Disclosure of Invention
The application aims to provide an intelligent ward rehabilitation diagnosis method, system, equipment and readable storage medium, so as to solve the problems.
In order to achieve the above object, the embodiment of the present application provides the following technical solutions:
in one aspect, an embodiment of the present application provides a method for rehabilitation diagnosis of an intelligent ward, the method comprising:
acquiring first rehabilitation data of a historical patient and second rehabilitation data of a patient to be predicted, wherein the first rehabilitation data are the same as the types of data contained in the second rehabilitation data, the first rehabilitation data comprise physiological parameter information, movement condition information, medical history information, historical diagnosis information, rehabilitation training information and nursing record information, and the rehabilitation training information comprises rehabilitation success probability;
preprocessing the first rehabilitation data to obtain preprocessed first rehabilitation data;
training a plurality of prediction models by using the preprocessed first rehabilitation data to obtain a plurality of trained prediction models, and combining all the trained prediction models to obtain a combined model;
and inputting second rehabilitation data of the patient to be predicted into the combined model, and obtaining the rehabilitation success probability of the patient to be predicted according to the output of the combined model.
In a second aspect, embodiments of the present application provide an intelligent ward rehabilitation diagnostic system that includes an acquisition module, a processing module, a training module, and a prediction module.
The system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring first rehabilitation data of a historical patient and second rehabilitation data of a patient to be predicted, the first rehabilitation data are the same as the types of data contained in the second rehabilitation data, the first rehabilitation data comprise physiological parameter information, movement condition information, medical history information, historical diagnosis information, rehabilitation training information and nursing record information, and the rehabilitation training information comprises rehabilitation success probability;
the processing module is used for preprocessing the first rehabilitation data to obtain preprocessed first rehabilitation data;
the training module is used for training the plurality of prediction models by utilizing the preprocessed first rehabilitation data to obtain a plurality of trained prediction models, and combining all the trained prediction models to obtain a combined model;
the prediction module is used for inputting second rehabilitation data of the patient to be predicted into the combination model, and obtaining the probability of rehabilitation success of the patient to be predicted according to the output of the combination model.
In a third aspect, embodiments of the present application provide an intelligent ward rehabilitation diagnostic apparatus comprising a memory and a processor. The memory is used for storing a computer program; the processor is used for executing the computer program to realize the steps of the intelligent ward rehabilitation diagnosis method.
In a fourth aspect, embodiments of the present application provide a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above-described smart ward rehabilitation diagnostic method.
The beneficial effects of the application are as follows:
1. personalized rehabilitation scheme: the intelligent ward rehabilitation diagnosis system can obtain the probability of rehabilitation success according to the rehabilitation data of patients by utilizing big data analysis and a machine learning algorithm, and can generate personalized rehabilitation scheme and treatment recommendation according to the probability of rehabilitation success, thereby improving the rehabilitation effect and the satisfaction degree of the patients.
2. And (3) rehabilitation process management: the rehabilitation process usually requires long-time monitoring and management, and the intelligent ward rehabilitation diagnostic system provides real-time rehabilitation progress reports and adjustment suggestions by integrating and analyzing a large amount of patient rehabilitation data, monitoring physiological parameters, exercise conditions and the like of patients in real time. Medical staff can timely adjust the rehabilitation plan according to data and suggestions provided by the system, and the rehabilitation effect is improved.
3. Real-time monitoring and early warning: the intelligent ward rehabilitation diagnostic system can provide real-time early warning and alarm mechanisms by monitoring physiological parameters, movement conditions and rehabilitation progress of patients in real time. When the system detects that the rehabilitation progress of the patient is not ideal or abnormal conditions occur, the system can timely send a notification to medical staff so as to timely adjust the rehabilitation plan and prevent problems in the rehabilitation process.
