CN115547500B - Hemodialysis patient's health monitoring equipment and system - Google Patents
Hemodialysis patient's health monitoring equipment and systemDownload PDFInfo
- Publication number
- CN115547500B CN115547500BCN202211366302.1ACN202211366302ACN115547500BCN 115547500 BCN115547500 BCN 115547500BCN 202211366302 ACN202211366302 ACN 202211366302ACN 115547500 BCN115547500 BCN 115547500B
- Authority
- CN
- China
- Prior art keywords
- blood
- monitoring
- data
- index
- clinical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Human Computer Interaction (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- External Artificial Organs (AREA)
Abstract
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to health monitoring equipment and a health monitoring system for hemodialysis patients.
Background
In recent years, significant advances have been made in hemodialysis technology, but the risk of infection in hemodialysis patients remains far higher than that seen in the general population. Hemodialysis patients are at several times the risk of infection for the general population.
At present, when a clinical hemodialysis patient is monitored, the clinical physiological parameters of the patient are usually determined regularly when the patient receives hemodialysis, infection risk prediction is carried out on the clinical physiological parameters by combining the actual conditions of the patient, the existing scheme cannot realize intelligent monitoring of the patient, a large amount of manpower is still consumed for real-time supervision, and the accuracy of health monitoring is greatly reduced.
Disclosure of Invention
The invention provides a health monitoring device and system for hemodialysis patients, which are used for realizing intelligent monitoring of the hemodialysis patients and improving the accuracy of health monitoring.
The invention provides a health monitoring device for hemodialysis patients, which acquires blood detection data of clinical hemodialysis patients, extracts index data of the blood detection data according to a plurality of preset blood monitoring indexes, and obtains monitoring index data corresponding to each blood monitoring index; the health monitoring equipment of the hemodialysis patient calls a plurality of preset index distribution functions to respectively fit a blood distribution curve corresponding to each blood monitoring index according to the monitoring index data of each blood monitoring index; the health monitoring equipment of the hemodialysis patient carries out abnormal fluctuation analysis on the plurality of blood monitoring indexes according to the blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generates a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the abnormal monitoring index set; the health monitoring equipment for the hemodialysis patient acquires clinical video data of the clinical hemodialysis patient based on a preset clinical monitoring terminal, and performs behavior state analysis on the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient; the health monitoring equipment of the hemodialysis patient inputs the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model for infection risk prediction and outputs an infection risk prediction result; and the health monitoring equipment of the hemodialysis patient generates health early warning information of the clinical hemodialysis patient according to the infection risk prediction result, generates a health analysis report according to the health early warning information, and sends the health analysis report to a preset nursing terminal for health monitoring.
Optionally, in a first implementation manner of the first aspect of the present invention, the acquiring, by the health monitoring device for the hemodialysis patient, blood detection data of a clinical hemodialysis patient, and performing index data extraction on the blood detection data according to a plurality of preset blood monitoring indexes to obtain monitoring index data corresponding to each blood monitoring index includes: crawling blood detection data of a clinical hemodialysis patient from a preset blood detection database, wherein the blood detection data are a plurality of times of blood sampling analysis data in a preset detection period; constructing a mapping relation between a plurality of preset blood monitoring indexes and index data; index data of blood sampling analysis data of each time is inquired from the blood sampling analysis data of multiple times according to the mapping relation; and performing data integration on the index data of the blood sampling analysis data every time to obtain the monitoring index data corresponding to each blood monitoring index.
Optionally, in a second implementation manner of the first aspect of the present invention, the method for fitting a blood distribution curve corresponding to each blood monitoring index by a health monitoring device of a hemodialysis patient calling a plurality of preset index distribution functions according to monitoring index data of each blood monitoring index includes: extracting time sequence data corresponding to the monitoring index data; performing data alignment on the monitoring index data of each blood monitoring index according to the time sequence data to obtain time sequence index data; calling a plurality of preset index distribution functions to calculate the characteristic distribution value of the time sequence index data; and respectively drawing a blood distribution curve corresponding to each blood monitoring index according to the characteristic distribution value.
Optionally, in a third implementation manner of the first aspect of the present invention, the health monitoring device for a hemodialysis patient performs abnormal fluctuation analysis on the multiple blood monitoring indexes according to a blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generates a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the abnormal monitoring index set, including: respectively calculating a plurality of characteristic values in the blood distribution curve of each blood monitoring index, and acquiring a standard value of each blood monitoring index; respectively comparing the plurality of characteristic values with the standard value to obtain a comparison result, and generating a characteristic abnormal value according to the comparison result; inquiring a plurality of abnormal blood monitoring indexes corresponding to the characteristic abnormal values, and generating an abnormal monitoring index set according to the plurality of abnormal blood monitoring indexes; and taking the characteristic abnormal value as a matrix element corresponding to the abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the matrix element.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the acquiring, by the health monitoring device for the hemodialysis patient, clinical video data of the clinical hemodialysis patient based on a preset clinical monitoring terminal, and performing behavior state analysis on the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient includes: acquiring clinical video data of the clinical hemodialysis patient according to a preset video acquisition time period based on a preset clinical monitoring terminal; carrying out audio and image segmentation on the clinical video data to obtain audio data and image data; generating an audio characteristic corresponding to the clinical hemodialysis patient according to the audio data, and generating a behavior characteristic corresponding to the clinical hemodialysis patient according to the image data; and inputting the audio features and the behavior features into a preset behavior state analysis model for behavior state analysis to obtain a behavior state evaluation coefficient.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the health monitoring device of the hemodialysis patient inputs the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model to predict infection risk, and outputs an infection risk prediction result, including: performing matrix conversion on the blood state evaluation matrix according to the behavior state evaluation coefficient to obtain a target state matrix; inputting the target state matrix into a preset blood infection risk prediction model, wherein the blood infection risk prediction model comprises a convolutional layer and a normalization function; performing infection risk prediction on the target state matrix through the blood infection risk prediction model, and outputting an infection risk prediction probability, wherein the infection risk prediction probability is used for indicating the probability of infection of the clinical hemodialysis patient; and generating an infection risk prediction result according to the infection risk prediction probability.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the health monitoring device of the hemodialysis patient acquires physiological index data of the clinical hemodialysis patient, and calculates an index change rate of the physiological index data; judging whether the clinical hemodialysis patient meets a preset physiological normal condition or not according to the index change rate to obtain a judgment result; and carrying out health monitoring on the clinical hemodialysis patient according to the judgment result and the infection risk prediction result.
