Method and device for generating single disease health management plan based on big data

Abstract

The present invention relates to a method and device for generating a single disease health management plan based on big data, wherein the method includes: extracting multi-dimensional data features from medical big data to obtain first feature information; constructing a medical behavior time series model based on the first feature information; extracting multi-dimensional data features from big data for health management task implementation to obtain second feature information; constructing a health management task time series model based on the second feature information; fitting the medical behavior time series model and the health management task time series model to obtain an optimized health management implementation time series model; inputting the patient's relevant information into the optimized health management implementation time series model to obtain a health management plan for the patient. The present invention can provide an optimized health management plan for chronic disease patients with different individual conditions in a more comprehensive and practical manner.

Description

Technical Field

[0001] The present invention relates to the field of medical big data application technology, and in particular to a method for generating a single disease health management plan based on big data. Background Art

[0002] Health management plans for single chronic diseases have always been a relatively mature means in the field of chronic disease treatment to prevent or slow down the occurrence of various serious illnesses caused by chronic diseases. The health management of chronic diseases is a series of tasks that are screened and combined according to the actual situation of the patient, and then implemented by the patient according to the task requirements. At present, pre-prepared health management plans are usually matched and implemented according to the patient's chronic disease progress. This method cannot effectively match the individual differences of patients and it is difficult to optimize the corresponding health management plan. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and device for generating a single disease health management plan based on big data, which can provide optimized health management plans for chronic disease patients with different individual conditions in a more comprehensive and actual manner.

[0004] The technical solution adopted by the present invention to solve the technical problem is: to provide a method for generating a single disease health management plan based on big data, comprising the following steps:

[0005] (1) extracting multi-dimensional data features from medical big data to obtain first feature information;

[0006] (2) constructing a medical behavior time series model based on the first characteristic information;

[0007] (3) extracting multi-dimensional data features from the big data of health management task implementation to obtain second feature information;

[0008] (4) constructing a health management task time series model based on the second feature information;

[0009] (5) fitting the medical behavior time series model and the health management task time series model to obtain an optimized health management implementation time series model;

[0010] (6) Inputting the patient's relevant information into the optimized health management implementation time series model to obtain a health management plan for the patient.

[0011] The first characteristic information in step (1) includes the patient's age, gender, disease diagnosis, medical treatment record, level of the institution performing the medical treatment, and medical expenses for performing the medical treatment.

[0012] The second characteristic information in step (3) includes the patient's age, gender, disease diagnosis, health management task implementation record, level of the institution proposing the health management task, patient compliance rating, and the cost of the patient implementing the health management task.

[0013] The step (5) is specifically as follows:

[0014] Summarize the correlation between medical behaviors and health management tasks in chronological order;

[0015] Taking the reduction of medical expenses and the number of medical behaviors as the evaluation objectives, the weights of health management tasks that have less impact on the relevance of medical behaviors are modified to generate an optimized health management implementation time series model of medical behaviors and weighted health management tasks.

[0016] The step (6) specifically comprises: using the gender, age, disease diagnosis of a single disease and medical behavior records in the patient-related information as the input of the optimized health management implementation time series model to obtain weighted health management tasks, and screening out the health management tasks according to a pre-established weight screening rule, and combining the screened health management tasks to obtain a health management plan for the patient.

[0017] The step between step (5) and step (6) also includes: using the gender, age, disease diagnosis of a single disease and medical behavior records in the patient-related information as input to the optimized health management implementation time series model to obtain weighted health management tasks, and performing consistency evaluation on the weighted health management tasks and the health management tasks in the patient's health management plan. When the consistency evaluation value is lower than the set threshold, step (6) is entered.

[0018] The technical solution adopted by the present invention to solve the technical problem is: a device for generating a single disease health management plan based on big data is also provided, comprising:

[0019] A first extraction module is used to extract multi-dimensional data features from the medical big data to obtain first feature information;

[0020] A first building module, used to build a medical behavior time series model based on the first characteristic information;

[0021] The second extraction module is used to extract multi-dimensional data features from the big data of the implementation of the health management task to obtain second feature information;

[0022] A second building module, used to build a health management task time series model based on the second feature information;

[0023] A fitting module, used to fit the medical behavior time series model and the health management task time series model to obtain an optimized health management implementation time series model;

[0024] A health management program generation module is used to input the patient's relevant information into the optimized health management implementation time series model to obtain a health management program for the patient.

