correctly, thecomputer102 moves tostate688 wherein thecomputer102 asks thepatient Question #2. In the presently preferred embodiment, the question is “what month of the year is it?” If the person answers the question correctly, as determined by adecision state690, thecomputer102 increments the value of Score by one. After Score is incremented or if the patient did not answer the second question correctly, thecomputer102 moves tostate694 wherein thecomputer102 asks thepatient Question #3. In the presently preferred embodiment, the question is “who is the President of the United States?” If the person answers the question correctly, as determined by adecision state696, the computer increments the value of Score by one. After Score is incremented atstate698 or if the patient did not answer the third question correctly, thecomputer102 moves through off-page connector A699 to adecision state700 on FIG. 16b.

At[0425]

decision state

700, thecomputer102 compares the score to the mental status exam threshold at adecision state700. If the score meets or exceeds the threshold, then the mental status exam returns to the evaluation process atstate701 and the diagnostic evaluation continues. If the score does not reach or exceed the threshold value, thecomputer102 moves tostate702 wherein the operating mode flag is set to Pending. TheMDATA system100 will then ask, at adecision state703, if someone else is available to continue the consultation. If no one else is available, any new information gathered up to this point in the session is saved to Pending file269 atstate704 and then, atstate705, the telephone call with the patient is transferred to a medical staff person. If someone else is available, as determined atstate703, and is able and willing to continue the evaluation process of the patient, as determined atstate706, thecomputer102 asks the person if he or she is a registered assistant atstate707. If the person responds “yes”, thecomputer102 invokes theassistant login process272 atstart state940 on FIG. 12a. If the person is not a registered assistant, thecomputer102 invokes theassistant registration process274 atstart state1050 on FIG. 14a. After assistant registration or login, thecomputer102 moves toterminal state708 wherein the mental status examination process terminates and theevaluation process254 resumes. At the end of theevaluation process254, any new information gathered during the session will be written to the patient's past medical history file atstate348 or to pendingfile269 atstate347 on FIG. 7d, depending on whether the session continued in real or pending mode. In the presently preferred embodiment, the value of Score could be zero, one, two, or three. Of course, in other embodiments, different questions to be asked of the patient may be utilized in the mentalstatus exam function508.

XIII. Semantic Discrepancy Evaluator Routine

Referring to FIG. 17, the semantic discrepancy evaluator routine (SDER)[0426]510 defined in FIG. 10bwill be described. TheSDER510 uses one or more questions that ask for the same information at different times, and in other embodiments, in different ways. The answers given by the patient are then compared within thesystem100 to help determine the mental status of the patient.

Beginning at a[0427]

start state

712, thecomputer102 moves tostate716 and recites a message to the patient. In the presently preferred embodiment, the message is “remember this three digit number . . . NUMBER”, where the computer generates a random three digit number (i.e., in therange 100 to 999 inclusive) as NUMBER which is kept in a session memory variable.

Then, after a predetermined time interval at[0428]

state

718, thecomputer102 moves tostate720 and recites a request of the patient. In the presently preferred embodiment, the request is “please tell me the three digit number.” Thecomputer102 then compares the number given by the patient in response tostate720 against the NUMBER kept in the memory variable at adecision state722. If the numbers match, thecomputer102 returns atstate724 with a status of pass to the evaluation process (FIG. 10b). If the numbers do not match, thecomputer102 returns atstate726 with a status of fail to the evaluation process. In the presently preferred embodiment, if the return status of theSDER510 is “fail”, theevaluation process254 automatically invokes the mentalstatus examination function508.

XIV. Past Medical History Routine

Referring to FIG. 18, the Past Medical History Routine (PMHR)[0429]512 defined in FIG. 10bwill be described. The contents of a patient's past medical history file, which is part of thePMH database268, are loaded to the symbol table when the patient logs in to thesystem100. During theevaluation process254, a TEST is performed by thecomputer102 before a particular medical algorithm is initiated to verify that necessary items are present in the symbol table. The effect of a negative TEST result is that thesystem100 prompts the patient to provide the missing past medical history information via thePMHR512.

The[0430]

PMHR

512 uses an input parameter “condition label” (L) as indicated atState740. The “Condition label” is unique, e.g., PMHRLTB1 corresponds to the first PMH object tested in the croup (RLTB) algorithm: diagnosis for croup in children. The label is passed so thatPMHR512 knows what questions to ask. The ability of thesystem100 to ask a past medical history question in the middle of theevaluation process254 is a feature that saves the patient from having to answer the entire PMH questionnaire during the registration process. The boolean result, or scalar value, is stored in the symbol table under this label (PMHRLTB1), and the algorithm can use it in decision making, e.g., If PMHRLTB1=True Then 4310 Else 4320.

Beginning at a[0431]

start state

742, thecomputer102 moves tostate744 and prompts the patient for the missing medical condition data. Moving tostate746, thecomputer102 repeats the information provided atstate744 and asks the patient if the repeated information is correct. Moving to adecision state748, the patient responds by indicating whether the repeated information is correct. If the data is not correct, thecomputer102 proceeds tostate750 to determine if the patient would like to attempt the data entry step again. If so, thecomputer102 loops back tostate744 and prompts the patient for the data again. If not, thecomputer102 returns atstate754 to the evaluation process (FIG. 10b).

If the newly-entered data is correct, as determined at[0432]

state

748, thecomputer102 advances tostate752 and installs the condition label (L) and the data value in the symbol table for the patient. Thecomputer102 then returns atstate754 to theevaluation process254.

XV. Physical Self Examination

Referring to FIG. 19, the Physical Self Examination function[0433]514 defined in FIG. 10bwill be described. A physical examination can actually be done by the patient under the direction of theMDATA system100. TheMDATA system100 is designed to function primarily based upon responses to carefully crafted questions, i.e., history, and physical findings elicited from the patient. There are times, however, when the addition of certain laboratory tests can increase the accuracy of the diagnosis as well as help determine the appropriate treatment recommendations. For this reason, a MDATA system Home Diagnostic and Treatment Kit is available for use by patients. If the patient has the Home Diagnostic and Treatment Kit, including visual field cards, Snelling chart, and possibly the MDATA system's “tele-stethoscope” to assess intracranial or carotid bruits, this information will be used in the diagnostic process as well.