4. Knowledge sharing and medical resource integration: the intelligent ward rehabilitation diagnosis system can integrate a large amount of medical data and knowledge resources, including clinical experience, expert knowledge, scientific research results and the like. Through data sharing and integration, the system can provide more comprehensive and accurate diagnosis and rehabilitation schemes for medical staff and promote optimal configuration and sharing of medical resources.
5. Reduce the burden of medical staff: the intelligent ward rehabilitation diagnosis system can automatically process a large amount of rehabilitation data and medical record information, and reduce the workload of medical staff. Medical staff can concentrate more on communicating with and paying attention to patients, and more humanized medical services are provided.
6. Continuous optimization and improvement: the intelligent ward rehabilitation diagnostic system can continuously collect patient rehabilitation data and user feedback for optimizing and improving models and recommendation algorithms. The performance and effect of the system may be improved over time.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that: like reference numerals or letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1
As shown in fig. 1, the present embodiment provides a smart ward rehabilitation diagnosis method, which includes step S1, step S2, step S3, and step S4.
Step S1, acquiring first rehabilitation data of a historical patient and second rehabilitation data of a patient to be predicted, wherein the first rehabilitation data are the same as the types of data contained in the second rehabilitation data, the first rehabilitation data comprise physiological parameter information, movement condition information, medical history information, historical diagnosis information, rehabilitation training information and nursing record information, and the rehabilitation training information comprises rehabilitation success probability;
in this step:
the physiological parameter information includes: such as heart rate, blood pressure, blood glucose, etc.
The movement condition information includes: such as walking distance, daily locomotion ability, etc.
The medical history information includes: such as fracture, hypertension, diabetes, etc.
The historical diagnostic information includes: conventional diagnostic results, advice, and the like.
The rehabilitation training information comprises: frequency, type, duration, etc. of rehabilitation, probability of success of rehabilitation, etc.
The care record information includes: such as taking medicine, rechecking time, special precautions, etc.
The second rehabilitation data can be understood to also include physiological parameter information, exercise condition information, medical history information, historical diagnosis information, rehabilitation training information and nursing record information;
in acquiring such data, the data of different data sources may be integrated, for example: a data interaction center system (DIC), a hospital integrated platform (ESB), an internet of things platform (IOT), an intelligent ward (SWP), to ensure data integrity and accuracy.
S2, preprocessing the first rehabilitation data to obtain preprocessed first rehabilitation data;
in the step, the data is also preprocessed before training, and the accuracy of the data is improved by preprocessing, so that the prediction accuracy of the model is improved, and the specific preprocessing method comprises the step S21;
step S21, preprocessing the first rehabilitation data, wherein preprocessing includes data structuring processing, data quality checking, missing value processing, outlier processing, data format conversion and standardization, data integration and deduplication, and the data quality checking includes checking whether missing values, outliers and duplicate values exist in the first rehabilitation data, and whether the data format is correct.
Besides the preprocessing method, the first rehabilitation data can be sent to the corresponding rehabilitation specialist in each field, and the first rehabilitation data are cooperated with the rehabilitation specialist to verify the data and ensure the rationality and the credibility of the data;
step S3, training a plurality of prediction models by using the preprocessed first rehabilitation data to obtain a plurality of trained prediction models, and combining all the trained prediction models to obtain a combined model;
the specific implementation steps of the step comprise a step S31 and a step S32;
step S31, dividing all the preprocessed first rehabilitation data into a training set and a verification set; respectively training a decision tree model, a support vector machine model and a neural network model by using the training set and the verification set to obtain a trained decision tree model, a trained support vector machine model and a trained neural network model;
in this step, a test set may be subdivided in addition to the training set and the validation set; meanwhile, the specific implementation steps of the step include step S311, step S312 and step S313;
step S311, training the decision tree model by utilizing the training set, selecting optimal dividing characteristics and decision nodes to obtain a preliminary decision tree model, pruning and parameter adjustment are carried out on the preliminary decision tree model by utilizing the verification set, and a trained decision tree model is obtained;
in this step, a decision tree algorithm (any of C4.5, ID3, CART) may be used to train the training set, and if a test set is still present, performance assessment of the model may be performed using the test set, for example, calculating indexes such as accuracy, recall, and F1 score of the model, to obtain a model performance assessment report, where the model performance assessment report includes performance of the model on each index, which helps to assess quality and applicability of the model, and provides decision support for ward doctors.
