Customized health management method for patient with cardiovascular and cerebrovascular chronic disease based on big data AI model

Abstract

The invention belongs to the technical field of medical health management, and particularly relates to a personalized health management method for a cardiovascular and cerebrovascular chronic disease patient based on a big data AI model, and the method comprises the steps: obtaining and preprocessing the multi-source disease data of the cardiovascular and cerebrovascular chronic disease patient; then constructing a big data AI model and a knowledge base in the field of cardiovascular and cerebrovascular diseases, inputting data in the knowledge base into the big data AI model for training and verification, inputting multi-source disease data into the trained big data AI model, and outputting risk factors and illness state data; an AI-driven health risk assessment model is constructed based on a big data AI model, risk factors and illness state data of a cardiac patient are input into the health risk assessment model, acquired index change data are compared with a preset index change threshold, and a personalized health management plan including prescriptions is generated according to a comparison result. And transmitting to the mobile terminal. According to the invention, a patient personalized health management technical scheme can be constructed and generated.

Description

Technical Field

[0001] The present invention belongs to the field of medical health management technology, and in particular relates to a personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on a big data AI model. Background Art

[0002] Currently, cardiovascular and cerebrovascular diseases (CVDs) are one of the leading causes of death worldwide. According to the World Health Organization, more than 17 million people die from such diseases each year, accounting for nearly one-third of the total global death toll. Especially in the context of an aging society, the morbidity and mortality of cardiovascular and cerebrovascular diseases continue to rise, becoming one of the major challenges facing the public health field.

[0003] The traditional chronic disease management model mainly relies on the experience of doctors and the self-management of patients. This approach has many shortcomings, including:

[0004] 1. Lack of systematic management. Traditional management models often focus on acute treatment and ignore long-term follow-up and management, especially the lack of sustained intervention for chronic diseases;

[0005] 2. Lack of personalized intervention. Doctors usually develop treatment plans based on their own experience and clinical guidelines, but this method is difficult to take into account the individual differences of each patient;

[0006] 3. Patient compliance is poor, patients’ self-management abilities vary, and there is often a lack of effective support and supervision mechanisms, leading to poor implementation of treatment plans;

[0007] 4. Limitations in primary medical services. Due to limited resources, primary medical institutions face challenges in providing high-quality cardiovascular and cerebrovascular disease prevention, rehabilitation and long-term follow-up services. Summary of the invention

[0008] The technical problem solved by the present invention is to provide a personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on a big data AI model, so as to construct a technical solution for generating personalized health management for patients.

[0009] The basic solution provided by the present invention: a personalized health management method for patients with chronic cardiovascular and cerebrovascular diseases based on a big data AI model, including:

[0010] S1: Obtain multi-source disease data of patients with cardiovascular and cerebrovascular chronic diseases and pre-process the multi-source disease data;

[0011] S2: Build a big data AI model and a knowledge base in the field of cardiovascular and cerebrovascular diseases, generate training data and verification data according to a preset ratio from the data in the knowledge base, input the training data into the big data AI model for training, and then verify the trained big data AI model with the verification data until a trained big data AI model is obtained;

[0012] S3: Input the preprocessed multi-source disease data into the trained big data AI model, and output the risk factors and condition data of patients with cardiovascular and cerebrovascular diseases;

[0013] S4: Build an AI-driven health risk assessment model based on the trained big data AI model, input the risk factors and condition data of patients with cardiovascular and cerebrovascular diseases into the health risk assessment model, obtain the change data of various indicators of patients with cardiovascular and cerebrovascular diseases, and preset indicator change thresholds based on the knowledge base, compare the obtained indicator change data with the preset indicator change thresholds, and output the comparison results;

[0014] S5: The health risk assessment model generates a personalized health management plan containing various prescriptions based on the comparison results and transmits it to the mobile terminal.

[0015] Further, the S1 includes:

[0016] S1-1: Build a multi-source data platform, access the target patient's medical system, and collect multi-source disease data of the target patient's medical treatment;

[0017] S1-2: Create multiple hierarchical data storage modules, pre-process the multi-source disease data, and store the pre-processed multi-source disease data in corresponding hierarchical data storage modules; the hierarchical data storage modules are named according to the diagnostic prompt words for cardiovascular and cerebrovascular diseases.