The[0434]

MDATA system

100 is also able to play tones of different frequencies and intensities to emulate audiometric testing for hearing acuity. This allows, for example, theMDATA system100 to detect the unilateral decrease in hearing caused by an acoustic neuroma.

Beginning at a[0435]

start state

770, thecomputer102 branches to one or more physical self examination procedures depending on the current problem and what equipment if any is available for use by the patient. These procedures include: homediagnostic tests772,vital signs774, observablephysical signs776,clinical sound recording778, and tele-stethoscope780.

A variety of home[0436]

diagnostic tests

772 are available for use by the patient. New advances in biotechnology, including a new generation of urine dipsticks such as a “Multistix 8 SG” produced by Ames and monoclonal antibody tests such as “ICON® STREP B” produced by Hybritech®, allow an entire spectrum of laboratory tests to be performed at home by the patient under the direction of the MDATA system. For example, urine dipsticks can be used to check for blood, nitrites, leukocytes, or leukocyte esterase indicating cystitis or a bladder infection.

In order to use much of the monoclonal antibody technology, however, a small amount of blood must be obtained by using a fingertip lancet. This is already successfully being done by diabetics at home who use a glucometer to measure their blood sugar after pricking their finger to get a small sample of blood.[0437]

The MDATA system Home Diagnostic and Treatment Kit also contains equipment to allow the patient, or someone else, to measure the patient's[0438]

vital signs

774. A blood pressure cuff and thermometer are included with instructions for their use as well as instructions to measure pulse and respiratory rate.

The patient may be directed by the[0439]

system

100 to observe variousphysical signs776. For example, a headache patient will be asked to palpate their temporal artery area, and to look at themselves in the mirror to identify the ptosis and tearing of a cluster headache or to identify the steamy cornea that may occur with acute narrow angle glaucoma.

As an example of how the MDATA system Home diagnostic and Treatment Kit could be helpful, consider a woman who (using the MDATA system's urine pregnancy test based on ICON® II HCG ImmunoConcentration™ Assay, produced by Hybritech®) finds out that she is pregnant. This is her first pregnancy. Later, when consulting the system for headache, a urine dipstick indicates protein in her urine and the measurement of her vital signs shows a significant rise in her blood pressure. This is a classic presentation of preeclampsia.[0440]

Instead of going to a doctor's office, patients could also use the MDATA system's Home Diagnostic and Treatment Kit to collect samples at home and then send them to a designated lab for analysis as needed. This saves time for the patient and is especially useful if the patient has difficulty in traveling. Costs should also be minimized in this type of laboratory analysis.[0441]

The[0442]

MDATA system

100 records clinicallyrelevant sounds778 of a patient such as the cough of bronchitis, the seal bark cough of croup or the inspiratory stridor of epiglottitis. These sounds are digitized and stored in the patient's medical record. Then, using the re-enter feature of thesystem100, the system can monitor, for example, a patient's cough over time to be sure that the cough is resolving as it should.

The general concept of recording and analyzing a cough is disclosed in the article[0443]A microcomputer-based interactive cough sound analysis system, C. William Thorpe, et al., published inComputer Methods and Programs in Biomedicine,1991. The cough sound analysis system describes the filtering, amplification, recording, and software processing of a cough sound. TheMDATA system100 uses the telephone handset microphone in conjunction with an amplifier to procure the clinical sounds. These sounds are then transmitted to thesystem100 where they are filtered, digitized usingVP board122 and recorded to a file in the patientmedical history database268 on the hard drive152 (FIG. 1).

The[0444]

MDATA system

100 is building a library of clinical sounds that allows patterns or profiles to be developed that relate the wave form of the clinical sound to the probability of a particular diagnosis. For example, theMDATA system100 could compare the cough of a patient to the sound library to see if the cough of the patient is similar to those that eventually have been diagnosed as lung cancer.

In addition, the patient's record of the pronunciation of his or her name may be periodically recorded and compared to previous recordings. This allows the[0445]

MDATA system

100 to potentially detect and evaluate the hoarseness that could be produced by a nodule on the patient's vocal cords.

A “tele-stethoscope”[0446]780 is a device that allows the sounds a physician would hear through a stethoscope to be transmitted over the telephone. The tele-stethoscope780 is functionally similar to that described in the 1992 Arthur D. Little report entitled “Telecommunications: Can It Help Solve America's Health Care Problems?”. The tele-stethoscope780 permits theMDATA system100 to greatly expand the spectrum of its sound analyses to include heart murmurs, the bruits of intracranial aneurysms, breathing sounds like the wheezes of asthma and the rales of congestive heart failure, or even the bowel sounds of an intestinal obstruction.

There is more information in clinical sounds than can be represented by a two-dimensional pattern matching model. Transforms, e.g., Fourier, are used to shift different aspects of sounds into domains that can be quantified. The sounds are then pattern matched using an n-dimensional array. Consider a simple two dimensional array where time is represented on the X coordinate and amplitude is measured on the Y coordinate. For example, a cough may be recorded at two times several days apart. In this example, the[0447]

computer

102 superimposes the waveform from one cough upon the other cough. The non-overlapping parts of the pattern both above and below represent the difference in the domain being measured between the two sounds. The area under these two curves is integrated to obtain the area. The sum of the areas of the two curves represents the difference between the two sounds in the domain being measured. The resultant area is then subjected to one or more sensitivity factors which are discussed hereinbelow. Hence, the more sensitive the system, the sooner it makes a match.

In this pattern matching scheme, different weights are given to the different aspects of the sound depending upon which clinical sound is measured. In most sounds, the amplitude and frequency are the most important aspects. The weight or the relative importance of an aspect is different for each of various clinical sounds, such as heart murmurs, bruits, wheezes, coughs, stridor and so forth.[0449]

When value(s) from any of the procedures[0450]772-780 are procured by thesystem100, thecomputer102 moves tostate782, recites the value and requests the patient to confirm the value. If the patient indicates that the value is correct, as determined at adecision state784, thecomputer102 proceeds tostate786 and installs the value into the symbol table associated with the current patient. If the value is not correct, as determined atdecision state784, thecomputer102 proceeds tostate790 to determine if the patient would like to try providing the value again. If so, thecomputer102 loops back to the beginning of thefunction514. If the patient does not wish to try again, as determined atstate790, or ifstate786 is completed, thecomputer102 returns atstate788 to the evaluation process (FIG. 10b).

