Chronic disease analysis method and system
By calculating the correlation number and population clustering of human sign data, periodic treatment plans are generated, which solves the problem of low informatization of chronic disease management, improves management efficiency and personalization of treatment plans, and reduces the work intensity of medical staff.
Patent Information
- Application Number
- CN202210386033.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-13
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2042-04-13
AI Technical Summary
In the prior art, chronic disease management mainly relies on medical staff, and the degree of informatization is low, resulting in high work intensity of medical staff and difficulty in effectively managing chronic diseases in the elderly.
By obtaining human sign data and health record data, calculating the correlation number of sign data, clustering people, and inputting the results into the decision support model based on artificial neural networks to generate periodic treatment plans, improving the degree of informatization and reducing the medical staff's Work intensity.
It has achieved the improvement of informatization of chronic disease management, reduced the work intensity of medical staff, and improved the personalization and accuracy of cluster analysis and treatment plans for chronic disease and complication risks.
Smart Images

Figure CN114694852B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of chronic disease treatment, and in particular to a chronic disease analysis method and system. Background Art
[0002] Coping with population aging is a topic of common concern around the world and a practical problem facing China. China has become the country with the largest elderly population in the world. As of 2017, the population aged 65 and above accounted for 11.4%. The prevalence of chronic diseases among the elderly is very high, while my country's primary medical resources, especially the number of general practitioners and family doctors, are insufficient, and the per capita medical care is relatively low, resulting in great pressure in the diagnosis, treatment and management of chronic diseases for the elderly.
[0003] At present, the management of chronic diseases for the elderly still mainly relies on medical staff. The degree of informatization is low, resulting in a very low labor efficiency ratio of medical staff. It is difficult to significantly increase the data of medical staff in the short term, resulting in limited coverage of chronic disease management for the elderly and high workload for medical staff. Summary of the invention
[0004] The present invention provides a chronic disease analysis method and system, thereby solving the technical problem that the management of chronic diseases in the prior art mainly relies on medical staff and has a low level of informatization, thereby achieving the technical effect of improving the level of informatization of chronic disease management and reducing the workload of medical staff.
[0005] The present invention provides a chronic disease analysis method, comprising:
[0006] Obtain each person's physical sign data;
[0007] By formula The correlation coefficient between the current human body sign data and the historical human body sign data is calculated; where t j represents the current moment, n represents the number of types of human vital signs data obtained, TP i Indicates the current human body data, HP i Indicates the physical sign values in the same historical period;
[0008] By formula H = Level BMI *W BMI +Level BP *W BP +Level BS *W BS The overall correlation coefficient of the physical sign data was calculated; among them, Level BMI 、Level BP and Level BS They represent the correlation coefficients of BMI, blood pressure and blood sugar, respectively, and WBMI , W BP and W BS represent the corresponding weights of BMI, blood pressure, and blood sugar respectively;
[0009] Access to health record data;
[0010] Clustering the population according to the health record data to obtain classification results;
[0011] The overall correlation coefficient of the physical sign data and the classification result are input into a trained decision support model based on an artificial neural network, and a periodic treatment plan is output.
[0012] Specifically, clustering the population according to the health record data to obtain classification results includes:
[0013] Step 1: Randomly select K points as the initial center points of K clusters;
[0014] Step 2: assigning each population sample to the cluster closest to the initial center point; wherein the population sample at least includes the health record dimension data, past history dimension data and compliance dimension data;
[0015] Step 3: Update the center point position of each cluster to obtain the classification results of each population;
[0016] Step 4: If the preset termination condition is met, terminate the clustering, otherwise return to step 2.
[0017] Specifically, the preset termination condition is that the change in the position of each cluster center point is less than or equal to a set change threshold.
[0018] Specifically, the overall correlation coefficient of the physical sign data and the classification result are input into a trained decision support model based on an artificial neural network to output a periodic treatment plan, including:
[0019] The overall correlation coefficient of the physical sign data, the classification results, demographic data, clinical data, laboratory data, and genetic data are input into the decision support model based on the artificial neural network, and a group of contents are automatically extracted from the preset treatment plan database for periodic display.