[0025] The fitting module comprises:

[0026] The induction unit is used to summarize the correlation between medical behaviors and health management tasks in time sequence;

[0027] The fitting generation unit is used to reduce medical expenses and the number of medical behaviors as evaluation goals, correct the weights of health management tasks that have less impact on the relevance of medical behaviors, and generate an optimized health management implementation time series model for medical behaviors and weighted health management tasks.

[0028] The health management plan generation module is used to use the gender, age, disease diagnosis of a single disease and medical behavior records in the patient-related information as the input of the optimized health management implementation timing model, obtain health management tasks with weights, and filter out health management tasks according to pre-established weight filtering rules, and combine the filtered health management tasks to obtain a health management plan for the patient.

[0029] The device for generating a single disease health management plan based on big data also includes an effectiveness evaluation module, which is used to use the gender, age, disease diagnosis and medical behavior records of a single disease in the patient-related information as inputs to the optimized health management implementation timing model to obtain weighted health management tasks, and to perform consistency evaluation on the weighted health management tasks and the health management tasks in the patient's health management plan. When the consistency evaluation value is lower than a set threshold, the health management plan generation module is used to generate a health management plan for the patient.

[0030] Beneficial Effects

[0031] Due to the adoption of the above-mentioned technical scheme, the present invention has the following advantages and positive effects compared with the prior art: the present invention summarizes and analyzes the medical behavior timing model and the health management task timing model, takes the reduction of medical expenses and the number of medical treatments as evaluation indicators, and establishes a model combination of weighted health management task timing and medical behavior timing to obtain an optimized health management implementation timing model, thereby being able to provide optimized health management plans for chronic disease patients with different individual conditions in a more comprehensive and actual situation. The health management implementation timing model can also be used to evaluate the effectiveness of existing health management plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a flowchart of the first embodiment of the present invention. DETAILED DESCRIPTION

[0033] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the application equally.

[0034] The first embodiment of the present invention relates to a method for generating a single disease health management plan based on big data, such as Figure 1 As shown, the following steps are included:

[0035] Step 1: extract multi-dimensional data features from medical big data, specifically including step 1a, extracting the patient's gender, age, disease diagnosis and medical behavior records, where the medical behavior records include characteristic information directly related to medical behavior, such as medication type, medication dosage, treatment method, and consultation time; step 1b: extracting relevant characteristic information such as institution level and medical expenses related to step 1a.

[0036] Step 2, constructing a medical behavior time series model based on the first characteristic information, specifically: performing time series modeling on the medical behavior characteristic information through the dimensions of disease diagnosis of a single disease, patient gender and age group. For example, a logistic regression model can be established, and the established logistic regression model can be trained to obtain the corresponding medical behavior time series model.

[0037] Step 3, extracting multi-dimensional data features from the big data of health management task implementation, specifically including step 3a, extracting the patient's gender, age, disease diagnosis and health management task implementation records, where the health management task implementation records include health management tasks, implementation time and duration and other characteristic information related to health management implementation; step 3b, extracting relevant characteristic information related to step 3a, such as institution level, patient compliance rating, and cost.

[0038] Step 4, constructing a health management task time series model based on the second characteristic information, specifically: modeling the characteristic information of health management implementation through the dimensions of disease diagnosis of a single disease, patient gender and age group. For example, a logistic regression model can be established, and the established logistic regression model can be trained to obtain the corresponding health management task time series model.

[0039] Step 5, fitting the medical behavior time series model and the health management task time series model to obtain an optimized health management implementation time series model, specifically including step 5a, summarizing the correlation between medical behaviors and health management tasks in time series, and step 5b, taking reducing medical expenses and the number of medical behaviors as evaluation goals, correcting the weights of health management tasks that have less impact on the correlation of medical behaviors, and generating an optimized health management implementation time series model of medical behaviors and weighted health management tasks.