Referring to FIG. 20, the Patient[0451]

Medical Condition Routine

516 defined in FIG. 10bwill be described. In the course of executing a particular medical algorithm in the evaluation process254 (as shown at state506), thecomputer102 may request additional medical condition information of the patient. This information reflects the current condition of the patient, which is in contrast to the information requested by the past medical history routine512 (FIG. 18) for past history information. Thestates800 through814 of the routine516 are essentially the same asstates740 through754 of routine512, except that in routine512 the condition label (L) denotes a value for which a past medical history question is to be asked during the evaluation process, while in routine516 the condition label denotes a new value desired by the algorithm. Therefore, states800-814 are not further described herein.

XVI. Symptom Severity Analysis

Referring now to FIGS. 10[0452]a,10b, and21, the symptomseverity analysis function518 defined in FIG. 10bwill be described. A review and further description of the re-enter feature, which is associated with symptom severity analysis, is also provided here.

An important feature of the[0453]

MDATA system

100 is its ability to follow or monitor a patient over time. If theMDATA system100 is in the process of diagnosing a patient's complaint but is not certain what action should be taken (states520-522 of FIG. 10b),system100 may ask the patient to re-enter the system at a designated time, usually within a few hours.

When the patient calls the MDATA system at the designated time, the system takes the patient through the initial problem screening questions ([0454]

state

483 of FIG. 10a) in order to exclude those problems that require immediate medical attention. The system detects that the patient is a re-enter case (state490 of FIG. 10a), and then determines the re-entry point in the evaluation process based upon the patient's previous interaction with the system (state492 of FIG. 10a). For example, if the MDATA system established a diagnosis of migraine, that is, if both the probability of migraine and the probability of confirmation of migraine reached threshold values, the patient would not repeat the diagnostic process, which is the usual case.

Occasionally, however, a patient for whom a diagnosis has not been established will be asked to re-enter the[0455]

system

100. This patient is again asked the diagnostic screening questions, in addition to the initial screening questions (state306 of FIG. 7a) and problem screening questions (state483 of FIG. 10a). If theMDATA system100 is not able to establish a diagnosis for a re-enter patient, he or she is referred to a physician for further evaluation.

In addition to the re-enter feature, the[0456]

MDATA system

100 has the capability to call patients back in order to monitor their progress. The same trending methodologies are used regardless of who initiates the call, i.e., the system or the patient. Using this capability, theMDATA system100 can provide regular or periodic monitoring of elderly patients in their homes as well as inform patients when a new therapy becomes available.

Many problems for which the[0457]

MDATA system

100 offers advice have absolute thresholds for the initial quantization of the severity of a symptom. For example, chest pain that is described by a patient as being 10 on a 10-scale of severity, would reach the problem-specific initial symptom-severity threshold and would mandate a consultation with a physician.

Interestingly, with headache, an initial severity characterized by the patient as 10 on a 10-scale would not, in itself, necessarily require an immediate consultation with a physician. If, in addition, the headache came on suddenly and, as was mentioned earlier, was described as the worst headache of the patient's life, the[0458]

MDATA system

100 would consider this to be suggestive enough of a subarachnoid hemorrhage to advise an immediate consultation with a physician.

Continuing in the headache example, after a re-enter patient with an established diagnosis is asked the initial and problem screening questions, the[0459]

MDATA system

100 again assesses the severity of the patient's headache. Reassessing the severity of the headache, by having the patient re-enter the system, establishes two points of reference. Thesystem100 is now able to analyze any changes in the level of severity as well as calculate the rate of change in severity over time.

The symptom[0460]

severity analysis function

518 has a Number of Points (N) as an input parameter as indicated atstate830. Number of Points refers to the points of reference established during the initial consultation for a particular problem and during subsequent re-enter consultation(s). Beginning at astart state832, the computer determines the value of (N), i.e., the number of reference points, at adecision state834. If it is determined that N=2, thecomputer102 moves tostate836 to compute the slope of a line connecting the two reference points using standard mathematical techniques. Proceeding tostate838, a variable named Power is set to be one because only two reference points are used atstate836. Thecomputer102 returns atstate840, with output parameters Slope and Power as determined byfunction518, to the evaluation process (FIG. 10b).

Using the returned Slope and Power parameters in the[0461]

evaluation process

254, if theMDATA system100 determines that the severity of the headache, for example, is increasing too rapidly, that is, if a slope of the line connecting two points on a graph of the severity reaches a set threshold,system100 will make an appropriate recommendation.

If the[0462]

MDATA system

100 finds that the severity of the headache is staying the same or is getting worse but is doing so at a relatively slow rate, it may ask the patient to re-enter the system a second time (i.e., for a third consultation), usually within a shorter period of time. The third consultation gives theMDATA system100 three points of reference from which to trend the severity of the headache. Thus, when thefunction518 is called by the evaluation process, the value of (N) is three, as determined atstate834, and thecomputer102 branches tostate844. Atstate844, thecomputer102 determines the slope and power of a line connecting the three reference points. The presently preferred embodiment uses the well-known Runge-Kutta method, which is a numerical approximation technique for solving differential equations. Other embodiments may use other well-known, standard curve fitting functions atstate844.

If the[0463]

system

100 determines that yet one or more additional consultations, i.e., beyond three consultations, are desired, e.g., to establish a trend with certainty, it will again request the patient to re-enter the system at a later time. In this situation, the three most recent reference points are used in the calculation atstate844.

The[0464]

system

100 then performs a “sequential symptom-severity slope analysis” to determine if the symptom is getting worse too rapidly as follows. The slopes of the lines connecting the first and second point, the second and third point, and then the first and third point are calculated. If any of these reach a problem-specific threshold, the appropriate recommendation is given.

If the sequential symptom-severity slope analysis does not reveal the need to seek medical attention, then the[0465]

MDATA system

100, in addition to calculating the rate of change in the severity of the symptom with respect to time (the slope analysis), now calculates the rate of change of the rapidity with which the headache is getting worse. This is the first derivative.

Table 4 (FIG. 25) illustrates this relationship. Time maps onto the “X” axis and the symptom's severity maps onto the “Y” axis. Note that a line connecting these three points forms a gently sloping straight line. The[0466]

MDATA system

100 using this data determines that, although the symptom is getting worse, it is doing so in an arithmetical or linear way. That is, although the severity of the symptom is increasing, the symptom's rate of change is not increasing.