A second aspect of the present invention provides a health monitoring system for a hemodialysis patient, the health monitoring system comprising: the system comprises an acquisition module, a data acquisition module and a data processing module, wherein the acquisition module is used for acquiring blood detection data of a clinical hemodialysis patient, and extracting index data of the blood detection data according to a plurality of preset blood monitoring indexes to obtain monitoring index data corresponding to each blood monitoring index; the fitting module is used for calling a plurality of preset index distribution functions to respectively fit a blood distribution curve corresponding to each blood monitoring index according to the monitoring index data of each blood monitoring index; the analysis module is used for performing abnormal fluctuation analysis on the plurality of blood monitoring indexes according to the blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the abnormal monitoring index set; the processing module is used for acquiring clinical video data of the clinical hemodialysis patient based on a preset clinical monitoring terminal, and analyzing the behavior state of the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient; the prediction module is used for inputting the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model for infection risk prediction and outputting an infection risk prediction result; and the monitoring module is used for generating health early warning information of the clinical hemodialysis patient according to the infection risk prediction result, generating a health analysis report according to the health early warning information, and sending the health analysis report to a preset nursing terminal for health monitoring.
Optionally, in a first implementation manner of the second aspect of the present invention, the obtaining module is specifically configured to: crawling blood detection data of a clinical hemodialysis patient from a preset blood detection database, wherein the blood detection data are a plurality of times of blood sampling analysis data in a preset detection period; constructing a mapping relation between a plurality of preset blood monitoring indexes and index data; index data of blood sampling analysis data of each time is inquired from the blood sampling analysis data of multiple times according to the mapping relation; and performing data integration on the index data of the blood sampling analysis data every time to obtain the monitoring index data corresponding to each blood monitoring index.
Optionally, in a second implementation manner of the second aspect of the present invention, the fitting module is specifically configured to: extracting time sequence data corresponding to the monitoring index data; performing data alignment on the monitoring index data of each blood monitoring index according to the time sequence data to obtain time sequence index data; calling a plurality of preset index distribution functions to calculate the characteristic distribution value of the time sequence index data; and respectively drawing a blood distribution curve corresponding to each blood monitoring index according to the characteristic distribution value.
Optionally, in a third implementation manner of the second aspect of the present invention, the analysis module is specifically configured to: respectively calculating a plurality of characteristic values in the blood distribution curve of each blood monitoring index, and acquiring a standard value of each blood monitoring index; respectively comparing the plurality of characteristic values with the standard value to obtain a comparison result, and generating a characteristic abnormal value according to the comparison result; inquiring a plurality of abnormal blood monitoring indexes corresponding to the characteristic abnormal values, and generating an abnormal monitoring index set according to the plurality of abnormal blood monitoring indexes; and taking the characteristic abnormal value as a matrix element corresponding to the abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the matrix element.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the processing module is specifically configured to: acquiring clinical video data of the clinical hemodialysis patient according to a preset video acquisition time period based on a preset clinical monitoring terminal; carrying out audio and image segmentation on the clinical video data to obtain audio data and image data; generating an audio characteristic corresponding to the clinical hemodialysis patient according to the audio data, and generating a behavior characteristic corresponding to the clinical hemodialysis patient according to the image data; and inputting the audio features and the behavior features into a preset behavior state analysis model for behavior state analysis to obtain a behavior state evaluation coefficient.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the prediction module is specifically configured to: performing matrix conversion on the blood state evaluation matrix according to the behavior state evaluation coefficient to obtain a target state matrix; inputting the target state matrix into a preset blood infection risk prediction model, wherein the blood infection risk prediction model comprises a convolutional layer and a normalization function; performing infection risk prediction on the target state matrix through the blood infection risk prediction model, and outputting an infection risk prediction probability, wherein the infection risk prediction probability is used for indicating the probability of infection of the clinical hemodialysis patient; and generating an infection risk prediction result according to the infection risk prediction probability.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the health monitoring system for hemodialysis patients further includes: the judgment module is used for acquiring physiological index data of the clinical hemodialysis patient and calculating the index change rate of the physiological index data; judging whether the clinical hemodialysis patient meets a preset physiological normal condition or not according to the index change rate to obtain a judgment result; and carrying out health monitoring on the clinical hemodialysis patient according to the judgment result and the infection risk prediction result.
In the technical scheme provided by the invention, a plurality of index distribution functions are called to respectively fit a blood distribution curve according to the monitoring index data of each blood monitoring index; the method comprises the steps of carrying out abnormal fluctuation analysis on a plurality of blood monitoring indexes according to a blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, generating a blood state evaluation matrix according to the abnormal monitoring index set, improving the detection accuracy of the abnormal fluctuation analysis by fitting the blood distribution curve, further constructing the blood state evaluation matrix through the detected abnormal monitoring index set, carrying out infection risk prediction on the blood state evaluation matrix through a blood infection risk prediction model, improving the accuracy of infection risk prediction, further realizing intelligent monitoring of hemodialysis patients and improving the accuracy of health monitoring.