[0018] Further, the S2 includes:

[0019] S2-1: Build a knowledge base based on existing literature data in the field of cardiovascular and cerebrovascular diseases and medical records of cardiovascular and cerebrovascular patients;

[0020] S2-2: Generate a big data AI model, connect the big data AI model to the Internet and knowledge base to receive data content in the field of cardiovascular and cerebrovascular diseases, and generate a prototype of the big data AI model;

[0021] S2-3: Import the medical record data of cerebrovascular patients in the knowledge base into the prototype of the big data AI model for training to obtain a trained big data AI model.

[0022] Further, the S3 includes:

[0023] S3-1: Preset storage prompt words for the big data AI model, extract data stored in multiple hierarchical data storage modules according to the preset storage prompt words, and analyze and process the data through the big data AI model;

[0024] S3-2: Extract risk factor features and disease data corresponding to the risk factor features from the analysis and processing results of the big data AI model.

[0025] Further, the S4 includes:

[0026] S4-1: Use the trained big data AI model as the driving model of the health risk assessment model;

[0027] S4-2: Generate a diagnostic mechanism based on the diagnostic process of cardiovascular and cerebrovascular diseases, generate diagnostic prompts based on risk factor characteristics, and input them into the health risk assessment model;

[0028] S4-3: The risk factors and condition data of patients with cardiovascular and cerebrovascular diseases are input into the health risk assessment model. The health risk assessment model retrieves the diagnostic prompt words and matches the risk factors according to the diagnostic mechanism, and retrieves the condition data after the match is successful to generate the change data of various indicators;

[0029] S4-4: Based on the preset indicator change thresholds in the knowledge base, the health risk assessment model compares the acquired indicator change data with the preset indicator change thresholds and outputs the comparison results.

[0030] Further, the S5 includes:

[0031] S5-1: Obtain the target medical institution information and the habit information of the target cardiovascular and cerebrovascular disease patients, input them into the health risk assessment model for processing, and generate the health management standard system of the target medical institution and the feasible health management plan for the target patients;

[0032] S5-2: The health risk assessment model generates a health management prescription based on the target comparison results, and matches the health management process in the health management prescription with the health management standard system of the target medical institution, as well as with the feasible health management plan for the target patient, to generate a personalized health management plan for the target patient and transmit it to the mobile terminal.

[0033] The personalized health management system for patients with cardiovascular and cerebrovascular diseases based on a big data AI model is applied to the above-mentioned personalized health management method for patients with cardiovascular and cerebrovascular diseases based on a big data AI model, including:

[0034] Data acquisition module: used to obtain multi-source disease data of patients with chronic cardiovascular and cerebrovascular diseases;

[0035] Data preprocessing module: used to preprocess the acquired multi-source disease data;

[0036] Knowledge base module: used to obtain medical knowledge in the field of cardiovascular and cerebrovascular diseases and build a knowledge base;

[0037] AI model building and training module: build a big data AI model, and generate training data and verification data according to the preset ratio of data in the knowledge base, input the training data into the big data AI model for training, and then verify the trained big data AI model with verification data until a trained big data AI model is obtained;

[0038] Disease analysis module: used to analyze and process the pre-processed multi-source disease data based on the trained big data AI model, and output the risk factors and disease data of patients with cardiovascular and cerebrovascular diseases;

[0039] Health risk assessment module: Build an AI-driven health risk assessment model based on the trained big data AI model, input the risk factors and condition data of patients with cardiovascular and cerebrovascular diseases into the health risk assessment model, obtain the change data of various indicators of patients with cardiovascular and cerebrovascular diseases, and preset indicator change thresholds based on the knowledge base. Compare the obtained indicator change data with the preset indicator change thresholds and output the comparison results;

[0040] Personalized health management plan generation module: used to use the health risk assessment model to generate a personalized health management plan containing various prescriptions based on the comparison results, and transmit it to the target patient.

[0041] An electronic device includes a processor and a memory, wherein the memory stores programs or instructions, and the processor executes the personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on the big data AI model as described above by calling the programs or instructions stored in the memory.

[0042] A computer-readable storage medium stores a program or instruction, which enables a computer to execute the personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on a big data AI model as described above.

[0043] The principles and advantages of the present invention are as follows: In the present invention, firstly, for the disease data of the target cardiovascular and cerebrovascular chronic disease patients, disease data from different sources, such as sources from different medical institutions, are obtained, and the disease data from these sources are classified and stored according to the diagnostic prompt words of cardiovascular and cerebrovascular diseases in the diagnosis process, and then identified through a big data AI model, wherein the construction process and training process of the big data AI model are both realized through a pre-built knowledge base, and according to the different situations of different patients in the training process, the medical records data of historical patients of the medical institution are used for real data training, so that the diagnosis mechanism of the big data AI model is more in line with the actual situation.