[0020] Specifically, the preset treatment plan database includes: disease clinical pathway information, pharmaceutical service content, diagnosis and treatment guidelines, patient education content, and medical resource information.
[0021] The present invention also provides a chronic disease analysis system, comprising:
[0022] A human body sign data acquisition module is used to acquire each person's human body sign data;
[0023] The module for calculating the correlation coefficient of single human body sign data is used to calculate the correlation coefficient of single human body sign data through the formula The correlation coefficient between the current human body sign data and the historical human body sign data is calculated; where t j represents the current moment, n represents the number of types of human vital signs data obtained, TP i Indicates the current human body data, HP i Indicates the physical sign values in the same historical period;
[0024] The overall human body sign data correlation coefficient calculation module is used to calculate the correlation coefficient of the human body sign data through the formula H = Level BMI *W BMI +Level BP *W BP +Level BS *W BS The overall correlation coefficient of the physical sign data was calculated; among them, Level BMI 、Level BP and Level BS They represent the correlation coefficients of BMI, blood pressure and blood sugar, respectively, and W BMI , W BP and W BS represent the corresponding weights of BMI, blood pressure, and blood sugar respectively;
[0025] A health record data acquisition module is used to acquire health record data;
[0026] A crowd classification module is used to cluster the crowd according to the health record data to obtain classification results;
[0027] The treatment plan output module is used to input the overall correlation coefficient of the physical sign data and the classification result into a trained decision support model based on an artificial neural network, and output a periodic treatment plan.
[0028] Specifically, the crowd classification module includes:
[0029] An initial center point selection unit is used to randomly select K points as the initial center points of K clusters;
[0030] A clustering execution unit, used to assign each population sample to the cluster closest to the initial center point; wherein the population sample at least includes the health record dimension data, past history dimension data and compliance dimension data;
[0031] The clustering update unit is used to update the center point position of each cluster to obtain the classification result of each population; if the preset termination condition is met, the clustering is terminated.
[0032] Specifically, the preset termination condition is that the change in the position of each cluster center point is less than or equal to a set change threshold.
[0033] Specifically, the treatment plan output module is used to input the overall correlation coefficient of the physical sign data, the classification results, demographic data, clinical data, laboratory data, and genetic data into the decision support model based on the artificial neural network, and automatically extract a group of content from the preset treatment plan database for periodic display.
[0034] Specifically, the preset treatment plan database includes: disease clinical pathway information, pharmaceutical service content, diagnosis and treatment guidelines, patient education content, and medical resource information.
[0035] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:
[0036] Obtain each person's vital signs data and health record data, and then use the formula to calculate the correlation coefficient between each current human vital signs data and the historical human vital signs data; then calculate the overall correlation coefficient of the vital signs data; then cluster the population according to the health record data to obtain the classification results, and then perform cluster analysis on the user's chronic disease and complication risks; finally, input the overall correlation coefficient of the vital signs data and the classification results into the trained decision support model based on artificial neural network, and output a periodic treatment plan, achieving the technical effect of improving the level of informatization of chronic disease management and reducing the workload of medical staff. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 A flowchart of a chronic disease analysis method provided by an embodiment of the present invention;
[0038] Figure 2 A module diagram of a chronic disease analysis system provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0039] The embodiments of the present invention provide a chronic disease analysis method and system, thereby solving the technical problem that the management of chronic diseases in the prior art mainly relies on medical staff and has a low level of informatization, thereby achieving the technical effect of improving the level of informatization of chronic disease management and reducing the workload of medical staff.
[0040] The technical solution in the embodiment of the present invention is to solve the above problems, and the overall idea is as follows:
[0041] Obtain each person's vital signs data and health record data, and then use the formula to calculate the correlation coefficient between each current human vital signs data and the historical human vital signs data; then calculate the overall correlation coefficient of the vital signs data; then cluster the population according to the health record data to obtain the classification results, and then perform cluster analysis on the user's chronic disease and complication risks; finally, input the overall correlation coefficient of the vital signs data and the classification results into the trained decision support model based on artificial neural network, and output a periodic treatment plan, achieving the technical effect of improving the level of informatization of chronic disease management and reducing the workload of medical staff.