Drawings
FIG. 1 is a schematic diagram of one embodiment of a hemodialysis patient health monitoring apparatus in an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a hemodialysis patient health monitoring apparatus in an embodiment of the present invention;
FIG. 3 is a schematic diagram of one embodiment of a health monitoring system for a hemodialysis patient in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of another embodiment of a hemodialysis patient health monitoring system in accordance with an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a health monitoring device and system for hemodialysis patients, which are used for realizing intelligent monitoring of the hemodialysis patients and improving the accuracy of health monitoring. The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a detailed flow of an embodiment of the present invention is described below, with reference to fig. 1, an embodiment of a hemodialysis patient health monitoring apparatus in an embodiment of the present invention includes:
101. obtaining blood detection data of a clinical hemodialysis patient, and extracting index data of the blood detection data according to a plurality of preset blood monitoring indexes to obtain monitoring index data corresponding to each blood monitoring index;
it is understood that the subject of the present invention may be a health monitoring system of a hemodialysis patient, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
Specifically, the blood detection data to be described includes blood detection data corresponding to a plurality of blood detection indexes, and it is to be described that the blood detection indexes include one of the most basic examinations in the blood examination, and data in the blood routine examination is observed, and the blood routine examination report includes Red Blood Cells (RBC), hemoglobin (Hb), white Blood Cells (WBC) and white blood cell classification count, hematocrit (HCT), and Platelets (PL).
102. Calling a plurality of preset index distribution functions to respectively fit a blood distribution curve corresponding to each blood monitoring index according to the monitoring index data of each blood monitoring index;
specifically, in the embodiment of the present invention, the server adopts a numerical analysis method to fit the blood distribution curve corresponding to the blood monitoring index in a segmented manner, and performs continuous correction, so that the correlation between the obtained blood distribution curve and the actual blood distribution curve is strongest. As is known, the accuracy of the value of the blood distribution curve directly affects the accuracy of the calculation result of the blood monitoring index, and through the steps, the accuracy of the calculated value in the blood distribution curve in the blood monitoring index can be improved.
103. Carrying out abnormal fluctuation analysis on a plurality of blood monitoring indexes according to the blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to a clinical hemodialysis patient according to the abnormal monitoring index set;
specifically, the server obtains a blood distribution curve of the blood monitoring index, the blood distribution curve of the blood monitoring index comprises at least one index data, the server determines at least one abnormal fluctuation index data in the at least one index data according to a preset data fluctuation detection method, the abnormal fluctuation index data are analyzed according to corresponding preset dimension information respectively, corresponding abnormal fluctuation analysis results are generated, the preset dimension information comprises dimensions of the abnormal fluctuation index data and at least one dimension index data corresponding to each dimension, and accuracy of data abnormal fluctuation detection and efficiency of analysis of data abnormal fluctuation reasons are improved.
104. Acquiring clinical video data of a clinical hemodialysis patient based on a preset clinical monitoring terminal, and analyzing the behavior state of the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient;
specifically, the server establishes a behavior recognition database and a behavior micro-expression database, acquires clinical video data to obtain behavior images, preprocesses the acquired clinical video data to eliminate background variegations in the clinical video data, performs emotion analysis on emotion characteristics in the preprocessed clinical video data, and completes recognition of the clinical video data. According to the invention, redundant confounding colors in the image can be removed by preprocessing the clinical video data such as edge extraction, histogram equalization, skin color segmentation and illumination compensation, and the server obtains the behavior state evaluation coefficient, so that the subsequent analysis and identification of details such as expression of the behavior are more accurate, and the identification time is further shortened.
105. Inputting the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model for infection risk prediction, and outputting an infection risk prediction result;
optionally, the server screens out evaluation indexes related to blood infection risk, brings the evaluation indexes into a preset regression model, analyzes and calculates regression coefficients of risk factors determining blood infection risk, then obtains risk scores through the regression coefficients of the risk factors, and finally calculates blood infection probability values by combining the risk scores with a blood infection risk prediction function, so that a risk prediction model based on a scoring system can be established. The prediction model of the invention has good fitting, shows better risk prediction capability compared with the existing foreign models, can achieve the aim of early screening postoperative blood infection high-risk patients, and plays the roles of early prevention, early discovery and early treatment, thereby reducing the incidence of blood infection risk.
106. And generating health early warning information of the clinical hemodialysis patient according to the infection risk prediction result, generating a health analysis report according to the health early warning information, and sending the health analysis report to a preset nursing terminal for health monitoring.
Specifically, health early warning information of a clinical hemodialysis patient is generated according to an infection risk prediction result, a health analysis report is generated according to the health early warning information, the health analysis report is sent to a preset nursing terminal for health monitoring, the server acquires health index data of a user, performs overall analysis and evaluation on all the health index data, performs individual analysis and evaluation on each health index data, queries the overall evaluation result and the individual evaluation result as indexes in a preset corpus respectively, gives a corresponding health suggestion according to the health early warning information, generates a health analysis report, and sends the health analysis report to the preset nursing terminal for health monitoring.
In the embodiment of the invention, a plurality of index distribution functions are called to respectively fit the blood distribution curves according to the monitoring index data of each blood monitoring index; the method comprises the steps of carrying out abnormal fluctuation analysis on a plurality of blood monitoring indexes according to a blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, generating a blood state evaluation matrix according to the abnormal monitoring index set, improving the detection accuracy of the abnormal fluctuation analysis by fitting the blood distribution curve, further constructing the blood state evaluation matrix through the detected abnormal monitoring index set, carrying out infection risk prediction on the blood state evaluation matrix through a blood infection risk prediction model, improving the accuracy of infection risk prediction, further realizing intelligent monitoring of hemodialysis patients and improving the accuracy of health monitoring.