[0044] Subsequently, during the diagnosis process, the corresponding stored disease data is extracted according to the stored diagnostic prompt words, risk factor feature extraction and corresponding condition data extraction are performed, and an AI-driven health risk assessment model is constructed using the big data AI model. This model can simulate the real doctor's consultation process to analyze and process the patient's disease data according to the level and diagnostic mechanism of the medical institution, and then generate a health management plan that fits the medical institution and meets the needs of the target patients based on the health management standard system of the target medical institution and the habit information of the target patients. On the one hand, it facilitates patients to be more motivated in the health management process, and on the other hand, doctors will be more familiar with the health management system during subsequent follow-up. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a flowchart of an embodiment of the present invention;

[0046] Figure 2 is a functional block diagram of an embodiment of the present invention;

[0047] Figure 3 FIG. 4 is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following is further described in detail through specific implementation methods:

[0049] The symbols in the drawings of the specification include: electronic device 400 , processor 401 , memory 402 , input device 403 , and output device 404 .

[0050] The embodiment is basically as shown in the attached Figure 1 Shown: Personalized health management method for patients with chronic cardiovascular and cerebrovascular diseases based on big data AI model, including:

[0051] S1: Obtain multi-source disease data of patients with chronic cardiovascular and cerebrovascular diseases and pre-process the multi-source disease data; S1 includes:

[0052] S1-1: Build a multi-source data platform, access the target patient's medical system, and collect multi-source disease data of the target patient's medical treatment;

[0053] S1-2: Create multiple hierarchical data storage modules to preprocess the multi-source disease data, and store the preprocessed multi-source disease data in corresponding hierarchical data storage modules.

[0054] At present, with the development of society, medical institutions are becoming more and more common, and patients have more choices. Especially for chronic cardiovascular and cerebrovascular diseases, patients tend to have more choices due to their long cycle. As a result, the disease data of patients are not centralized, which often leads to patients having to undergo repeated examinations in different medical institutions according to their medical standards and procedures, resulting in poor patient experience and incommunicability of disease data.

[0055] In this regard, the multi-source data platform in this application is installed in the user's mobile terminal, for example, in the form of an APP or a mini-program, and obtains authorization to access the systems of various medical platforms, thereby breaking the data silos when patients visit different medical institutions and making disease data interoperable.

[0056] As for the acquired multi-source disease data, the content of the multi-source disease data is optimized through missing value processing, duplicate value processing, etc., and then multiple hierarchical data storage modules are created. In this embodiment, the multiple hierarchical data storage modules are named according to the diagnostic prompt words of cardiovascular and cerebrovascular chronic diseases, for example, blood pressure diagnosis, ultrasound diagnosis, etc. The disease data of the target patients stored in this storage method can be specifically identified in the data storage module when the data is read subsequently, which greatly improves the data reading speed.

[0057] S2: Build a big data AI model and a knowledge base in the field of cardiovascular and cerebrovascular diseases, generate training data and verification data according to a preset ratio from the data in the knowledge base, input the training data into the big data AI model for training, and then verify the trained big data AI model with the verification data until a trained big data AI model is obtained; wherein, S2 includes:

[0058] S2-1: Build a knowledge base based on existing literature data in the field of cardiovascular and cerebrovascular diseases and medical records of cardiovascular and cerebrovascular patients;

[0059] S2-2: Generate a big data AI model, connect the big data AI model to the Internet and knowledge base to receive data content in the field of cardiovascular and cerebrovascular diseases, and generate a prototype of the big data AI model;

[0060] S2-3: Import the medical record data of cerebrovascular patients in the knowledge base into the prototype of the big data AI model for training to obtain a trained big data AI model.

[0061] In this embodiment, based on a multi-source data platform, authorization is obtained to obtain the medical record data of cardiovascular and cerebrovascular patients from various medical institutions, as well as the existing literature data in the field of cardiovascular and cerebrovascular diseases, to build a knowledge base. The big data AI model subsequently constructed uses the knowledge base as its training corpus to achieve the purpose of training, so as to obtain a big data AI model that can effectively diagnose cardiovascular and cerebrovascular diseases.