[0040] Step 6, evaluating the effectiveness of the existing health management plan, specifically including step 6a, matching the patient's single disease diagnosis, gender, age group and existing medical behavior records, that is, using the gender, age, single disease diagnosis and medical behavior records in the patient's relevant information as the input of the optimized health management implementation time series model to obtain a weighted health management task; step 6b, evaluating the consistency of the weighted health management task with the health management task in the patient's existing health management plan. When the consistency evaluation value is higher than or equal to the set threshold, it indicates that the effectiveness of the existing health management plan is high and there is no need to optimize the health management plan. When the consistency evaluation value is lower than the set threshold, it indicates that the effectiveness of the existing health management plan is low and it is necessary to proceed to the next step of optimizing the health management plan.

[0041] Step 7, automatically generating an optimized health management plan, specifically including step 7a, matching the patient's disease diagnosis of a single disease, the patient's gender, age group and existing medical behavior records, that is, using the patient's gender, age, disease diagnosis of a single disease and medical behavior records in the relevant information as the input of the optimized health management implementation timing model to obtain weighted health management tasks; step 7a, screening out health management tasks according to a pre-established weight screening rule, that is, traversing the obtained weights, selecting health management tasks corresponding to weights exceeding a preset value, and combining the screened health management tasks to obtain a health management plan for the patient.

[0042] A second embodiment of the present invention relates to a device for generating a single disease health management plan based on big data, comprising: a first extraction module, used to perform multi-dimensional data feature extraction on medical big data to obtain first feature information; a first construction module, used to construct a medical behavior time series model based on the first feature information; a second extraction module, used to perform multi-dimensional data feature extraction on big data for implementation of health management tasks to obtain second feature information; a second construction module, used to construct a health management task time series model based on the second feature information; a fitting module, used to fit the medical behavior time series model and the health management task time series model to obtain an optimized health management implementation time series model; a health management plan generation module, used to input relevant information of the patient into the optimized health management implementation time series model to obtain a health management plan for the patient.

[0043] The first characteristic information includes the patient's age, gender, disease diagnosis, medical behavior record, the level of the institution that performs the medical behavior, and the medical expenses for performing the medical behavior. The medical behavior record includes the type of medication, dosage, treatment method, consultation time and other characteristic information directly related to the medical behavior. The second characteristic information includes the patient's age, gender, disease diagnosis, health management task implementation record, the level of the institution that proposes the health management task, the patient's compliance rating and the cost of the patient's health management task implementation. The health management task implementation record includes the health management task, implementation time and duration and other characteristic information related to the implementation of health management.

[0044] The fitting module includes: an induction unit, which is used to summarize the correlation between medical behaviors and health management tasks in time series; a fitting generation unit, which is used to correct the weights of health management tasks that have a smaller impact on the correlation of medical behaviors with the evaluation goal of reducing medical expenses and the number of medical behaviors, and generate an optimized health management implementation time series model of medical behaviors and weighted health management tasks.

[0045] The health management plan generation module is used to use the gender, age, disease diagnosis of a single disease and medical behavior records in the patient-related information as the input of the optimized health management implementation timing model, obtain health management tasks with weights, and filter out health management tasks according to pre-established weight filtering rules, and combine the filtered health management tasks to obtain a health management plan for the patient.

[0046] The device for generating a single disease health management plan based on big data also includes an effectiveness evaluation module, which is used to use the gender, age, disease diagnosis and medical behavior records of a single disease in the patient-related information as inputs to the optimized health management implementation timing model to obtain weighted health management tasks, and to perform consistency evaluation on the weighted health management tasks and the health management tasks in the patient's health management plan. When the consistency evaluation value is lower than a set threshold, the health management plan generation module is used to generate a health management plan for the patient.

[0047] It is not difficult to find that the present invention, through the inductive analysis of the medical behavior timing model and the health management task timing model, takes the reduction of medical expenses and the number of medical treatments as evaluation indicators, establishes a model combination of weighted health management task timing and medical behavior timing to obtain an optimized health management implementation timing model, thereby being able to provide optimized health management plans for chronic disease patients with different individual conditions in a more comprehensive and actual situation. The health management implementation timing model can also be used to evaluate the effectiveness of existing health management plans.

Claims

1. A method for generating a single disease health management plan based on big data, characterized in that: The following steps are involved: (1) extracting multi-dimensional data features from medical big data to obtain first feature information; (2) constructing a medical behavior time series model based on the first characteristic information; (3) extracting multi-dimensional data features from the big data of health management task implementation to obtain second feature information; (4) constructing a health management task time series model based on the second feature information; (5) Fitting the medical behavior time series model and the health management task time series model to obtain an optimized health management implementation time series model, specifically: Summarize the correlation between medical behaviors and health management tasks in chronological order; Taking the reduction of medical expenses and the number of medical behaviors as the evaluation goal, the weights of health management tasks with less impact on the relevance of medical behaviors are modified to generate an optimized health management implementation time series model of medical behaviors and weighted health management tasks; (6) Inputting the patient's relevant information into the optimized health management implementation time series model to obtain a health management plan for the patient.

2. The method for generating a single disease health management plan based on big data according to claim 1, characterized in that: The first characteristic information in step (1) includes the patient's age, gender, disease diagnosis, medical treatment record, level of the institution performing the medical treatment, and medical expenses for performing the medical treatment.

3. The method for generating a single disease health management plan based on big data according to claim 1 is characterized in that: The second characteristic information in step (3) includes the patient's age, gender, disease diagnosis, health management task implementation record, level of the institution proposing the health management task, patient compliance rating, and the cost of implementing the health management task for the patient.

4. The method for generating a single disease health management plan based on big data according to claim 1, characterized in that: The step (6) specifically comprises: using the gender, age, disease diagnosis of a single disease and medical behavior records in the patient-related information as the input of the optimized health management implementation time series model to obtain weighted health management tasks, and screening out the health management tasks according to a pre-established weight screening rule, and combining the screened health management tasks to obtain a health management plan for the patient.

5. The method for generating a single disease health management plan based on big data according to claim 1 is characterized in that: The step between step (5) and step (6) also includes: using the gender, age, disease diagnosis of a single disease and medical behavior records in the patient-related information as input to the optimized health management implementation time series model to obtain weighted health management tasks, and performing consistency evaluation on the weighted health management tasks and the health management tasks in the patient's health management plan. When the consistency evaluation value is lower than the set threshold, step (6) is entered.

6. A device for generating a single disease health management plan based on big data, characterized in that: include: A first extraction module is used to extract multi-dimensional data features from the medical big data to obtain first feature information; A first building module, used to build a medical behavior time series model based on the first characteristic information; The second extraction module is used to extract multi-dimensional data features from the big data of the implementation of the health management task to obtain second feature information; A second building module, used to build a health management task time series model based on the second feature information; A fitting module is used to fit the medical behavior time series model and the health management task time series model to obtain an optimized health management implementation time series model; the fitting module includes: The induction unit is used to summarize the correlation between medical behaviors and health management tasks in time sequence; The fitting generation unit is used to reduce medical expenses and the number of medical behaviors as evaluation goals, modify the weights of health management tasks that have little impact on the relevance of medical behaviors, and generate an optimized health management implementation time series model for medical behaviors and weighted health management tasks. The health management program generation module is used to input the patient's relevant information into the optimized health management implementation timing model to obtain a health management program for the patient.

7. The device for generating a single disease health management plan based on big data according to claim 6, characterized in that: The health management plan generation module is used to use the gender, age, disease diagnosis of a single disease and medical behavior records in the patient-related information as the input of the optimized health management implementation timing model, obtain health management tasks with weights, and filter out health management tasks according to pre-established weight filtering rules, and combine the filtered health management tasks to obtain a health management plan for the patient.

8. The device for generating a single disease health management plan based on big data according to claim 6, characterized in that: It also includes an effectiveness evaluation module, which is used to use the gender, age, disease diagnosis of a single disease and medical behavior records in the patient-related information as input of the optimized health management implementation timing model to obtain weighted health management tasks, and conduct consistency evaluation on the weighted health management tasks and the health management tasks in the patient's health management plan. When the consistency evaluation value is lower than the set threshold, the health management plan generation module is used to generate a health management plan for the patient.

Images