Referring to fig. 2, another embodiment of a health monitoring apparatus for hemodialysis patients in accordance with an embodiment of the present invention comprises:
201. obtaining blood detection data of a clinical hemodialysis patient, and extracting index data of the blood detection data according to a plurality of preset blood monitoring indexes to obtain monitoring index data corresponding to each blood monitoring index;
specifically, blood detection data of a clinical hemodialysis patient is crawled from a preset blood detection database, wherein the blood detection data is a plurality of times of blood sampling analysis data in a preset detection period; constructing a mapping relation between a plurality of preset blood monitoring indexes and index data; index data of blood sampling analysis data of each time is inquired from the blood sampling analysis data of multiple times according to the mapping relation; and performing data integration on the index data of the blood sampling analysis data every time to obtain the monitoring index data corresponding to each blood monitoring index.
The server presets a plurality of sets of blood detection schemes in a local RFID scanning terminal, wherein each set of blood detection scheme comprises the following steps: a combination of a plurality of different types of blood test data (e.g., 10 and 12 blood test tubes), corresponding to the organization name. It should be noted that the data of the blood testing protocol may be stored in the server or in a local RFID scanning terminal. If the RFID scanning terminal is stored locally, the process of pulling data from the server to the RFID scanning terminal can be reduced, and the functions of the RFID scanning terminal and the server are further integrated.
Specifically, each blood test tube is filled with a blood sample and is adhered with an RFID label, test tube number data recorded in the RFID label is in one-to-one correlation correspondence with blood detection data in the blood test tube, a server constructs a preset mapping relation between a plurality of blood monitoring indexes and index data, the index data of each blood sampling analysis data is inquired from a plurality of times of blood sampling analysis data according to the mapping relation, data integration is carried out on the index data of each blood sampling analysis data, and the monitoring index data corresponding to each blood monitoring index is obtained.
202. Calling a plurality of preset index distribution functions to respectively fit a blood distribution curve corresponding to each blood monitoring index according to the monitoring index data of each blood monitoring index;
specifically, extracting time sequence data corresponding to the monitoring index data; performing data alignment on the monitoring index data of each blood monitoring index according to the time sequence data to obtain time sequence index data; calling a plurality of preset index distribution functions to calculate the characteristic distribution value of the time sequence index data; and respectively drawing a blood distribution curve corresponding to each blood monitoring index according to the characteristic distribution values.
The server extracts time sequence data corresponding to the monitoring index data, performs data alignment on the acquired data, retains the monitoring index data and the blood data existing at the same time, and calls a plurality of preset index distribution functions in the processed acquired data to calculate a characteristic distribution value of the time sequence index data; the method comprises the steps that a blood distribution curve corresponding to each blood monitoring index is respectively drawn according to a characteristic distribution value, specifically, a server keeps monitoring index data X of a sample A unchanged, monitoring index data Y of a sample B is more than t1 moment forward and more than t2 moment backward, a sampling window is moved backward from data start for the data Y, and when the window is moved every time, delay correlation between data in the sampling window after the data Y is moved and the data X is calculated, so that the blood distribution curve corresponding to each blood monitoring index is obtained, the correlation is more accurate, and the health monitoring accuracy is further improved.
203. Carrying out abnormal fluctuation analysis on the plurality of blood monitoring indexes according to the blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to a clinical hemodialysis patient according to the abnormal monitoring index set;
specifically, a plurality of characteristic values in a blood distribution curve of each blood monitoring index are respectively calculated, and a standard value of each blood monitoring index is obtained; respectively comparing the plurality of characteristic values with the standard values to obtain comparison results, and generating characteristic abnormal values according to the comparison results; inquiring a plurality of abnormal blood monitoring indexes corresponding to the characteristic abnormal values, and generating an abnormal monitoring index set according to the plurality of abnormal blood monitoring indexes; and taking the characteristic abnormal value as a matrix element corresponding to the abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the matrix element.
Optionally, it should be noted that the data fluctuation detection method may be a preset algorithm for detecting whether the index data is abnormal fluctuation index data, and specifically, whether the index data is abnormal fluctuation index data may be determined by detecting a fluctuation amount or a fluctuation rate of the index data. Further, after determining at least one abnormal fluctuation index data in the at least one index data according to a preset data fluctuation detection method, generating data abnormal fluctuation warning information may also be included. Specifically, a data abnormal fluctuation warning message may be generated after each determination of one abnormal fluctuation index data, or a data abnormal fluctuation warning message may be generated after at least one abnormal fluctuation index data in at least one index data is determined. Specifically, the server obtains each abnormal fluctuation index data in at least one abnormal fluctuation index data, analyzes the abnormal fluctuation index data according to the corresponding preset dimension information, and generates a corresponding abnormal fluctuation analysis result, that is, each abnormal fluctuation index data generates a corresponding abnormal fluctuation analysis result. The invention can also generate an abnormal monitoring index set according to a plurality of abnormal blood monitoring indexes; and taking the characteristic abnormal value as a matrix element corresponding to the abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the matrix element.
204. Acquiring clinical video data of a clinical hemodialysis patient based on a preset clinical monitoring terminal, and analyzing the behavior state of the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient;
specifically, based on a preset clinical monitoring terminal, acquiring clinical video data of a clinical hemodialysis patient according to a preset video acquisition time period; carrying out audio and image segmentation on the clinical video data to obtain audio data and image data; generating an audio characteristic corresponding to the clinical hemodialysis patient according to the audio data, and generating a behavior characteristic corresponding to the clinical hemodialysis patient according to the image data; and inputting the audio characteristics and the behavior characteristics into a preset behavior state analysis model for behavior state analysis to obtain a behavior state evaluation coefficient.