Step S312, training the support vector machine model by using the training set, searching optimal hyperplane or kernel function parameters by using a linear SVM or a kernel function SVM to obtain a preliminary support vector machine model, and performing parameter tuning on the preliminary support vector machine model by using the verification set to obtain a trained support vector machine model;
in the step, if the test set exists, performance evaluation can be performed on the model by using the test set, indexes such as accuracy, sensitivity, specificity and the like of the model are calculated, a model performance evaluation report is generated, and the report comprises the performance of the model on each index, so that the quality and the applicability of the model can be evaluated, and support is provided for medical decision.
Step S313, training the neural network model by using the training set, updating network parameters by using a back propagation algorithm to obtain a preliminary neural network model, and performing parameter tuning on the preliminary neural network model by using the verification set to obtain a trained neural network model;
in this step, if there is a test set, the test set may be used to evaluate the final performance of the neural network model, calculate the results of the model on various evaluation indexes, such as accuracy, recall, F1 score, and the like, generate a model performance evaluation report for evaluating the quality and applicability of the model, and provide support for rehabilitation diagnosis and recommendation.
And S32, combining the trained decision tree model, the trained support vector machine model and the trained neural network model to obtain a combined model.
In the step, three models are combined together in parallel to form a combined model;
and S4, inputting second rehabilitation data of the patient to be predicted into the combined model, and obtaining the probability of rehabilitation success of the patient to be predicted according to the output of the combined model.
In this step, after the second rehabilitation data of the patient to be predicted is input into the combined model, three probabilities of rehabilitation success are obtained, and after the three probabilities of rehabilitation success are obtained, the median value, the mean value or the maximum value thereof can be used as the probability of rehabilitation success of the patient to be predicted.
Besides the steps, the user can input the rehabilitation data of the user in real time to obtain the real-time rehabilitation success probability, and can also match different early warning information according to the real-time rehabilitation success probability, so that the purpose of monitoring the user in real time can be realized, and problems in the rehabilitation process are prevented.
Example 2
As shown in fig. 2, the present embodiment provides an intelligent ward rehabilitation diagnostic system, which includes an acquisition module 701, a processing module 702, a training module 703, and a prediction module 704.
An obtaining module 701, configured to obtain first rehabilitation data of a historical patient and second rehabilitation data of a patient to be predicted, where the first rehabilitation data is the same as the second rehabilitation data in the types of data, and the first rehabilitation data includes physiological parameter information, exercise condition information, medical history information, historical diagnosis information, rehabilitation training information and nursing record information, and the rehabilitation training information includes a rehabilitation success probability;
the processing module 702 is configured to pre-process the first rehabilitation data to obtain first rehabilitation data after the pre-processing;
the training module 703 is configured to train the plurality of prediction models by using the preprocessed first rehabilitation data to obtain a plurality of trained prediction models, and combine all the trained prediction models to obtain a combined model;
and the prediction module 704 is configured to input second rehabilitation data of the patient to be predicted into the combination model, and obtain a rehabilitation success probability of the patient to be predicted according to an output of the combination model.
In a specific embodiment of the disclosure, the processing module 702 further includes a processing unit 7021.
The processing unit 7021 is configured to perform preprocessing on the first rehabilitation data, where preprocessing includes data structuring processing, data quality checking, missing value processing, outlier processing, data format conversion and standardization, data integration and deduplication, and the data quality checking includes checking whether missing values, outliers and duplicate values exist in the first rehabilitation data, and whether a data format is correct.