[0062] S3: Input the preprocessed multi-source disease data into the trained big data AI model, and output the risk factors and condition data of patients with cardiovascular and cerebrovascular diseases; S3 includes:

[0063] S3-1: preset prompt words for the big data AI model, extract data stored in multiple hierarchical data storage modules according to the preset prompt words, and analyze and process the data through the big data AI model;

[0064] S3-2: Extract risk factor features and disease data corresponding to the risk factor features from the analysis and processing results of the big data AI model.

[0065] In this embodiment, for the diagnosis process of the big data AI model, prompt words are preset, and the prompt words here include those that are consistent with the naming types of multiple hierarchical data storage modules. At the same time, semantic algorithms are used for semantic recognition, so that the preset prompt words in the big data AI model can adapt to more scenarios; after extracting the disease data stored in the multi-level storage module, the big data AI model extracts the risk factor characteristics of cardiovascular and cerebrovascular diseases of the target patients according to the training results, as well as the corresponding condition data. The risk factors in this application include blood pressure, blood lipids, electrocardiogram, glycosylated hemoglobin, blood rheology, coronary angiography, carotid artery ultrasound, etc., and the corresponding condition data are the indicator data of these risk factors.

[0066] S4: Building an AI-driven health risk assessment model based on the trained big data AI model, inputting the risk factors and condition data of patients with cardiovascular and cerebrovascular diseases into the health risk assessment model, obtaining the change data of various indicators of patients with cardiovascular and cerebrovascular diseases, and comparing the obtained change data of various indicators with the preset indicator change thresholds based on the knowledge base, and outputting the comparison results; wherein, S4 includes:

[0067] S4-1: Use the trained big data AI model as the driving model of the health risk assessment model;

[0068] S4-2: Generate a diagnostic mechanism based on the diagnostic process of cardiovascular and cerebrovascular diseases, generate diagnostic prompts based on risk factor characteristics, and input them into the health risk assessment model;

[0069] S4-3: The risk factors and condition data of patients with cardiovascular and cerebrovascular diseases are input into the health risk assessment model. The health risk assessment model retrieves the diagnostic prompt words and matches the risk factors according to the diagnostic mechanism, and retrieves the condition data after the match is successful to generate the change data of various indicators;

[0070] S4-4: Based on the preset indicator change thresholds in the knowledge base, the health risk assessment model compares the acquired indicator change data with the preset indicator change thresholds and outputs the comparison results.

[0071] In this embodiment, the constructed health risk assessment model is also driven by the big data AI model. The difference is that the health risk assessment model is used to generate a health management plan for patients. Specifically, based on the existing cardiovascular and cerebrovascular disease diagnosis process, the risk factor characteristics in S3-2 are used as diagnostic prompts, and the changes in various indicators in the target patient's condition data are analyzed in turn according to the diagnostic process, and the change results are compared with the preset indicator change thresholds to obtain comparison results.

[0072] Therefore, according to step S4, the abnormality of the target patient's indicators in cardiovascular and cerebrovascular diseases can be obtained, and based on the abnormality of the indicators, targeted improvements or adjustments need to be made, specifically:

[0073] S5: The health risk assessment model generates a personalized health management plan including various prescriptions based on the comparison results and transmits it to the mobile terminal; wherein S5 includes:

[0074] S5-1: Obtain the target medical institution information and the habit information of the target cardiovascular and cerebrovascular disease patients, input them into the health risk assessment model for processing, and generate the health management standard system of the target medical institution and the health management plan of the target patient;

[0075] S5-2: The health risk assessment model generates a health management prescription based on the target comparison results, and matches the health management process in the health management prescription with the health management standard system of the target medical institution, and matches it with the health management plan of the target patient, to generate a personalized health management plan for the target patient and transmit it to the mobile terminal.

[0076] In this embodiment, the target medical institution information obtained includes the target medical institution's on-duty doctor information, medical equipment status, medical institution patient number information, medical system structure, medical treatment process, etc., and the target cardiovascular and cerebrovascular disease patient's habit information includes the patient's eating habits, behavioral habits, exercise habits, etc. Based on this information, a personalized health management plan that conforms to the medical institution and patient habits is generated, so that doctors can operate based on the equipment and facilities of the target medical institution when assisting in health management or follow-up visits. On the other hand, the health management plan is more compatible with the habits of the target patients and can improve the execution rate of the target patients.