Optionally, in this embodiment, a method based on a statistical histogram may be further used for initial background estimation, the algorithm is based on the assumption that a moving object does not stay at one position for a long time in a scene, a pixel value with the highest occurrence frequency at a specific pixel position of a video sequence is a background pixel value of the point within a certain period of time, specifically, the server counts consecutive N frames, records the occurrence condition of a point gray scale in the pixel, and uses the maximum occurrence frequency of the point gray scale of the consecutive N frames as a gray scale value of the point, i.e., an initial background gray scale value, and further, the server performs background update by using a histogram method, and needs to segment the object for detecting a behavior feature, the algorithm segments the moving object by using a method based on a background difference, and performs morphological filtering and connected domain calculation on the segmented result to obtain a full moving object, and finally, the server generates an audio feature corresponding to a clinical hemodialysis patient according to the audio data, and generates a behavior feature corresponding to the clinical hemodialysis patient according to the image data; and inputting the audio characteristics and the behavior characteristics into a preset behavior state analysis model for behavior state analysis to obtain a behavior state evaluation coefficient.
205. Inputting the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model for infection risk prediction, and outputting an infection risk prediction result;
specifically, matrix conversion is carried out on the blood state evaluation matrix according to the behavior state evaluation coefficient to obtain a target state matrix; inputting the target state matrix into a preset blood infection risk prediction model, wherein the blood infection risk prediction model comprises a convolutional layer and a normalization function; predicting the infection risk of the target state matrix through a blood infection risk prediction model, and outputting an infection risk prediction probability, wherein the infection risk prediction probability is used for indicating the probability of infection of a clinical hemodialysis patient; and generating an infection risk prediction result according to the infection risk prediction probability.
The server performs matrix conversion on the blood state evaluation matrix according to the behavior state evaluation coefficient to obtain a target state matrix, and inputs the target state matrix into a preset blood infection risk prediction model, wherein the blood infection risk prediction model comprises a convolutional layer and a normalization function, and specifically, the server processes an input image by adopting the convolutional layer in a preset convolutional network; the method comprises the steps of processing a target state matrix by a convolutional layer in a convolutional network, inputting a feature vector passing through the convolutional layer into a normalization layer, processing a normalized result for N4 times by the convolutional layer or the convolutional network, connecting the feature vector processed for N4 times to a full connection layer, calculating loss function values of a training sample and a real sample by a loss function, performing reverse iteration until the model converges, and finally outputting an infection risk prediction probability by a blood infection risk prediction model.
206. Generating health early warning information of a clinical hemodialysis patient according to an infection risk prediction result, generating a health analysis report according to the health early warning information, and sending the health analysis report to a preset nursing terminal for health monitoring;
207. acquiring physiological index data of a clinical hemodialysis patient, and calculating the index change rate of the physiological index data;
208. judging whether the clinical hemodialysis patient meets preset physiological normal conditions or not according to the index change rate to obtain a judgment result;
209. and carrying out health monitoring on the clinical hemodialysis patient according to the judgment result and the infection risk prediction result.
Specifically, health early warning information of clinical hemodialysis patients is generated according to infection risk prediction results, health analysis reports are generated according to the health early warning information, the health analysis reports are sent to a preset nursing terminal for health monitoring, the server acquires health index data of users, overall analysis and evaluation are conducted on all the health index data, individual analysis and evaluation are conducted on all the health index data, the overall evaluation results and the individual evaluation results are respectively used as indexes to be inquired in a pre-established corpus, and meanwhile the server gives corresponding health suggestions according to the health early warning information and generates health analysis reports. Optionally, the server obtains physiological index data of the clinical hemodialysis patient, calculates an index change rate of the physiological index data, judges whether the clinical hemodialysis patient meets a preset physiological normal condition according to the index change rate to obtain a judgment result, and performs health monitoring on the clinical hemodialysis patient according to the judgment result and an infection risk prediction result, so that the accuracy and efficiency of health monitoring can be further improved.
In the embodiment of the invention, a plurality of index distribution functions are called to respectively fit the blood distribution curves according to the monitoring index data of each blood monitoring index; the method comprises the steps of carrying out abnormal fluctuation analysis on a plurality of blood monitoring indexes according to a blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, generating a blood state evaluation matrix according to the abnormal monitoring index set, improving the detection accuracy of the abnormal fluctuation analysis by fitting the blood distribution curve, further constructing the blood state evaluation matrix through the detected abnormal monitoring index set, carrying out infection risk prediction on the blood state evaluation matrix through a blood infection risk prediction model, improving the accuracy of infection risk prediction, further realizing intelligent monitoring of hemodialysis patients and improving the accuracy of health monitoring.
With reference to fig. 3, the health monitoring system for hemodialysis patients in the embodiment of the present invention is described above, and an embodiment of the health monitoring system for hemodialysis patients in the embodiment of the present invention includes:
theacquisition module 301 is configured to acquire blood detection data of a clinical hemodialysis patient, and perform index data extraction on the blood detection data according to a plurality of preset blood monitoring indexes to obtain monitoring index data corresponding to each blood monitoring index;
afitting module 302, configured to call a plurality of preset index distribution functions to respectively fit a blood distribution curve corresponding to each blood monitoring index according to the monitoring index data of each blood monitoring index;
ananalysis module 303, configured to perform abnormal fluctuation analysis on the multiple blood monitoring indexes according to a blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generate a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the abnormal monitoring index set;
theprocessing module 304 is configured to acquire clinical video data of the clinical hemodialysis patient based on a preset clinical monitoring terminal, and perform behavior state analysis on the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient;
theprediction module 305 is configured to input the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model to perform infection risk prediction, and output an infection risk prediction result;
and themonitoring module 306 is configured to generate health early warning information of the clinical hemodialysis patient according to the infection risk prediction result, generate a health analysis report according to the health early warning information, and send the health analysis report to a preset nursing terminal for health monitoring.