In contrast, a line connecting the three points on the graph of Table 5 (FIG. 26) forms a sharply upturned curve. The[0467]

MDATA system

100 using the data of Table 5 determines that, not only is the symptom rapidly getting worse, but more significantly, the rate at which the symptom is getting worse is also increasing. In theMDATA system100, this analysis is termed an “exponential symptom-severity filter.” All patients who re-enter the system a second time are subjected to this analysis.

It is important to note that the severity of a problem, e.g., a headache, is not necessarily related to the seriousness of the underlying cause. The[0468]

MDATA system

100 is programmed such that when any symptom gets rapidly worse, medical intervention is frequently advised as necessary. This concept is valid for many symptoms.

Returning to the symptom severity analysis function[0469]518 (FIG. 21), if thefunction518 is called with N=0, or N=1, the computer branches tostate842. Atstate842, the Slope and Power parameters are set to zero, and thecomputer102 returns these parameters atstate840 to the evaluation process (FIG. 10b). The values set atstate842 essentially flag an error condition that is acted on by theevaluation process254.

XVII. Treatment Table

Referring to FIG. 22, the[0470]

Treatment Table process

256 defined in FIG. 7dwill be described. TheMDATA system100 is modularized in its approach to diagnosis and treatment. In medicine, diagnosis simply means figuring out what is causing the problem, and treatment refers to what action should be taken once the cause of the problem is known.

Diagnosis is composed of history, physical examination, imaging studies, and laboratory tests. Again, history is by far the most important factor in making the diagnosis. In fact, in medical school, students are taught that if they don't have a good idea of the diagnosis by the end of the history, they are doing something wrong.[0471]

The treatment side of medicine is conceptually different from diagnosis in that, while the basic principles of making the diagnosis remain the same, treatment is continually changing. Treatment is fundamentally a “look-up” table with the diagnosis, age and sex on the left and the most current treatment on the right as shown in Table 6. Or, treatment can be thought of like the cubbyholes or boxes of a post office. Each individual box holds the treatment for a given disease. The information given is age and sex specific. The contents of the box are constantly changing, but the location of the box does not. For example, what is thought to be the best antibiotic to treat meningitis in a two-year-old child could literally change from week to week as more antibiotics are developed and approved or more controlled studies are published.[0472]

TABLE 6


Simplified TREATMENT TABLE Example

	Diagnosis	Treatment

	meningitis in a	antibiotic of choice
	two-year old child	as of current date

The[0473]

MDATA system

100 maintains a treatment table that can be updated instantaneously to provide the most current treatment recommendations.

The treatment table can be directly accessed by patients who already know their diagnosis. For example, asthma patients can consult the system as often as they wish to see what the absolute latest treatment is for their condition. In fact, links are maintained between the treatment table and the patient medical history files[0474]268. In this way, when a new treatment is introduced for any of the ICD□9□M codes listed in theMDATA system100, patients can be contacted and asked to either call thesystem100 back at their convenience or have theMDATA system100 fax or mail the information to them. TheMDATA system100 can also notify patients' doctors when a new treatment is identified.

The concept of using a table is also helpful with regard to two aspects of the diagnostic process that often do change: the imaging modality of choice (like X-ray, Computerized Tomography (CT), Magnetic Resonance Imaging (MRI)), and the laboratory test(s) of choice. Therefore, the[0475]

MDATA system

100 also maintains a table for imaging modality of choice as well as laboratory test(s) of choice in the work-up or diagnosis of a particular complaint. By modularizing these aspects of the diagnosis, as new imaging techniques, like Positron Emission Tomography (PET) scanning, and new laboratory tests, like recombinant DNA technology, are discovered, only the tables have to be altered, not the medical algorithms themselves.

The treatment table will be further described in a general way as[0476]

process

256 in FIG. 22. Thetreatment table process256 begins atstart state860 and proceeds tostate862 wherein the computer prompts the caller to choose a treatment selection method:

i. Treatment selected from layered menus, or[0477]

ii. Treatment selected via direct entry of a catalog number.[0478]

The first selection method entails the use of the menu-driven[0479]

treatment selection process

864 which will be described hereinbelow in conjunction with FIG. 23. The second selection method atstate866 uses a treatment table catalog message number. This catalog is part of the patient information package, a section of which appears in Table 7. The treatment table catalog is organized by anatomic area and diagnosis, and when applicable, by age and gender. After the patient selects a catalog number, thecomputer102 stores the selection in a memory variable ‘M’. As an alternate selection method, thesystem100 allows the patient to directly enter the ICD□9□CM code for their problem. In this case, thecomputer102 will look-up the ICD□9□CM code in an internal cross-reference table to identify the catalog number, and set the memory variable ‘M’ to this catalog number.

TABLE 7


Portion of Treatment Table Catalog
NEUROLOGY

	Diagnosis	Message

	Epilepsy
	1101
	Meningitis
	2 years old & younger	1201
	over 2 years old	1202
	Depression
	Male
	Under age
50	1301
	50 years and older	1303
	Female
	Underage 50	1302
	50 years and older	1304

Once the value of the memory variable ‘M’ is established by[0480]

process

864 orstate866, thecomputer102 moves tostate868 and plays treatment message ‘M’ to the patient. At the conclusion of treatment message playback, thecomputer102 moves to adecision state870.

At[0481]

state

870 thecomputer102 checks for existence of society message ‘M’. The society message category contains information about organizations that assist patients with a particular disease. If the society message ‘M’ does not exist, thecomputer102 moves to adecision state874. Otherwise, thecomputer102 will move tostate872 wherein it plays society message ‘M’ to the patient. At the end of the society message ‘M’, the computer moves tostate874.

At[0482]

state

874, thecomputer102 checks for the existence of an over-the-counter (OTC) message ‘M’. The OTC message category contains information about generally available over-the-counter medications and home treatment for a particular diagnosis. If the OTC message ‘M’ does not exist, the computer moves tostate878. Otherwise, thecomputer102 moves tostate876 wherein it play OTC message ‘M’ to the patient. At the end of the OTC message ‘M’, thecomputer102 moves tostate878.