[0077] like Figure 2As shown, in another embodiment of the present embodiment, a personalized health management system for patients with cardiovascular and cerebrovascular diseases based on a big data AI model is also included, which is applied to the above-mentioned personalized health management method for patients with cardiovascular and cerebrovascular diseases based on a big data AI model, including:

[0078] Data acquisition module: used to obtain multi-source disease data of patients with chronic cardiovascular and cerebrovascular diseases;

[0079] Data preprocessing module: used to preprocess the acquired multi-source disease data;

[0080] Knowledge base module: used to obtain medical knowledge in the field of cardiovascular and cerebrovascular diseases and build a knowledge base;

[0081] AI model building and training module: build a big data AI model, and generate training data and verification data according to the preset ratio of data in the knowledge base, input the training data into the big data AI model for training, and then verify the trained big data AI model with verification data until a trained big data AI model is obtained;

[0082] Disease analysis module: used to analyze and process the pre-processed multi-source disease data based on the trained big data AI model, and output the risk factors and disease data of patients with cardiovascular and cerebrovascular diseases;

[0083] Health risk assessment module: Build an AI-driven health risk assessment model based on the trained big data AI model, input the risk factors and condition data of patients with cardiovascular and cerebrovascular diseases into the health risk assessment model, obtain the change data of various indicators of patients with cardiovascular and cerebrovascular diseases, and preset indicator change thresholds based on the knowledge base. Compare the obtained indicator change data with the preset indicator change thresholds and output the comparison results;

[0084] Personalized health management plan generation module: used to use the health risk assessment model to generate a personalized health management plan containing various prescriptions based on the comparison results, and transmit it to the target patient.

[0085] Also included is an electronic device such as Figure 3 As shown, the electronic device 400 includes one or more processors 401 and a memory 402 .

[0086] The processor 401 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 400 to perform desired functions.

[0087] The memory 402 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 401 may run the program instructions to implement the personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on the big data AI model of any embodiment of the present invention described above and / or other desired functions. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0088] In one example, the electronic device 400 may further include: an input device 403 and an output device 404, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, etc. The output device 404 may output various information to the outside, including early warning information, braking force, etc. The output device 404 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0089] Of course, to simplify, Figure 3 Only some of the components related to the present invention in the electronic device 400 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 400 may also include any other appropriate components.

[0090] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on a big data AI model provided in any embodiment of the present invention.

[0091] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0092] In addition, an embodiment of the present invention may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on a big data AI model provided in any embodiment of the present invention.

[0093] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0094] The above are only embodiments of the present invention. Common knowledge such as the known specific structures and characteristics in the scheme is not described in detail here. Ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. Personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on big data AI model, Features: include: S1: Obtain multi-source disease data of patients with cardiovascular and cerebrovascular chronic diseases and pre-process the multi-source disease data; S2: Build a big data AI model and a knowledge base in the field of cardiovascular and cerebrovascular diseases, generate training data and verification data according to a preset ratio from the data in the knowledge base, input the training data into the big data AI model for training, and then verify the trained big data AI model with the verification data until a trained big data AI model is obtained; S3: Input the preprocessed multi-source disease data into the trained big data AI model, and output the risk factors and condition data of patients with cardiovascular and cerebrovascular diseases; S4: Build an AI-driven health risk assessment model based on the trained big data AI model, input the risk factors and condition data of patients with cardiovascular and cerebrovascular diseases into the health risk assessment model, obtain the change data of various indicators of patients with cardiovascular and cerebrovascular diseases, and preset indicator change thresholds based on the knowledge base, compare the obtained indicator change data with the preset indicator change thresholds, and output the comparison results; S5: The health risk assessment model generates a personalized health management plan containing various prescriptions based on the comparison results and transmits it to the mobile terminal.

2. According to claim 1, the personalized health management method for patients with chronic cardiovascular and cerebrovascular diseases based on the big data AI model, Features: The S1 includes: S1-1: Build a multi-source data platform, access the target patient's medical system, and collect multi-source disease data of the target patient's medical treatment; S1-2: Create multiple hierarchical data storage modules, pre-process the multi-source disease data, and store the pre-processed multi-source disease data in corresponding hierarchical data storage modules; the hierarchical data storage modules are named according to the diagnostic prompt words for cardiovascular and cerebrovascular diseases.