In the embodiment of the invention, a plurality of index distribution functions are called to respectively fit the blood distribution curves according to the monitoring index data of each blood monitoring index; the method comprises the steps of carrying out abnormal fluctuation analysis on a plurality of blood monitoring indexes according to a blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, generating a blood state evaluation matrix according to the abnormal monitoring index set, improving the detection accuracy of the abnormal fluctuation analysis by fitting the blood distribution curve, further constructing the blood state evaluation matrix through the detected abnormal monitoring index set, carrying out infection risk prediction on the blood state evaluation matrix through a blood infection risk prediction model, improving the accuracy of infection risk prediction, further realizing intelligent monitoring of hemodialysis patients and improving the accuracy of health monitoring.
Referring to fig. 4, another embodiment of the health monitoring system for hemodialysis patients in accordance with the present invention comprises:
the obtainingmodule 301 is configured to obtain blood detection data of a clinical hemodialysis patient, and perform index data extraction on the blood detection data according to a plurality of preset blood monitoring indexes to obtain monitoring index data corresponding to each blood monitoring index;
afitting module 302, configured to call a plurality of preset index distribution functions to respectively fit a blood distribution curve corresponding to each blood monitoring index according to the monitoring index data of each blood monitoring index;
ananalysis module 303, configured to perform abnormal fluctuation analysis on the multiple blood monitoring indexes according to a blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generate a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the abnormal monitoring index set;
theprocessing module 304 is configured to acquire clinical video data of the clinical hemodialysis patient based on a preset clinical monitoring terminal, and perform behavior state analysis on the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient;
theprediction module 305 is configured to input the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model to perform infection risk prediction, and output an infection risk prediction result;
and themonitoring module 306 is configured to generate health early warning information of the clinical hemodialysis patient according to the infection risk prediction result, generate a health analysis report according to the health early warning information, and send the health analysis report to a preset nursing terminal for health monitoring.
Optionally, the obtainingmodule 301 is specifically configured to: crawling blood detection data of a clinical hemodialysis patient from a preset blood detection database, wherein the blood detection data are a plurality of times of blood sampling analysis data in a preset detection period; constructing a mapping relation between a plurality of preset blood monitoring indexes and index data; index data of blood sampling analysis data of each time is inquired from the blood sampling analysis data of multiple times according to the mapping relation; and performing data integration on the index data of the blood sampling analysis data every time to obtain the monitoring index data corresponding to each blood monitoring index.
Optionally, thefitting module 302 is specifically configured to: extracting time sequence data corresponding to the monitoring index data; performing data alignment on the monitoring index data of each blood monitoring index according to the time sequence data to obtain time sequence index data; calling a plurality of preset index distribution functions to calculate the characteristic distribution value of the time sequence index data; and respectively drawing a blood distribution curve corresponding to each blood monitoring index according to the characteristic distribution value.
Optionally, theanalysis module 303 is specifically configured to: respectively calculating a plurality of characteristic values in the blood distribution curve of each blood monitoring index, and acquiring a standard value of each blood monitoring index; respectively comparing the plurality of characteristic values with the standard value to obtain a comparison result, and generating a characteristic abnormal value according to the comparison result; inquiring a plurality of abnormal blood monitoring indexes corresponding to the characteristic abnormal values, and generating an abnormal monitoring index set according to the plurality of abnormal blood monitoring indexes; and taking the characteristic abnormal value as a matrix element corresponding to the abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the matrix element.
Optionally, theprocessing module 304 is specifically configured to: based on a preset clinical monitoring terminal, acquiring clinical video data of the clinical hemodialysis patient according to a preset video acquisition time period; carrying out audio and image segmentation on the clinical video data to obtain audio data and image data; generating an audio characteristic corresponding to the clinical hemodialysis patient according to the audio data, and generating a behavior characteristic corresponding to the clinical hemodialysis patient according to the image data; and inputting the audio features and the behavior features into a preset behavior state analysis model for behavior state analysis to obtain a behavior state evaluation coefficient.
Optionally, theprediction module 305 is specifically configured to: performing matrix conversion on the blood state evaluation matrix according to the behavior state evaluation coefficient to obtain a target state matrix; inputting the target state matrix into a preset blood infection risk prediction model, wherein the blood infection risk prediction model comprises a convolutional layer and a normalization function; performing infection risk prediction on the target state matrix through the blood infection risk prediction model, and outputting an infection risk prediction probability, wherein the infection risk prediction probability is used for indicating the probability of infection of the clinical hemodialysis patient; and generating an infection risk prediction result according to the infection risk prediction probability.
Optionally, the health monitoring system for hemodialysis patients further comprises:
a judgingmodule 307, configured to obtain physiological index data of the clinical hemodialysis patient, and calculate an index change rate of the physiological index data; judging whether the clinical hemodialysis patient meets a preset physiological normal condition or not according to the index change rate to obtain a judgment result; and carrying out health monitoring on the clinical hemodialysis patient according to the judgment result and the infection risk prediction result.