[0042] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0043] See also Figure 1 , the chronic disease analysis method provided by the embodiment of the present invention includes:
[0044] Step S110: Acquire each person's physical sign data;
[0045] In this embodiment, the acquired physical sign data of each person include: blood pressure, blood sugar, blood lipids and other data.
[0046] Step S120: By formula The correlation coefficient between the current human body sign data and the historical human body sign data is calculated; where t j represents the current moment, n represents the number of types of human vital signs data obtained. For example, the current system can obtain three human vital signs: blood pressure, blood sugar, and BMI, then n = 3, TP i Indicates the current human body data, HP i Indicates the physical sign values in the same historical period;
[0047] Step S130: Use the formula H = Level BMI *W BMI +Level BP *W BP +Level BS *W BS The overall correlation coefficient of the physical sign data was calculated; among them, Level BMI 、Level BP and Level BS They represent the correlation coefficients of BMI, blood pressure and blood sugar, respectively, and W BMI , W BP and W BS represent the corresponding weights of BMI, blood pressure, and blood sugar respectively;
[0048] Step S140: Obtain health record data;
[0049] Step S150: clustering the population according to the health record data to obtain classification results;
[0050] This step is explained in detail. The population is clustered according to the health record data to obtain the classification results, including:
[0051] Step 1: Randomly select K points as the initial center points of K clusters;
[0052] Specifically, the population is divided into six categories: high-risk population for chronic diseases, low-risk population for chronic diseases, high-risk population for early complications of chronic diseases, low-risk population for early complications of chronic diseases, high-risk population for cardiovascular and cerebrovascular accidents caused by chronic diseases, and low-risk population for cardiovascular and cerebrovascular accidents caused by chronic diseases. Therefore, in this embodiment, K=6.
[0053] Step 2: Assign each population sample to the cluster closest to the initial center point; wherein the population sample includes at least health record dimension data, past history dimension data and compliance dimension data; in this embodiment, the health record dimension data include: BMI, whether smoking, drinking, exercise frequency, etc., the past history dimension data include: whether the three highs have been diagnosed in the past, family genetic history, diagnosis of diseases related to the three highs, etc., and the compliance dimension data include: follow-up compliance, medication compliance, etc.
[0054] It should be noted here that after extracting the user's three-dimensional feature information, the preliminary proportional relationship of the three-dimensional weights is preliminarily determined, the features are compared pairwise to obtain the corresponding evaluation matrix, and corresponding adjustments are made to make it pass the consistency test. The weights of the three-dimensional features are obtained using the hierarchical analysis method.
[0055] Step 3: Update the center point position of each cluster to obtain the classification results of each population;
[0056] Step 4: If the preset termination condition is met, terminate the clustering, otherwise return to step 2.
[0057] In this embodiment, the preset termination condition is that the change in the position of each cluster center point is less than or equal to a set change threshold, that is, the position of each cluster center point hardly changes.
[0058] It should be noted here that the acquisition of each person's vital signs data and health record data does not distinguish between orders, and can be obtained at the same time.
[0059] Step S160: input the overall correlation coefficient of the physical sign data and the classification result into the trained decision support model based on the artificial neural network, and output a periodic treatment plan.
[0060] This step is specifically described. The overall correlation coefficient and classification results of the physical sign data are input into the trained decision support model based on artificial neural network, and a periodic treatment plan is output, including:
[0061] The overall correlation coefficient of physical sign data, classification results, demographic data, clinical data, laboratory data, and genetic data are input into the decision support model based on artificial neural network, and a group of contents are automatically extracted from the preset treatment plan database for periodic display.
[0062] Specifically, the preset treatment plan database includes: disease clinical pathway information, pharmaceutical service content, diagnosis and treatment guidelines, patient education content, and medical resource information.
[0063] To further explain this step, the input layer includes multiple input variables such as demographic data, clinical data, laboratory data, genetics and other data, especially including the risk association coefficient of the current physical sign value and the historical characteristic value of the same period in the above step and the risk prediction classification results of chronic diseases and complications, so that the intervention plan can be more accurate, comprehensive and personalized. By grouping and encoding these variables, the nodes in the hidden layer are determined through a cascade learning process. Each node contained in the output layer corresponds to an intervention or treatment plan. The system can automatically extract a group of content from the preset intervention or treatment plan database according to the intervention or treatment plan for periodic and regular display.
[0064] The preset treatment plan database is a rule-based knowledge base system. The knowledge base contains standardized content of the guideline type, and can also be edited to improve innovative professional knowledge content. For example, the knowledge base related to pharmaceutical services can be compiled and improved by medical experts according to content classification, archived and stored according to categories, and one or a group of contents will be sent to the user for each intervention. A brief description of each content category is as follows:
[0065] Dosage and Usage: Provide general usage for each drug, including the number of times a day it is taken, the dosage for each dose, contraindications for general use, and how to adjust the drug in special circumstances.
[0066] Drug knowledge: explain the types of drugs, main ingredients, efficacy, etc., especially the applicable precautions, common adverse reactions and treatment methods.
[0067] Disease Knowledge: Explains the definition of the disease, its causes and predisposing factors, and provides lifestyle recommendations based on the most common causes and predisposing factors.
[0068] Medication compliance: Emphasize the importance of taking medication as directed and remind patients to take medication from the perspective of patient education
[0069] Repurchase reminder: When the patient's purchased medicine is about to be taken out or has been taken out but no drug purchase behavior is detected according to the correct usage and dosage, a repurchase reminder is triggered to remind the patient to purchase supplementary medicine and continue to take the medicine as prescribed by the doctor.
[0070] Hazards of complications: List common complications and their risks to help patients have a deeper understanding of the harmfulness of the disease.
[0071] Effect evaluation: After the patient has been taking medication and undergoing indicator testing for more than one month, an effect evaluation will be conducted based on the trend of the test results, allowing the patient to have an intuitive understanding of the disease control effect.
[0072] Contraindications: Special reminders on contraindications for special groups of people and special drugs.
[0073] Test reminder: For indicators such as blood pressure and blood sugar that require long-term testing, if the patient has not uploaded the test records for a period of time, a test reminder will be issued to the patient.
[0074] The final result is to present a set of intervention plans to the user within a cycle. The period, frequency and content of the intervention plan reaching the user are determined by the results of the above-mentioned decision support model based on artificial neural network.
[0075] An example of a patient receiving 9 intervention reminders throughout the cycle is as follows:
[0076]
[0077] See also Figure 2 , the chronic disease analysis system provided by the embodiment of the present invention includes:
[0078] A human body sign data acquisition module 100 is used to acquire each human body sign data;
[0079] It should be noted here that this system includes a data acquisition module that comprehensively aggregates a variety of heterogeneous user information, including:
[0080] (1) Basic information manually filled in by the user: age, gender, height, weight, income, current medical history, past medical history, family history, etc.
[0081] (2) Physical sign test data: including blood pressure, blood sugar, blood lipids, weight, etc. Data sources include manual reporting by users, automatic upload by home testing equipment, and data synchronization by hospitals or physical examination institutions.
[0082] (3) Drug purchase data: The drug purchase data is captured from the drug store ERP's automatic synchronization data and the drug purchase data manually reported by the user. The drug purchase data can be used to infer the user's medication compliance based on the drug's usage and dosage knowledge, purchase frequency, and quantity.
[0083] (4) Medical data: mainly obtained synchronously from the hospital HIS system, and can also be combined with records manually filled in by users.
[0084] After crawling the data, the data is normalized and cleaned. For example, based on the characteristics of drug purchase records, the drug purchase information of each member is integrated on a daily basis, and the drug purchase information on the same day is integrated as a single drug purchase information; members with drug return records are deleted; records with very small single drug purchase amounts are deleted; if data sources from multiple channels are found to have data duplication problems, the duplicate records are removed and only one record is retained.