In a specific embodiment of the disclosure, the training module 703 further includes a dividing unit 7031 and a combining unit 7032.
A dividing unit 7031 for dividing all the preprocessed first rehabilitation data into a training set and a verification set; respectively training a decision tree model, a support vector machine model and a neural network model by using the training set and the verification set to obtain a trained decision tree model, a trained support vector machine model and a trained neural network model;
the combining unit 7032 is configured to combine the trained decision tree model, the trained support vector machine model, and the trained neural network model to obtain a combined model.
In one specific embodiment of the disclosure, the dividing unit 7031 further includes a first training unit 70311, a second training unit 70312, and a third training unit 70313.
The first training unit 70311 is configured to train the decision tree model by using the training set, select an optimal division feature and a decision node to obtain a preliminary decision tree model, and perform pruning and parameter adjustment on the preliminary decision tree model by using the verification set to obtain a trained decision tree model;
the second training unit 70312 is configured to train the support vector machine model by using the training set, search for optimal hyperplane or kernel function parameters by using a linear SVM or a kernel function SVM to obtain a preliminary support vector machine model, and perform parameter tuning on the preliminary support vector machine model by using the verification set to obtain a trained support vector machine model;
and the third training unit 70313 is configured to train the neural network model by using the training set, update the network parameters through a back propagation algorithm to obtain a preliminary neural network model, and perform parameter tuning on the preliminary neural network model by using the verification set to obtain a trained neural network model.
It should be noted that, regarding the system in the above embodiment, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment regarding the method, and will not be described in detail herein.
Example 3
Corresponding to the above method embodiments, the disclosed embodiments also provide a smart ward rehabilitation diagnostic device, which is described below and to which the above described smart ward rehabilitation diagnostic method can be referred correspondingly.
Fig. 3 is a block diagram illustrating an intelligent ward rehabilitation diagnostic device 800, according to an exemplary embodiment. As shown in fig. 3, the smart ward rehabilitation diagnostic device 800 may include: a processor 801, a memory 802. The smart ward rehabilitation diagnostic device 800 may also include one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
Wherein the processor 801 is used to control the overall operation of the intelligent ward rehabilitation diagnostic apparatus 800 to perform all or part of the steps of the intelligent ward rehabilitation diagnostic method described above. The memory 802 is used to store various types of data to support the operation of the intelligent ward rehabilitation diagnostic device 800, which may include, for example, instructions for any application or method operating on the intelligent ward rehabilitation diagnostic device 800, as well as application-related data, such as contact data, messages, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the smart ward rehabilitation diagnostic device 800 and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G or 4G, or a combination of one or more thereof, the respective communication component 805 may thus comprise: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the intelligent ward rehabilitation diagnostic apparatus 800 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, abbreviated as ASIC), digital signal processors (DigitalSignal Processor, abbreviated as DSP), digital signal processing apparatus (Digital Signal Processing Device, abbreviated as DSPD), programmable logic devices (Programmable Logic Device, abbreviated as PLD), field programmable gate arrays (Field Programmable Gate Array, abbreviated as FPGA), controllers, microcontrollers, microprocessors, or other electronic components for performing the intelligent ward rehabilitation diagnostic method described above.
In another exemplary embodiment, a computer readable storage medium is also provided that includes program instructions that, when executed by a processor, implement the steps of the intelligent ward rehabilitation diagnostic method described above. For example, the computer readable storage medium may be the memory 802 including program instructions described above that are executable by the processor 801 of the intelligent ward rehabilitation diagnostic device 800 to perform the intelligent ward rehabilitation diagnostic method described above.
Example 4
Corresponding to the above method embodiments, the present disclosure further provides a readable storage medium, and a readable storage medium described below and an intelligent ward rehabilitation diagnosis method described above may be referred to correspondingly to each other.
A readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the intelligent ward rehabilitation diagnostic method of the above-described method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, and the like.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.