In the embodiment of the invention, a plurality of index distribution functions are called to respectively fit the blood distribution curves according to the monitoring index data of each blood monitoring index; the method comprises the steps of carrying out abnormal fluctuation analysis on a plurality of blood monitoring indexes according to a blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, generating a blood state evaluation matrix according to the abnormal monitoring index set, improving the detection accuracy of the abnormal fluctuation analysis by fitting the blood distribution curve, further constructing the blood state evaluation matrix through the detected abnormal monitoring index set, carrying out infection risk prediction on the blood state evaluation matrix through a blood infection risk prediction model, improving the accuracy of infection risk prediction, further realizing intelligent monitoring of hemodialysis patients and improving the accuracy of health monitoring.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. The health monitoring equipment for the hemodialysis patient is characterized in that the health monitoring equipment for the hemodialysis patient acquires blood detection data of a clinical hemodialysis patient, and performs index data extraction on the blood detection data according to a plurality of preset blood monitoring indexes to obtain monitoring index data corresponding to each blood monitoring index;
the health monitoring equipment of the hemodialysis patient calls a plurality of preset index distribution functions to respectively fit a blood distribution curve corresponding to each blood monitoring index according to the monitoring index data of each blood monitoring index;
the health monitoring equipment of the hemodialysis patient carries out abnormal fluctuation analysis on the plurality of blood monitoring indexes according to the blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generates a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the abnormal monitoring index set;
the health monitoring equipment of the hemodialysis patient acquires clinical video data of the clinical hemodialysis patient based on a preset clinical monitoring terminal, and analyzes the behavior state of the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient;
the health monitoring equipment of the hemodialysis patient inputs the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model for infection risk prediction and outputs an infection risk prediction result;
and the health monitoring equipment of the hemodialysis patient generates health early warning information of the clinical hemodialysis patient according to the infection risk prediction result, generates a health analysis report according to the health early warning information, and sends the health analysis report to a preset nursing terminal for health monitoring.
2. The hemodialysis patient health monitoring apparatus of claim 1, wherein the hemodialysis patient health monitoring apparatus obtains blood detection data of a clinical hemodialysis patient, and performs index data extraction on the blood detection data according to a plurality of preset blood monitoring indexes to obtain monitoring index data corresponding to each blood monitoring index, and the monitoring index data comprises:
crawling blood detection data of a clinical hemodialysis patient from a preset blood detection database, wherein the blood detection data are a plurality of times of blood sampling analysis data in a preset detection period;
constructing a mapping relation between a plurality of preset blood monitoring indexes and index data;
index data of blood sampling analysis data of each time is inquired from the blood sampling analysis data of multiple times according to the mapping relation;
and performing data integration on the index data of the blood sampling analysis data every time to obtain the monitoring index data corresponding to each blood monitoring index.
3. The hemodialysis patient health monitoring apparatus according to claim 1, wherein the hemodialysis patient health monitoring apparatus calls a plurality of preset index distribution functions to respectively fit a blood distribution curve corresponding to each blood monitoring index according to the monitoring index data of each blood monitoring index, and the method comprises:
extracting time sequence data corresponding to the monitoring index data;
performing data alignment on the monitoring index data of each blood monitoring index according to the time sequence data to obtain time sequence index data;
calling a plurality of preset index distribution functions to calculate the characteristic distribution value of the time sequence index data;
and respectively drawing a blood distribution curve corresponding to each blood monitoring index according to the characteristic distribution value.
4. The hemodialysis patient health monitoring apparatus of claim 1, wherein the hemodialysis patient health monitoring apparatus performs abnormal fluctuation analysis on the plurality of blood monitoring indexes according to a blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generates a corresponding blood status evaluation matrix of the clinical hemodialysis patient according to the abnormal monitoring index set, comprising:
respectively calculating a plurality of characteristic values in the blood distribution curve of each blood monitoring index, and acquiring a standard value of each blood monitoring index;
respectively comparing the plurality of characteristic values with the standard value to obtain a comparison result, and generating a characteristic abnormal value according to the comparison result;
inquiring a plurality of abnormal blood monitoring indexes corresponding to the characteristic abnormal values, and generating an abnormal monitoring index set according to the plurality of abnormal blood monitoring indexes;
and taking the characteristic abnormal value as a matrix element corresponding to the abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the matrix element.
5. The hemodialysis patient health monitoring device of claim 1, wherein the hemodialysis patient health monitoring device collects clinical video data of the clinical hemodialysis patient based on a preset clinical monitoring terminal, and performs behavior state analysis on the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient, and the behavior state evaluation coefficient comprises:
based on a preset clinical monitoring terminal, acquiring clinical video data of the clinical hemodialysis patient according to a preset video acquisition time period;
carrying out audio and image segmentation on the clinical video data to obtain audio data and image data;
generating an audio characteristic corresponding to the clinical hemodialysis patient according to the audio data, and generating a behavior characteristic corresponding to the clinical hemodialysis patient according to the image data;
and inputting the audio features and the behavior features into a preset behavior state analysis model for behavior state analysis to obtain a behavior state evaluation coefficient.
6. The hemodialysis patient health monitoring apparatus of claim 1, wherein the hemodialysis patient health monitoring apparatus inputs the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model for infection risk prediction, and outputs an infection risk prediction result, comprising:
performing matrix conversion on the blood state evaluation matrix according to the behavior state evaluation coefficient to obtain a target state matrix;
inputting the target state matrix into a preset blood infection risk prediction model, wherein the blood infection risk prediction model comprises a convolutional layer and a normalization function;
performing infection risk prediction on the target state matrix through the blood infection risk prediction model, and outputting an infection risk prediction probability, wherein the infection risk prediction probability is used for indicating the probability of infection of the clinical hemodialysis patient;
and generating an infection risk prediction result according to the infection risk prediction probability.
7. The hemodialysis patient health monitoring apparatus of any one of claims 1 to 6, wherein the hemodialysis patient health monitoring apparatus acquires physiological index data of the clinical hemodialysis patient and calculates an index change rate of the physiological index data;
judging whether the clinical hemodialysis patient meets preset physiological normal conditions or not according to the index change rate to obtain a judgment result;
and carrying out health monitoring on the clinical hemodialysis patient according to the judgment result and the infection risk prediction result.