[0085] The single human body sign data correlation coefficient calculation module 200 is used to calculate the correlation coefficient of the single human body sign data by the formula The correlation coefficient between the current human body sign data and the historical human body sign data is calculated; where t j represents the current moment, n represents the number of types of human vital signs data obtained. For example, the current system can obtain three human vital signs: blood pressure, blood sugar, and BMI, then n = 3, TP i Indicates the current human body data, HP i Indicates the physical sign values in the same historical period;
[0086] The overall human body sign data correlation coefficient calculation module 300 is used to calculate the correlation coefficient of the human body sign data by the formula H = Level BMI *W BMI +Level BP *W BP +Level BS *W BS The overall correlation coefficient of the physical sign data was calculated; among them, Level BMI 、Level BP and Level BS They represent the correlation coefficients of BMI, blood pressure and blood sugar, respectively, and W BMI , W BP and W BS represent the corresponding weights of BMI, blood pressure, and blood sugar respectively;
[0087] The health record data acquisition module 400 is used to acquire health record data;
[0088] The crowd classification module 500 is used to cluster the crowd according to the health record data to obtain the classification result;
[0089] Specifically, the crowd classification module 500 includes:
[0090] The initial center point selection unit is used to randomly select K points as the initial center points of K clusters; specifically, the population is divided into six categories: high-risk population for chronic diseases, low-risk population for chronic diseases, high-risk population for early complications of chronic diseases, low-risk population for early complications of chronic diseases, high-risk population for cardiovascular and cerebrovascular accidents caused by chronic diseases, and low-risk population for cardiovascular and cerebrovascular accidents caused by chronic diseases. Therefore, in this embodiment, K=6.
[0091] A clustering execution unit is used to assign each population sample to the cluster that is closest to the initial center point; wherein the population sample includes at least health record dimension data, past history dimension data and compliance dimension data; in this embodiment, the health record dimension data include: BMI, whether smoking, drinking, exercise frequency, etc., the past history dimension data include: whether the three highs have been diagnosed in the past, family genetic history, diagnosis of diseases related to the three highs, etc., and the compliance dimension data include: follow-up compliance, medication compliance, etc.
[0092] It should be noted here that after extracting the user's three-dimensional feature information, the preliminary proportional relationship of the three-dimensional weights is preliminarily determined, the features are compared pairwise to obtain the corresponding evaluation matrix, and corresponding adjustments are made to make it pass the consistency test. The weights of the three-dimensional features are obtained using the hierarchical analysis method.
[0093] The clustering update unit is used to update the center point position of each cluster to obtain the classification result of each population; if the preset termination condition is met, the clustering is terminated.
[0094] In this embodiment, the preset termination condition is that the change in the position of each cluster center point is less than or equal to a set change threshold, that is, the position of each cluster center point hardly changes.
[0095] It should be noted here that the acquisition of each person's vital signs data and health record data does not distinguish between orders, and can be obtained at the same time.
[0096] The treatment plan output module 600 is used to input the overall correlation coefficient of the physical sign data and the classification result into the trained decision support model based on the artificial neural network, and output a periodic treatment plan.
[0097] Specifically, the treatment plan output module 600 is specifically used to input the overall correlation coefficient of physical sign data, classification results, demographic data, clinical data, laboratory data, and genetic data into a decision support model based on an artificial neural network, and automatically extract a group of content from a preset treatment plan database for periodic display.
[0098] In this embodiment, the preset treatment plan database includes: disease clinical pathway information, pharmaceutical service content, diagnosis and treatment guidelines, patient education content, and medical resource information.
[0099] Technical Effects
[0100] Obtain each person's vital signs data and health record data, and then use the formula to calculate the correlation coefficient between each current human vital signs data and the historical human vital signs data; then calculate the overall correlation coefficient of the vital signs data; then cluster the population according to the health record data to obtain the classification results, and then perform cluster analysis on the user's chronic disease and complication risks; finally, input the overall correlation coefficient of the vital signs data and the classification results into the trained decision support model based on artificial neural network, and output a periodic treatment plan, achieving the technical effect of improving the level of informatization of chronic disease management and reducing the workload of medical staff.
[0101] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0102] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0103] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0105] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0106] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A method for analyzing chronic diseases, characterized in that: include: Obtain each person's physical sign data; By formula The correlation coefficient between the current human body sign data and the historical human body sign data is calculated; where t j represents the current moment, n represents the number of types of human vital signs data obtained, TP i Indicates the current human body data, HP i Indicates the physical sign values in the same historical period; Through the formula H = Level BMI *W BMI +Level BP *W BP +Level BS *W BS The overall correlation coefficient of the physical sign data was calculated; among them, Level BMI 、Level BP and Level BS They represent the correlation coefficients of BMI, blood pressure and blood sugar, respectively, and W BMI , W BP and W BS represent the corresponding weights of BMI, blood pressure, and blood sugar respectively; Access to health record data; Clustering the population according to the health record data to obtain classification results; Inputting the overall correlation coefficient of the physical sign data and the classification result into a trained decision support model based on an artificial neural network, and outputting a periodic treatment plan; The step of inputting the overall correlation coefficient of the physical sign data and the classification result into a trained decision support model based on an artificial neural network and outputting a periodic treatment plan comprises: The overall correlation coefficient of the physical sign data, the classification results, demographic data, clinical data, laboratory data, and genetic data are input into the decision support model based on the artificial neural network, and a group of contents are automatically extracted from the preset treatment plan database for periodic display.
2. The method according to claim 1, characterized in that The clustering of the population according to the health record data to obtain the classification results includes: Step 1: Randomly select K points as the initial center points of K clusters; Step 2: assigning each population sample to the cluster closest to the initial center point; wherein the population sample at least includes health record dimension data, past history dimension data and compliance dimension data; Step 3: Update the center point position of each cluster to obtain the classification results of each population; Step 4: If the preset termination condition is met, terminate the clustering, otherwise return to step 2.
3. The method according to claim 2, characterized in that The preset termination condition is that the change in the position of each cluster center point is less than or equal to a set change threshold.
4. The method according to claim 1, characterized in that The preset treatment plan database includes: disease clinical pathway information, pharmaceutical service content, diagnosis and treatment guidelines, patient education content, and medical resource information.
5. A chronic disease analysis system, characterized in that: include: A human body sign data acquisition module is used to acquire each person's human body sign data; The module for calculating the correlation coefficient of single human body sign data is used to calculate the correlation coefficient of single human body sign data through the formula The correlation coefficient between the current human body sign data and the historical human body sign data is calculated; where t j represents the current moment, n represents the number of types of human vital signs data obtained, TP i Indicates the current human body data, HP i Indicates the physical sign values in the same historical period; The overall human body sign data correlation coefficient calculation module is used to calculate the correlation coefficient of the human body sign data through the formula H = Level BMI *W BMI +Level BP *W BP +Level BS *W BS The overall correlation coefficient of the physical sign data was calculated; among them, Level BMI 、Level BP and Level BS They represent the correlation coefficients of BMI, blood pressure and blood sugar, respectively, and W BMI , W BP and W BS represent the corresponding weights of BMI, blood pressure, and blood sugar respectively; A health record data acquisition module is used to acquire health record data; A crowd classification module is used to cluster the crowd according to the health record data to obtain classification results; A treatment plan output module, used for inputting the overall correlation coefficient of the physical sign data and the classification result into a trained decision support model based on an artificial neural network, and outputting a periodic treatment plan; The treatment plan output module is specifically used to input the overall correlation coefficient of the physical sign data, the classification results, demographic data, clinical data, laboratory data, and genetic data into the decision support model based on the artificial neural network, and automatically extract a group of content from the preset treatment plan database for periodic display.
6. The system according to claim 5, characterized in that The crowd classification module comprises: An initial center point selection unit is used to randomly select K points as the initial center points of K clusters; A clustering execution unit, used to assign each population sample to a cluster that is closest to the initial center point; wherein the population sample at least includes health record dimension data, past history dimension data and compliance dimension data; The clustering update unit is used to update the center point position of each cluster to obtain the classification result of each population; if the preset termination condition is met, the clustering is terminated.
7. The system according to claim 6, characterized in that The preset termination condition is that the change in the position of each cluster center point is less than or equal to a set change threshold.
8. The system according to claim 5, characterized in that The preset treatment plan database includes: disease clinical pathway information, pharmaceutical service content, diagnosis and treatment guidelines, patient education content, and medical resource information.