3. The personalized health management method for patients with chronic cardiovascular and cerebrovascular diseases based on big data AI model according to claim 2, Features: The S2 includes: S2-1: Build a knowledge base based on existing literature data in the field of cardiovascular and cerebrovascular diseases and medical records of cardiovascular and cerebrovascular patients; S2-2: Generate a big data AI model, connect the big data AI model to the Internet and knowledge base to receive data content in the field of cardiovascular and cerebrovascular diseases, and generate a prototype of the big data AI model; S2-3: Import the medical record data of cerebrovascular patients in the knowledge base into the prototype of the big data AI model for training to obtain a trained big data AI model.

4. According to claim 3, the personalized health management method for patients with chronic cardiovascular and cerebrovascular diseases based on the big data AI model, Features: The S3 includes: S3-1: Preset storage prompt words for the big data AI model, extract data stored in multiple hierarchical data storage modules according to the preset storage prompt words, and analyze and process the data through the big data AI model; S3-2: Extract risk factor features and disease data corresponding to the risk factor features from the analysis and processing results of the big data AI model.

5. According to claim 4, the personalized health management method for patients with chronic cardiovascular and cerebrovascular diseases based on the big data AI model, Features: The S4 includes: S4-1: Use the trained big data AI model as the driving model of the health risk assessment model; S4-2: Generate a diagnostic mechanism based on the diagnostic process of cardiovascular and cerebrovascular diseases, generate diagnostic prompts based on risk factor characteristics, and input them into the health risk assessment model; S4-3: The risk factors and condition data of patients with cardiovascular and cerebrovascular diseases are input into the health risk assessment model. The health risk assessment model retrieves the diagnostic prompt words and matches the risk factors according to the diagnostic mechanism, and retrieves the condition data after the match is successful to generate the change data of various indicators; S4-4: Based on the preset indicator change thresholds in the knowledge base, the health risk assessment model compares the acquired indicator change data with the preset indicator change thresholds and outputs the comparison results.

6. The personalized health management method for patients with chronic cardiovascular and cerebrovascular diseases based on big data AI model according to claim 5, Features: The S5 includes: S5-1: Obtain the target medical institution information and the habit information of the target cardiovascular and cerebrovascular disease patients, input them into the health risk assessment model for processing, and generate the health management standard system of the target medical institution and the health management plan of the target patient; S5-2: The health risk assessment model generates a health management prescription based on the target comparison results, and matches the health management process in the health management prescription with the health management standard system of the target medical institution, and matches it with the health management plan of the target patient, to generate a personalized health management plan for the target patient and transmit it to the mobile terminal.

7. A personalized health management system for patients with cardiovascular and cerebrovascular diseases based on a big data AI model, applied to the personalized health management method for patients with cardiovascular and cerebrovascular diseases based on a big data AI model as described in any one of claims 1 to 6 above, Features: include: Data acquisition module: used to obtain multi-source disease data of patients with chronic cardiovascular and cerebrovascular diseases; Data preprocessing module: used to preprocess the acquired multi-source disease data; Knowledge base module: used to obtain medical knowledge in the field of cardiovascular and cerebrovascular diseases and build a knowledge base; AI model building and training module: build a big data AI model, and generate training data and verification data according to the preset ratio of data in the knowledge base, input the training data into the big data AI model for training, and then verify the trained big data AI model with verification data until a trained big data AI model is obtained; Disease analysis module: used to analyze and process the pre-processed multi-source disease data based on the trained big data AI model, and output the risk factors and disease data of patients with cardiovascular and cerebrovascular diseases; Health risk assessment module: Build an AI-driven health risk assessment model based on the trained big data AI model, input the risk factors and condition data of patients with cardiovascular and cerebrovascular diseases into the health risk assessment model, obtain the change data of various indicators of patients with cardiovascular and cerebrovascular diseases, and preset indicator change thresholds based on the knowledge base. Compare the obtained indicator change data with the preset indicator change thresholds and output the comparison results; Personalized health management plan generation module: used to use the health risk assessment model to generate a personalized health management plan containing various prescriptions based on the comparison results, and transmit it to the target patient.

8. An electronic device, Features: It includes a processor and a memory, wherein the memory stores programs or instructions, and the processor executes the personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on a big data AI model as described in any one of claims 1 to 6 by calling the programs or instructions stored in the memory.

9. A computer-readable storage medium, Features: The computer-readable storage medium stores programs or instructions, which enable the computer to execute the personalized health management method for patients with cardiovascular and cerebrovascular chronic diseases based on a big data AI model as described in any one of claims 1 to 6 above.

Images