At[0483]

state

878 thecomputer102 plays a terminal menu to the patient which allows the patient to either select another treatment, or to exit from thetreatment table process256. If the patient wishes to hear another treatment message, thecomputer102 moves back to the treatment selectionmethod menu state862. If the patient wishes to exit thetreatment table process256, the system moves tostate880, wherein thetreatment table process256 terminates and returns to the top level flow (FIG. 7d) atstate344.

An example of the treatment, society and OTC messages for epilepsy are given in Table 8. Note that since the OTC message is empty, the[0484]

computer

102 would skip over the OTC message playback and proceed directly to the terminal menu.

Table 8Treatment Table Messages for Epilepsy

Treatment Message[0485]

As of Dec. 20, 1993, according to Emergency Medicine: Concepts and Clinical Practice, Third Edition, by Drs. Rosen, Barkin, et. al., pages 1800 and 1801, the initial treatment of generalized tonic-clonic seizures, i.e., grand mal seizures, is as follows:[0486]

After efforts to discover and treat acutely correctable causes like hypoglycemia, the following pharmacologic agents are indicated:[0487]

1. Intravenous administration of lorazepam, with a loading dose of 0.1 mg/kg and an infusion rate not to exceed 2 mg/min.[0488]

Which is usually followed by:[0489]

2. Intravenous administration of phenyloin, with a loading dose of 15 to 18 mg/kg and an infusion rate not to exceed 0.75 mg/kg per minute.[0490]

If lorazepam is not effective, and in those individuals allergic to phenyloin:[0491]

3. Intravenous administration of phenobarbital, with a loading dose of 8 to 20 mg/kg and an infusion rate not to exceed 0.75 mg/kg per minute.[0492]

If the above is not successful:[0493]

4. A neuromuscular blocking agent like pancuronium, with an intravenous dose of 0.03 to 0.1 mg/kg.[0494]

5. Intravenous administration of paraldehyde, with a loading dose of 0.1 to 0.15 ml/kg, diluted with saline to a 4% to 6% solution and slowly infused over 1 hour.[0495]

Society Message[0496]

“For further information on epilepsy, contact:[0497]

Epilepsy Foundation of America[0498]

1828 L Street, N.W., Suite 406[0499]

Washington, D.C. 20036[0500]

(202) 293-2930[0501]

In addition to the national headquarters, there are 100 local chapters. The San Diego chapter can be contacted at (619) 296-0161.”[0502]

OTC Message[0503]

None.[0504]

Referring now to FIG. 23, the menu-drive[0505]

treatment selection process

864 defined in FIG. 22 will be described. The menu-driventreatment selection process864 begins withstart state890 and proceeds tostate892 wherein thecomputer102 recites an area menu to the patient and requests selection of one area. The complete menu is not shown instate892. The areas are arranged by anatomic system. For example, if a patient has epilepsy, the patient can simply select this from the anatomic system menu for the neurological system.

Based on the patient's selection, the[0506]

computer

102 branches to a selection area menu state, such as neurologicalarea menu state894, wherein thecomputer102 recites a list of diagnoses to the patient and requests selection of a diagnosis. In some cases the diagnosis is further subdivided by gender, age or both gender and age. Atstate904, for example, for a diagnosis of meningitis, thecomputer102 would prompt the patient to select from a secondary menu between a treatment for a child two years old or younger and a treatment for somebody over two years old. Then, based on the patient's selection, thecomputer102 sets a memory variable ‘M’ to the value of the selected diagnosis message number at

state

908 or910.State906 is another example secondary level menu which has four choices based on gender and age. These four choices are associated with four states,912,914,916,918, wherein thecomputer102 sets the memory variable ‘M’ to the value of the diagnosis message number that was selected atstate906. After the catalog number has been stored in memory variable ‘M’, thecomputer102 moves to returnstate923 wherein the menu-driven treatment selection process terminates and returns control to thetreatment table process256.

[0507]

Area2 menu

896 andAreaN menu898 are indicative of menus similar tomenu894 but for different anatomic systems.

Menu

896 and898 may have secondary menus, similar to

menus

904 and906 undermenu894. Then, states920 and922 are indicative of thecomputer102 setting memory variable ‘M’ to the value of the diagnosis message number selected from the

parent menu

896 or898, respectively.

XVIII. The MDATA System Paradigm

The MDATA system paradigm is based on several fundamental principles. They are as follows:[0508]

Centralization of medical information[0509]

Accessibility of medical information[0510]

Modularity of medical information[0511]

Modifiability of the system.[0512]

As mentioned earlier, one of the purposes of the[0513]

MDATA system

100 is to bring together highly qualified medical experts, encode their knowledge in a central location, and make this information available to everyone.

Although the issue of accessibility has been discussed several times, it is important to understand its significance. Accessibility in the[0514]

MDATA system

100 refers both to the way in which the medical information can be retrieved from thesystem100 by non-medically trained personnel as well as to the need for people everywhere to easily and promptly obtain medical information. By using the already established worldwide telecommunications network, theMDATA system100 can provide universal and nearly instantaneous access to high quality, 100%-consistent medical advice.

In the[0515]

MDATA system

100, the concepts of modularity and modifiability are inextricably intertwined. Modularity is the key to the MDATA system's ability to provide patients with the most current medical information available. The MDATA system's modular design and object oriented techniques allow the individual components of the system to be modified or updated without generating a ripple effect on other information in thesystem100.

In contrast, the print media suffers from an inability to quickly adapt to changing information. Once a book or journal is published, it cannot be modified until its next publishing date. The[0516]

MDATA system

100, however, can be modified within hours of a new discovery in medicine. Easy modifiability is another way in which theMDATA system100 is qualitatively different from previously published algorithms.

Once the medical algorithms for the[0517]

MDATA system

100 are written and programmed, they can then be continuously updated and refined as advances in medicine are made. Unfortunately, physicians today are simply not able to keep up with the explosion of new medical information and technology. This ability to nearly instantaneously modify theMDATA system100 is a powerful feature of the system.

It is presently possible for a computer to search the world's medical literature daily. Any articles pertaining to a particular topic can automatically be requested and the information used to update the system.[0518]

In addition, the[0519]

MDATA system

100 is currently using optical character recognition technology to digitize its medical database. Then, using indexing techniques, theMDATA system100 is able to search for and retrieve any information desired. For example, the system can search for the character string “headache” and retrieve any amount of surrounding text or graphic information. This information is then collected, collated, printed and referred to the physician(s) maintaining the headache algorithm. This process will become easier as more of the world's medical literature is digitized.

Global Factors—Sensitivity and Selectivity[0520]

Another way in which the MDATA system is modifiable is in its use of global sensitivity/selectivity factors. As with every decision, there is always a balance to be achieved between risk and benefit, and so with the[0521]

MDATA system

100. One of the questions theMDATA system100 tries to answer is whether the patient needs to be seen immediately by a physician. This leads to this discussion about sensitivity and selectivity.

Sensitivity and selectivity are statistical terms that refer to how accurately a decision can be made. In this case, sensitivity refers to the number of patients which the[0522]

MDATA system

100 did not think needed to be seen by a physician but that actually did.

If the program were to be so sensitive that no disease process that eventually required meaningful physician intervention would be treated at home (no false negatives), then every single complaint would necessitate a visit to the doctor, which is a useless system. On the other hand, too selective a system (no false positives) i.e., no unnecessary visits to the doctor's office, would necessitate that an attempt be made at home treatment for every complaint, which is a useless and dangerous system.[0523]

So again, a balance must be reached between these two ends of the spectrum. To achieve this, the sensitivity/selectivity ratio of the[0524]

entire MDATA system

100 can be changed by setting or tuning a plurality of sensitivity factors. These sensitivity factors affect the following functions: meta thresholds, reenter horizon threshold, frequency of call back, symptom-severity filters, sequential slope filters, exponential symptom-severity filters, and probabilities of diagnoses in the treatment table. In addition, as in the headache example, the scoring of the screening questions already weighted is modulated or modified by the sensitivity factors.

Experience from the regionalization of trauma centers in this country shows an interesting trend over time with respect to sensitivity and selectivity. It has been shown that the inverse relationship between sensitivity and selectivity, when plotted over time, yields a sinusoidal wave form in which the amplitude of the wave form gradually decreases with time as the system is “fined tuned” as shown in Table 9 (FIG. 27). The MDATA system's sensitivity factors are designed to do just that, i.e., fine tune the system over time to find the right balance between sensitivity and selectivity.[0525]

In addition to the use of global factors, the[0526]

MDATA system

100 maintains what are termed “emergency filter response sets.” When a patient replies “yes” to any of the problem screening questions, the recommendation or message that follows is called an emergency filter response or “EFR.” The EFR sets are modularized so that the system can customize the message that the patient hears. This allows thesystem100 to match the EFR sets to the desired level of sensitivity or selectivity as well as provide information specific to an HMO or Managed Care Plan.

System Sensitivity Factors[0527]

There are ten sensitivity factors that affect threshold determination in the MDATA system[0528]100:

S1=system-wide (usually established by the system administrator and affects the entire MDATA system)[0529]

S2=the anatomic system of the body involved (e.g., nervous system in headache example)[0530]

S3=cause (e.g., infection causes meningitis)[0531]

S4=problem specific (established by the algorithm author at the beginning of an algorithm)[0532]

S5=question specific (within a particular algorithm)[0533]

S6=organizational specific (e.g., HMO, hospital)[0534]

S7=patient specific[0535]

S8=a reserved sensitivity factor for later use[0536]

S9=a reserved sensitivity factor for later use[0537]

S10=a reserved sensitivity factor for later use[0538]

Initially, the sensitivity factors have a value of 1.0. The sensitivity factor's value is usually inversely proportional to sensitivity; i.e., if the value is decreased, sensitivity increases.[0539]

The sensitivity factors are applied to the threshold constant value in the relational expression component of an IF-Then or If-Then-Else statement of a medical algorithm. For example, let's assume that the[0540]

system

100 is in the meningitis algorithm and that a temperature greater than 102 degrees will trigger a recommendation to go to a hospital. An example of a threshold calculation without sensitivity factors follows:

If temp>102 then X else Y[0541]

where X denotes the recommendation to go to the hospital and Y denotes a different branch point. Following is the same example, but including sensitivity factors:[0542]

If temp>([0543]102*S1*S2*S3*S4*S5*S6*S7*S8*S9*S10) then X else Y

The use of the sensitivity factors permits anticipation of change. Tuning the initial product of the sensitivity factors from “1.00” to “0.95” would decrease the temperature at which the system recommends a trip to the hospital. Each threshold calculation or other use of the sensitivity factors may use any number of (e.g., two factors) and any combination of the factors. Additionally, any combination of factors may be modified from the initial 1.0 value in any particular threshold calculation.[0544]

Age criteria is also modified by use of the sensitivity factors. For example: If Age>45*S1*S4 then X else Y.[0545]

Examples of areas the[0546]

system

100 could be tuned follow:

Anatomic system (e.g., cardiovascular)—the system is missing too many heart attacks;[0547]

Cause (infection)—the system is missing too many injuries (trauma);[0548]

Problem specific (e.g., headache)—the headache algorithm is missing too many cases of meningitis or subarachnoid bleeds;[0549]

Question specific (each question in an algorithm can be modified)—this would change the “weight” of a question in a series of weighted questions like the migraine screening questions;[0550]

Patient specific—one patient might want to be VERY careful while another might say, “in general I don't go to the doctor until I'm really sure something is wrong with me”;[0551]

Organizational (e.g., Kaiser patients)—Kaiser hospital management may say that the system is missing too many cases of meningitis and may request to be more careful with their patients (send them in with a lower temperature).[0552]

The sensitivity factors affect the following[0553]

system

100 functions:

(a) Re-enter Feature—the sensitivity factors affect the re-enter horizon, i.e., the amount of time after which the[0554]

system

100 considers a repetition of the same complaint to be a new problem. If sensitivity increases, the re-enter horizon becomes sooner.

(b) Meta Function—the sensitivity factors affect the matching and time density ratio thresholds. By reducing the values of the system-wide and problem sensitivity factors, e.g., from 1.0 to 0.9, the matching threshold and the time density ratio are decreased:[0555]

EXAMPLE 1Without Sensitivity Factors

Meta(“NHDA”, “****”, “**********”, 06/01/93, 12/31/93)[0556]

If MC>=3 then 100 else 101[0557]

EXAMPLE 1With Sensitivity Factors

Meta(“NHDA”, “****”, “**********”, 06/01/93, 12/31/93)[0558]

If MC>=(3*S1*S4) then 100 else 101[0559]

EXAMPLE 2Without Sensitivity Factors

Meta(“****”, “****”, “I**********”, 06/01/93, 12/31/93)[0560]

If TDR>=2.0 then 200 else 201[0561]

EXAMPLE 2With Sensitivity Factors

Meta(“****”, “****”, “I*********”, 06/01/93, 12/31/93)[0562]

If TDR>=(2.0*S1*S4) then 200 else 201[0563]

Thus, there is no necessity to change the algorithms themselves. In other words, the factors can be modified rather than changing the algorithms.[0564]

(c) Problem Questions—To take the headache example previously used, the sum of the scores of the screening and confirmation questions (and sometimes the questions themselves) is multiplied by the sensitivity factors. The questions are also weighted, of course, depending upon how important each question is to the diagnosis. The sum of the weighted scores is compared against the threshold value that will result in either making the diagnosis of say migraine (in response to the migraine screening questions) or confirming the diagnosis of migraine in response to the migraine confirmation questions.[0565]

Thus, if we wanted to increase the sensitivity of diagnosing subarachnoid hemorrhage, we would not have to write another algorithm, but rather, simply multiply the screening and confirmation scores by the sensitivity factors.[0566]

For example, if the threshold for the[0567]

MDATA system

100 to make a diagnosis of subarachnoid hemorrhage based on the sum of the weighted subarachnoid screening questions threshold is set at, say 75%, then that percentage of the sensitivity variable would make this diagnosis with a smaller score and, thus, pick up more cases. Thus, individual diagnoses within an algorithm can be “tuned” independently, and in some cases, this even applies to the individual questions themselves.

(d) Symptom Severity and Symptom Severity Trend Analysis—the sensitivity factors alter the absolute value, the first, second and third slope thresholds. With increased sensitivity, a more gently sloping line triggers an earlier medical evaluation. In the algorithm, when the[0568]

system

100 makes use of any quantitatable parameter to make a decision, all of these are joined, influenced or multiplied by the sensitivity factors. As a very simple example, if theMDATA system100 would normally make a recommendation, partly based on the age of the patient (e.g., if you are male and you are over 50 and . . . ), the decision can be triggered if the patient is 49 or 48 and so on.

(e) Home Diagnostic and Treatment Kit—if the patient has a MDATA system treatment kit or a blood pressure cuff, the level at which a fever or blood pressure effects a decision can be changed.[0569]

(f) Mental Status Examination—the mental status examination can be modified at a system, or problem (algorithm) level.[0570]

(g) Clinical Sound Library—the pattern matching process (as in the clinical sound library) is quantifiable by modifying the sensitivity factors.[0571]

XIX. Video Imaging of the Patient

There are four main types of video imaging: static black and white, static color, video black and white and video color. Each of these main types is now discussed.[0572]

Images as basic as static black and white images can provide useful information to the[0573]

system

100. Static black and white imaging is used with neural net pattern matching. This process permits analyzing for example, facial features to aid in the detection of certain diseases, such as the characteristic facies of Cushing's syndrome or the exophthalmos of Graves disease.

Color static imaging allows color frequency analysis to detect diseases that are not as readily detected with static black and white imaging, such as cyanosis of respiratory failure or the scleral icterus of hepatitis. Color thus provides an incremental benefit in the level of disease detection.[0574]

Real time black and white video imaging allows for the evaluation of physical signs such as pupillary responses, extra ocular muscle function, lid lag, and nystagmus. Cranial nerve function can be remotely evaluated, along with, for example, the distinction between central and peripheral VII nerve function.[0575]

Color video imaging, especially using fiber optics, adds much more capability in the evaluation of a patient's condition. For example, color video imaging is very useful in evaluating capillary refill or monitoring the response of a patient with cyanosis to supplemental oxygen. Another embodiment of the[0576]

system

100 may employ inexpensive laser sources to perform real time holographic imaging.

XX. Benefits of the MDATA System

It is rare when the humanitarian and entrepreneurial interests of a venture overlap. The confluence of purpose that exists in the MDATA system is striking. It is a “win-win” proposition from every perspective.[0577]

Not only will the[0578]

MDATA system

100 substantially reduce the overwhelming costs of our current health care system, but for the first time in history, every person can have access to high quality, 100%-consistent and affordable medical advice and information. No matter from what perspective one views theMDATA system100, its benefits are substantial.

The health care consumer obviously gains the most. Now, whenever he or she has a medical problem, or any member of their family, an immediate consultation can be obtained. The knowledge that the best health care information and medical advice is only a telephone call away can assuage the anxiety of everyone from new mothers to elderly patients confined to their homes.[0579]

By endorsing the[0580]

MDATA system

100, federal, state and local governments could discharge their obligation to provide a universal and affordable level of health care for all of their citizens. In addition, theMDATA system100 helps care for patients who cannot pay, thus relieving primary care physicians of the necessity to provide care without reimbursement. For the first time, Health Maintenance Organizations and Managed Care Plans will be able to effectively screen patients by telephone in order to ensure that patients are best matched with the services they need.

Specialists can use their talents, not on the repetition of familiar rituals, but will be free to concentrate on those more challenging problems that cannot easily be resolved by the[0581]

MDATA system

100. They will also benefit from an increased number of patient referrals as well as having a well-constructed patient history when a consultation is sought.

Physicians themselves can access the[0582]

MDATA system

100 in order to stay informed about new information and technological advances in the medical field. This is particularly true with the treatment, imaging, and laboratory test databases.

Medical information is a continually renewable resource because it is not consumed in its dissemination. The opportunity exists, through the[0583]

MDATA system

100, for the United States to provide much needed medical information to the world and, at the same time, bring capital into this country. In the process, this country could maintain its leadership in innovation, technology, and software development.

The United States and the world are facing a health care crisis so monumental that it is difficult to comprehend. There are diseases that threaten our very survival as a species. All of us know the apprehension and bewilderment we feel when an illness strikes. When this occurs, we need answers to specific medical questions, answers that are absolutely up-to-date, instantly available, and affordable.[0584]

The key is information: information about prevention, early detection of disease, and about its most efficient treatment. The[0585]

MDATA system

100 can provide this information through the simple use of the telephone, to nearly every inhabitant of the planet. In addition, theMDATA system100 converts and explains complicated medical terminology and concepts into language easily understood by everyone.

People do not have to be ill to consult the[0586]

MDATA system

100, just curious. Patients do not have to schedule appointments, they can simply pick up the telephone. Although many patients will later be seen by a physician, theMDATA system100 can provide immediate help for everyone. TheMDATA system100 at once establishes egalitarian access to health care information. Although many patients in this country receive state-of-the art medical care, there is a large segment of the population that is deprived of one the most basic health care and medical information. TheMDATA system100 begins to close this enormous gap.

The[0587]

MDATA system

100 begins to effect a restructuring of the health care delivery system in which both health care consumers and providers participate in the improvement of the system itself. TheMDATA system100 and its patients will be in partnership to provide the most current, economical, and concise treatment available. The upside potential is unlimited. Whether one believes health care is a right or a privilege, there can be no doubt that it is fundamentally necessary. Whether one believes we have a civic responsibility or a moral obligation to care for one another, it must be done. The fundamental simplicity of the structure of theMDATA system100 belies its power as a highly useful tool in the delivery of health care.

XXI. Optional System Configuration

A second embodiment of the MDATA system entails a major shift of how the questions and responses are delivered to the patient. Rather than the use of a telephone, the voice processing and voice response technology, the system software is published via media such as floppy disks, CD ROM, or PCMCIA cards for use on a patient's personal computer. This second embodiment is referred to as the screen version or the (Stand-Alone) SA-MDATA system. The computer could be, for example, a desktop computer, a laptop or notebook computer, or a handheld, pen-driven computer. The system questions are displayed on a display screen that is part of the computer or is connected to the computer. The patient uses a keyboard or a pointing/writing device connected to the computer to respond to the questions. The patient files are maintained and updated within the computer or on removable storage devices. The diagnosis, advice, and treatments can be displayed on the screen and also printed in hardcopy form on a printer (if available). New versions of the SA-MDATA system are either mailed to subscribers are available via modem. These new versions may include updates of the treatment table for new treatments. Another embodiment of the SA-MDATA system may include using specialized receiver devices that receive encoded FM signals on a demand basis when an event (a new treatment) triggers the device, such as described in U.S. Pat. No. 5,030,948.[0588]

A unique and separate authoring language (called File Output or FO) was used to develop the medical algorithms used in the screen version embodiment of the[0589]

system

100. Through the use of FO, the contents of text files are presented online to users, and then the users respond to questions and directions issued by the text files.

FO is designed as a typical, generalized authoring language, in which commands are embedded into text files (herein called FO files) to perform specific screen and keyboard functions. FO files are in effect programs written in the FO “language” that communicate (via FO) with the user online.[0590]

FO adds no text of its own. In fact, FO does not need to know what text file content it is executing. The programmer or author of a FO file is in complete control of the text content and the sequence in which it is presented. Using the various commands, the author can display text, format the screen, ask the user questions, input responses from the user, select different text files for execution, and generally control and direct the entire session.[0591]

This version of FO is intended as a development version that gives the user much freedom at the keyboard. The user can interrupt a presentation and edit the FO file being presented. The assumption here is that the user is in fact the author or an alpha tester charged with verifying and correcting file content.[0592]

A FO file is any standard sequential ASCII text file with variable-length lines terminating with a Carriage Return (ASCII[0593]13). Any line with a period in column one is treated as a command. A line without a leading period is treated as a print command.

The FO program processes a FO file by reading it one line at a time into memory. If the line is a text line, it is printed and the next line is loaded. If the line is a command line, the command is executed. If the command involves a wait on the user (such as a .M command), FO continues loading the FO file behind the scenes until it has been completely loaded. In this manner, FO executes the FO file as it is loading it. Once loaded, the FO file remains entirely in memory.[0594]

The system software for the screen version embodiment is written in Borland Turbo Pascal version 3.0. A second version of the system software for the screen version embodiment of the[0595]

system

100 is written in Microsoft G.W. Basic and is run in interpretive mode.

In yet other embodiments, other databases/files or algorithms can be used. The general system, method and procedures would remain the same. For example, a specialty field such as sports medicine could be added to the system.[0596]

The[0597]

MDATA system

100 described herein finds application in many environments, and is readily adaptable for use therein. For example, the system finds use in any application that is step-oriented and can be algorithmically described. For example, the system could give car diagnostic services over the phone to a caller. Then, when the car is brought to a service facility for repairs (treatment), the caller will be informed and have a good idea of what the problem is and probable repairs will be. Accordingly, the claims are to be interpreted to encompass these and other applications of the invention within their scope and are not to be limited to the embodiments described herein.

XXII. Summary of Advantages of the Present Invention

One of the main problems of the health care crisis is the limited access to health care information when it is needed. The MDATA system provides up-to-date medical information and advice that is instantly available twenty-four hours a day. The advice that is given is 100% consistent.[0598]

The quality of the advice is much better if a physician can stop, research, and anticipate all possible causes of a problem and then systematically go about dealing with all of these possible causes. In medical practice, a physician just does this from memory.[0599]

No humans are necessary to actually give the medical advice. The MDATA system is automated which helps to bring down the cost of health care.[0600]

An exact record of the questions asked and the answers given is stored in the patient's database. The MDATA system time-and-date stamps the responses to the questions (as transaction records) so that an exact reconstruction of the patient's interview(s) can be generated for use by a physician or other health care professional. The system also keeps a record of what version of an algorithm has been consulted as well as the sensitivity factor set for that consultation. At the conclusion of the interaction, the MDATA system can tell the patient how long the consultation has taken and what charges have been incurred, if any.[0601]

When possible, the[0602]

MDATA system

100 takes into account the past medical history of the patient, especially those pieces of information learned from past consultations with theMDATA system100, before advice is given. In addition, the advice given is different depending upon the age and sex of the patient. The “meta” functions provide another advantage by allowing theMDATA system100 to evaluate a problem in the context of the patient's prior consultations with the system.

While the above detailed description has shown, described and pointed out the fundamental novel features of the invention as applied to various embodiments, it will be understood that various omissions and substitutions and changes in the form and details of the device illustrated may be made by those skilled in the art, without departing from the spirit of the invention.[0603]