8. A hemodialysis patient health monitoring system, comprising:
the system comprises an acquisition module, a data acquisition module and a data processing module, wherein the acquisition module is used for acquiring blood detection data of a clinical hemodialysis patient, and extracting index data of the blood detection data according to a plurality of preset blood monitoring indexes to obtain monitoring index data corresponding to each blood monitoring index;
the fitting module is used for calling a plurality of preset index distribution functions to respectively fit a blood distribution curve corresponding to each blood monitoring index according to the monitoring index data of each blood monitoring index;
the analysis module is used for carrying out abnormal fluctuation analysis on the plurality of blood monitoring indexes according to the blood distribution curve of each blood monitoring index to obtain an abnormal monitoring index set, and generating a blood state evaluation matrix corresponding to the clinical hemodialysis patient according to the abnormal monitoring index set;
the processing module is used for acquiring clinical video data of the clinical hemodialysis patient based on a preset clinical monitoring terminal, and analyzing the behavior state of the clinical hemodialysis patient according to the clinical video data to obtain a behavior state evaluation coefficient;
the prediction module is used for inputting the blood state evaluation matrix and the behavior state evaluation coefficient into a preset blood infection risk prediction model for infection risk prediction and outputting an infection risk prediction result;
and the monitoring module is used for generating health early warning information of the clinical hemodialysis patient according to the infection risk prediction result, generating a health analysis report according to the health early warning information, and sending the health analysis report to a preset nursing terminal for health monitoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211366302.1ACN115547500B (en) | 2022-11-03 | 2022-11-03 | Hemodialysis patient's health monitoring equipment and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211366302.1ACN115547500B (en) | 2022-11-03 | 2022-11-03 | Hemodialysis patient's health monitoring equipment and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115547500A CN115547500A (en) | 2022-12-30 |
| CN115547500Btrue CN115547500B (en) | 2023-03-24 |
Family
ID=84721195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211366302.1AActiveCN115547500B (en) | 2022-11-03 | 2022-11-03 | Hemodialysis patient's health monitoring equipment and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115547500B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117195139B (en)* | 2023-11-08 | 2024-02-09 | 北京珺安惠尔健康科技有限公司 | Chronic disease health data dynamic monitoring method based on machine learning |
| CN117830719B (en)* | 2023-12-29 | 2024-09-03 | 国医通（北京）科技发展有限公司 | Focus classifying device and method based on dialysis liquid image analysis |
| CN117912711B (en)* | 2024-03-19 | 2024-05-24 | 吉林大学 | Hemodialysis data acquisition and analysis system and method |
| CN118430732B (en)* | 2024-07-02 | 2024-09-10 | 深圳爱递医药科技有限公司 | Hemodialysis data intelligent processing system based on smart phone application program |
| CN118711821B (en)* | 2024-08-29 | 2024-10-29 | 长春中医药大学 | Blood index monitoring system for chronic disease patients |
| CN118797245B (en)* | 2024-09-12 | 2024-12-06 | 吉林大学 | On-line monitoring system and method for hemodialysis process of patient |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240002A (en)* | 2014-04-04 | 2014-12-24 | 博彦网鼎信息技术有限公司 | Hemodialysis management system and method |
| CN112384983A (en)* | 2018-06-29 | 2021-02-19 | 费森尤斯医疗保健控股公司 | System and method for identifying risk of infection in dialysis patient |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3092888A1 (en)* | 2018-04-12 | 2019-10-17 | Fresenius Medical Care Holdings, Inc. | Systems and methods for determining functionality of dialysis patients for assessing parameters and timing of palliative and/or hospice care |
| US20220068445A1 (en)* | 2020-08-31 | 2022-03-03 | Nec Laboratories America, Inc. | Robust forecasting system on irregular time series in dialysis medical records |
- 2022
- 2022-11-03CNCN202211366302.1Apatent/CN115547500B/enactiveActive
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240002A (en)* | 2014-04-04 | 2014-12-24 | 博彦网鼎信息技术有限公司 | Hemodialysis management system and method |
| CN112384983A (en)* | 2018-06-29 | 2021-02-19 | 费森尤斯医疗保健控股公司 | System and method for identifying risk of infection in dialysis patient |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115547500A (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115547500B (en) | Hemodialysis patient's health monitoring equipment and system | |
| US11538585B2 (en) | Detecting abnormalities in ECG signals | |
| CN106530295A (en) | Fundus image classification method and device of retinopathy | |
| CN113995419A (en) | A risk prediction system for atrial fibrillation based on heartbeat rhythm signal and its application | |
| CN111598868B (en) | Lung ultrasonic image identification method and system | |
| CN117334331B (en) | Medical diagnosis system for health condition based on artificial intelligence | |
| CN118486466B (en) | Intelligent robot management system and method applied to health monitoring | |
| CN115040093A (en) | Nursing intervention method and system for medical elderly patients | |
| CN112579808A (en) | Data annotation processing method, device and system | |
| CN118507075B (en) | A method and system for processing urological postoperative vital sign monitoring data | |
| CN115956903A (en) | Method for judging state abnormity of target object and storage medium | |
| CN114707608A (en) | Medical quality control data processing method, apparatus, device, medium, and program product | |
| US20030191732A1 (en) | Online learning method in a decision system | |
| CN119477856A (en) | General surgery incision image analysis method and system | |
| KR20230083966A (en) | Teeth condition analyzing method and system based on deep learning | |
| CN112614091A (en) | Ultrasonic multi-section data detection method for congenital heart disease | |
| CN117808786A (en) | Retinal artery branch angle change correlation prediction method | |
| CN115662595A (en) | User information management method and system based on online diagnosis and treatment system | |
| CN115100177A (en) | A tongue coating image analysis system based on image recognition | |
| CN114494299A (en) | temperature detection equipment | |
| CN119833125B (en) | Palm temperature monitor for TCM diagnosis | |
| CN119007412B (en) | A pig farm disease monitoring and early warning method and system based on machine learning | |
| CN119888789B (en) | Evaluation device and method for identifying ear status classification of people based on local features | |
| KR102595646B1 (en) | Tympanic disease prediction model system using deep neural network and monte carlo dropout | |
| CN119480121B (en) | A stroke emergency identification method and system combining TOPSIS and artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |