Cardiovascular disease multi-dimensional data collaborative management system and method based on AI driving

Abstract

The invention belongs to the technical field of medical treatment and health, and particularly relates to an AI-driven cardiovascular disease multi-dimensional data collaborative management system and method.The method comprises the steps that firstly, a data recording module records disease data of historical cardiovascular diseases of a target patient through a mobile diagnosis and treatment terminal and stores the disease data in a classified mode; the system construction module obtains diagnosis and treatment process information of the target medical institution, and constructs a medical guidance system corresponding to the target medical institution according to the diagnosis and treatment process information; then, the data management module performs matching management on the stored disease data of the target patient and a medical treatment guidance system of a medical institution for medical treatment of the target patient according to a pre-constructed AI driving model to generate a medical treatment guidance result; and finally, the data feedback module feeds back the doctor-seeing guidance result of the target patient to the mobile diagnosis and treatment terminal of the target patient. According to the invention, the problems of data islands and non-unification of cardiovascular disease multi-dimensional data in the prior art can be solved.

Description

Technical Field

[0001] The present invention belongs to the field of medical health technology, and in particular to an AI-driven cardiovascular disease multidimensional data collaborative management system and method. Background Art

[0002] Cardiovascular disease is one of the most serious diseases in the society today. It includes coronary artery disease, hypertension, heart failure, etc. These cardiovascular diseases not only affect the quality of life of patients, but also increase the economic burden. Therefore, the treatment of cardiovascular disease can achieve rapid and accurate response, which is the greatest help to patients. However, most of the current medical systems, when facing acute cardiovascular diseases, are unable to provide timely and effective treatment due to geographical restrictions, time constraints and uneven distribution of professional resources.

[0003] In recent years, with the development of the Internet, big data and artificial intelligence technologies, "smart first aid" has become a new trend in the field of cardiovascular disease treatment. The application of these technologies can significantly improve the efficiency and effectiveness of treatment. For example, by collecting patients' vital signs data through mobile medical devices, real-time monitoring can be achieved. Using big data analysis technology to process these data can help with early warning and accurate diagnosis. Artificial intelligence can assist doctors in making decisions and improve the level of diagnosis and treatment.

[0004] However, cardiovascular disease is a general term for a variety of diseases. When the data sources of a patient's cardiovascular disease are different and the forms and dimensions are different, the problems that often exist in the existing technology are: 1. There is a lack of effective data sharing mechanism between different medical institutions, resulting in data islands, and the patient's disease data cannot be effectively utilized; 2. When diagnosing patients, it is difficult for each medical institution to form a unified diagnosis opinion, and there is a lack of effective communication between institutions, which will increase the patient's medical costs. Summary of the invention

[0005] The technical problem solved by the present invention is to provide an AI-driven collaborative management system and method for multidimensional data of cardiovascular diseases, so as to solve the problems of data islands and inconsistency in multidimensional data of cardiovascular diseases existing in the prior art.

[0006] The basic solution provided by the present invention is a cardiovascular disease multidimensional data collaborative management system driven by AI, including:

[0007] Data recording module: used to record the target patient's historical cardiovascular disease data through the mobile diagnosis and treatment terminal, and store them by category;

[0008] System construction module: used to obtain the diagnosis and treatment process information of the target medical institution, and build the corresponding medical guidance system of the target medical institution based on the diagnosis and treatment process information;

[0009] Data management module: used to match and manage the stored disease data of target patients and the medical guidance system of the medical institution where the target patients seek medical treatment based on the pre-built AI-driven model, and generate medical guidance results;

[0010] Data feedback module: used to feed back the medical guidance results of the target patient to the target patient's mobile diagnosis and treatment terminal.

[0011] Furthermore, the data recording module includes a platform access unit, a data collection unit and a storage unit. The platform access unit is used to access the medical platform of the target medical institution each time the target patient seeks medical treatment. The data collection unit is used to collect the disease data of the target patient through unique ID information after the platform access unit accesses the medical platform of the target medical institution. In the storage unit, multiple distributed storage sub-units are established according to the diagnosis prompt words of the medical institution, and each storage sub-unit stores the disease data of the target patient according to the diagnosis prompt words.

[0012] Furthermore, the system construction module includes an information acquisition unit and a system construction unit. The information acquisition unit is used to obtain the change information of each diagnosis and treatment subject when the target medical institution is in operation; the system construction unit is used to establish a corresponding medical guidance system based on the obtained change information of each diagnosis and treatment subject of the target medical institution.

[0013] Furthermore, the data management module includes:

[0014] AI-driven model building unit: used to build an AI-driven model for cardiovascular disease medical guidance and management, and to train the AI-driven model for cardiovascular disease recognition and diagnosis;

[0015] Model training unit: used to obtain authorization from the target medical institution and then access the target medical institution’s Internet data and the medical guidance system corresponding to the internal diagnosis and treatment process to conduct AI-driven model training;

[0016] Data analysis and processing unit: used to generate diagnostic prompt words according to the characteristics of the diagnosis and treatment process of the medical guidance system, and use the diagnostic prompt words through the AI-driven model to actively extract disease data from the corresponding storage sub-unit for identification and diagnosis to generate diagnostic results.

[0017] Furthermore, the data management module also includes a judgment unit and a medical guidance optimization unit. The judgment unit is used to judge whether the diagnosis result generated in the data analysis and processing unit has defects. If not, it is directly pushed to the data feedback module. If so, the medical guidance optimization unit is called to perform optimization processing;

[0018] The medical guidance optimization unit is used to generate multiple medical improvement plans based on the defects in the diagnosis results through an AI-driven model, and calculate the recommendation degree based on the diagnosis and treatment subjects in the target medical institution to generate the optimal medical improvement plan.

[0019] Furthermore, the data feedback module is also used to provide feedback to the doctor when the diagnosis result of the target patient is judged to be free of defects.

[0020] The AI-driven cardiovascular disease multidimensional data collaborative management method is applied to the above-mentioned AI-driven cardiovascular disease multidimensional data collaborative management system, including:

[0021] S1: Record the target patient’s historical cardiovascular disease data through a mobile diagnosis and treatment terminal and store them by category;

[0022] S2: Obtain the diagnosis and treatment process information of the target medical institution, and build a medical guidance system corresponding to the target medical institution based on the diagnosis and treatment process information;

[0023] S3: Match and manage the stored disease data of the target patient and the medical guidance system of the medical institution where the target patient seeks medical treatment based on the pre-built AI-driven model to generate medical guidance results;

[0024] S4: Feedback the medical guidance results of the target patient to the target patient's mobile diagnosis and treatment terminal.

[0025] The principles and advantages of the present invention are as follows: In the present invention, in view of the problem of different sources of disease data of cardiovascular disease patients when seeking medical treatment and data islands between medical institutions in the prior art, the present application first records the disease data of patients each time they seek medical treatment based on a mobile diagnosis and treatment terminal that users can carry with them, and classifies the data according to the type of diagnosis prompt words, so that the disease data of the target patients can be recorded at any time regardless of whether the target patients seek medical treatment in a fixed medical institution or frequently change medical institutions for treatment; then, when the target patients seek medical treatment in a new medical institution, a medical guidance system is generated according to the diagnosis and treatment process information of the current medical institution. This is because different medical institutions have different disease data. The allocation of personnel, medical equipment, and diagnostic levels are all different. In order to better enable the target patients to have a good medical experience, on the one hand, it is important to share the patient's historical disease data, and on the other hand, it is also important to improve the patient's good guidance in medical institutions. Finally, the AI-driven module generates the patient's diagnosis results according to the medical institution's medical guidance system and disease data, and generates a medical guidance plan based on the defects in the diagnosis results, such as disease data that requires additional examinations for the patient, or additional examinations that need to be done, as well as generating a detailed plan to improve the defects in combination with the target medical institution's medical guidance system for orderly and targeted improvements for the target patients.

[0026] Therefore, this application solution not only breaks the data island problem and data inconsistency problem between medical institutions, but also can provide good medical guidance plans to the medical institutions where the target patients are located, greatly improving the medical experience of the target patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a functional block diagram of Embodiment 1 of the present invention;

[0028] Figure 2 This is a flowchart of Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0029] The following is further described in detail through specific implementation methods:

[0030] Embodiment 1:

[0031] Embodiment 1 is basically as shown in the attached Figure 1 Shown: AI-driven cardiovascular disease multidimensional data collaborative management system, including:

[0032] Data recording module: used to record the target patient's historical cardiovascular disease data through the mobile diagnosis and treatment terminal, and store them by category; in this application, the data recording module includes a platform access unit, a data acquisition unit and a storage unit, specifically:

[0033] The platform access unit is used to access the medical platform of the target medical institution each time the target patient seeks medical treatment. During the access process, the authorization of the target medical institution is first obtained, and then the target medical institution provides the corresponding data content to the platform access unit based on the open permissions.

[0034] The data collection unit is used to collect the disease data of the target patient through the unique ID information after the platform access unit accesses the medical platform of the target medical institution. Specifically, the unique ID information in this application is the identity information of the target patient. Through the unique ID information, the target patient's mobile diagnosis and treatment terminal can obtain the disease data of the target patient in the current medical institution. In actual use, the target patient does not suffer from only one cardiovascular disease, but may suffer from multiple cardiovascular diseases at the same time, such as coronary artery disease, arrhythmia, etc., and the diagnostic data of each cardiovascular disease is different, which leads to the multi-dimensional situation of the target patient's disease data. How to manage this pile of multi-dimensional disease data, on the one hand, to facilitate doctors to make diagnostic decisions, and on the other hand, to facilitate the target patient to determine the physiological indicators that need to be focused on during the next medical visit, is the technical problem that needs to be solved in this application.

[0035] The above-mentioned collected disease data is stored in a storage unit, and the storage unit of the present application is different from a general storage unit. It can establish multiple distributed storage sub-units according to the diagnosis prompt words of the medical institution, and each storage sub-unit stores the disease data of the target patient according to the diagnosis prompt words; for example, during a cardiovascular disease diagnosis process of the target patient, a coronary artery disease examination was performed, and during the coronary artery disease examination, it is necessary to obtain the target patient's physiological signs including electrocardiogram, blood test, coronary angiography, cardiac ultrasound, etc., and these examination indicators are the diagnostic keywords based on which the distributed storage sub-units in the present application classify and store data.

[0036] System construction module: used to obtain the diagnosis and treatment process information of the target medical institution, and to construct the medical guidance system corresponding to the target medical institution according to the diagnosis and treatment process information; in the present application, the system construction module includes an information acquisition unit and a system construction unit, wherein the information acquisition unit is used to obtain the change information of each diagnosis and treatment subject when the target medical institution is in operation. Specifically, when the medical institution is in operation, the diagnosis and treatment subjects involved in the present application include the on-duty doctor information, medical equipment status, number of patients in the medical institution, medical system structure, diagnosis and treatment process, etc. These diagnosis and treatment subjects change over time, and the system construction unit obtains the diagnosis and treatment subject information of each target medical institution according to the information. A corresponding medical guidance system is established based on the change information of the treatment subject; in this embodiment, after the system construction unit obtains the change information of each subject of the target medical institution, it first generates a preliminary patient medical process system according to the diagnosis and treatment process and the structure of the medical system, and then adjusts the generated preliminary patient medical process system according to the information of the doctor on duty, the status of medical equipment, the number of patients in the departments involved in each process, the duration of the consultation and other information to generate a medical guidance system for the target disease in the target medical institution. The medical guidance system in this application can facilitate the medical guidance personnel to divert the patients, and can also facilitate the feasibility of the patients' independent selection.

[0037] Data management module: used to match and manage the stored disease data of target patients and the medical guidance system of the medical institution where the target patients seek medical treatment based on the pre-built AI-driven model, and generate medical guidance results;

[0038] In this embodiment, the data management module includes an AI-driven model building unit, a model training unit, and a data analysis and processing unit, wherein:

[0039] The AI-driven model construction unit is used to construct an AI-driven model for medical guidance and management of cardiovascular diseases, and to train the AI-driven model for cardiovascular disease identification and diagnosis; in this application, the constructed AI-driven model is generated based on the existing big data AI model infrastructure, and is professionally used to provide portable data management and medical guidance for target patients.

[0040] After the AI-driven model is built, it needs to be trained. In the present application, the model training unit obtains authorization from the target medical institution and then accesses the target medical institution's Internet data and the medical guidance system corresponding to the internal diagnosis and treatment process to train the AI-driven model. Specifically, after obtaining authorization from the target medical institution, the target medical institution's Internet data is accessed. The target medical institution's Internet data can provide good cognitive basic data for the AI-driven model, so that the AI-driven model has a corresponding understanding of the target medical institution's basic cognition and concepts. At the same time, after accessing the target medical institution, the generated medical guidance system is obtained. According to the content of the system, the AI-driven model can provide the target patient with targeted medical guidance suggestions of the medical institution.

[0041] After the model training is completed, the AI-driven model is used to process and analyze the disease data of the target patient. Specifically, the data analysis and processing unit generates diagnostic prompt words according to the characteristics of the diagnosis and treatment process of the medical guidance system, and uses the diagnostic prompt words through the AI-driven model to actively extract disease data from the corresponding storage subunit for identification and diagnosis to generate a diagnosis result; in this embodiment, the AI-driven model extracts diagnostic prompt words based on the medical guidance system of the target medical institution that is currently in operation. For example, the first examination process in the medical guidance system generated by the target patient is a blood test. Based on the characteristics of the process, a diagnostic prompt word for a blood indicator is generated. The AI-driven model traverses the storage subunit based on the diagnostic prompt word, and after querying the disease data stored in the storage subunit of the blood indicator, extracts the relevant blood indicator examination data, identifies and diagnoses the data, and generates a diagnosis result; in this way, the AI-driven model set in the present application can efficiently, quickly and accurately obtain the required disease data.

[0042] The data management module also includes a judgment unit and a medical guidance optimization unit. The judgment unit is used to judge whether the diagnosis result generated by the data analysis and processing unit has defects. If not, it is directly pushed to the data feedback module. If so, the medical guidance optimization unit is called for optimization processing. For example, if the judgment unit judges that the disease data of the blood drawing index is missing in the diagnosis result, or the disease data needs to be re-examined, it will be processed by the medical guidance optimization unit. During the processing, the medical guidance optimization unit generates multiple medical improvement plans according to the defective content in the diagnosis result through the AI-driven model, and optimizes the medical treatment according to the target medical data. The recommendation degree is calculated based on the diagnosis and treatment subjects in the medical institution to generate the optimal medical improvement plan; for example, if the diagnosis result of the target patient lacks chest X-ray data, the missing content is extracted and inserted into the medical improvement plan, so that after all the missing content is extracted, a new medical improvement plan is generated. When the new medical improvement plan is converted into an implementation plan, there are multiple variable factors, such as the number of patients and the time of the consultation. Therefore, there will be multiple implementation plans. In order to select the optimal implementation plan, this application selects the implementation plan with the highest recommendation degree as the optimal medical improvement plan through recommendation degree calculation.

[0043] After the perfect medical treatment plan is generated, it can be used as a medical guidance result and fed back to the target patient's mobile diagnosis and treatment terminal through the data feedback module, and the target patient will execute it according to the medical guidance results.

[0044] In addition, the medical guidance results of this application can also be transmitted to the medical end and reviewed by the doctor.

[0045] like Figure 2 As shown, in another embodiment of this embodiment, it also includes an AI-driven cardiovascular disease multidimensional data collaborative management method, which is applied to the above-mentioned AI-driven cardiovascular disease multidimensional data collaborative management system, including:

[0046] S1: Record the target patient’s historical cardiovascular disease data through a mobile diagnosis and treatment terminal and store them by category;

[0047] S2: Obtain the diagnosis and treatment process information of the target medical institution, and build a medical guidance system corresponding to the target medical institution based on the diagnosis and treatment process information;

[0048] S3: Match and manage the stored disease data of the target patient and the medical guidance system of the medical institution where the target patient seeks medical treatment based on the pre-built AI-driven model to generate medical guidance results;

[0049] S4: Feedback the medical guidance results of the target patient to the target patient's mobile diagnosis and treatment terminal.

[0050] Embodiment 2:

[0051] The difference between Example 2 and Example 1 is that the medical guidance optimization unit described in Example 2 is also used to generate multiple medical improvement plans according to the defective content in the diagnosis results through an AI-driven model, and call the improved optimization algorithm to perform matching optimization iterations according to the situation of the diagnosis and treatment subjects in the target medical institution to generate the optimal medical improvement plan.

[0052] In this embodiment, the improved optimization algorithm adopted is a genetic algorithm. The difference from the existing genetic algorithm is that the fitness value thereof is improved in this application. Specifically, the preset fitness values ​​of this application include the shortest medical journey and the shortest medical duration. The shortest medical journey is the shortest journey required for the target patient to improve the medical content according to the defective content, and the shortest medical duration is the shortest duration required for the target patient to improve the medical content according to the defective content. The improved optimization algorithm performs crossover, mutation and other operations on multiple generated medical improvement plans, and then calculates the preset fitness value of the newly generated medical improvement plan. After a preset number of iterations, the medical improvement plan with the largest fitness value is output as the optimal medical improvement plan in this embodiment.

[0053] 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. AI-driven cardiovascular disease multidimensional data collaborative management system, characterized by: include: Data recording module: used to record the target patient's historical cardiovascular disease data through the mobile diagnosis and treatment terminal, and store them by category; System construction module: used to obtain the diagnosis and treatment process information of the target medical institution, and build the corresponding medical guidance system of the target medical institution based on the diagnosis and treatment process information; Data management module: used to match and manage the stored disease data of target patients and the medical guidance system of the medical institution where the target patients seek medical treatment based on the pre-built AI-driven model, and generate medical guidance results; Data feedback module: used to feed back the medical guidance results of the target patient to the target patient's mobile diagnosis and treatment terminal.

2. The AI-driven cardiovascular disease multidimensional data collaborative management system according to claim 1, characterized in that: The data recording module includes a platform access unit, a data collection unit and a storage unit. The platform access unit is used to access the medical platform of the target medical institution each time the target patient seeks medical treatment. The data collection unit is used to collect the disease data of the target patient through unique ID information after the platform access unit accesses the medical platform of the target medical institution. In the storage unit, multiple distributed storage sub-units are established according to the diagnosis prompt words of the medical institution, and each storage sub-unit stores the disease data of the target patient according to the diagnosis prompt words.

3. The AI-driven cardiovascular disease multidimensional data collaborative management system according to claim 2, characterized in that: The system construction module includes an information acquisition unit and a system construction unit. The information acquisition unit is used to obtain the change information of each diagnosis and treatment subject when the target medical institution is in operation; the system construction unit is used to establish a corresponding medical guidance system based on the obtained change information of each diagnosis and treatment subject of the target medical institution.

4. The AI-driven cardiovascular disease multidimensional data collaborative management system according to claim 3 is characterized by: The data management module comprises: AI-driven model building unit: used to build an AI-driven model for cardiovascular disease medical guidance and management, and to train the AI-driven model for cardiovascular disease recognition and diagnosis; Model training unit: used to obtain authorization from the target medical institution and then access the target medical institution’s Internet data and the medical guidance system corresponding to the internal diagnosis and treatment process to conduct AI-driven model training; Data analysis and processing unit: used to generate diagnostic prompt words according to the characteristics of the diagnosis and treatment process of the medical guidance system, and use the diagnostic prompt words through the AI-driven model to actively extract disease data from the corresponding storage sub-unit for identification and diagnosis to generate diagnostic results.

5. The AI-driven cardiovascular disease multidimensional data collaborative management system according to claim 4, characterized in that: The data management module also includes a judgment unit and a medical guidance optimization unit. The judgment unit is used to judge whether the diagnosis result generated by the data analysis and processing unit has defects. If not, it is directly pushed to the data feedback module. If so, the medical guidance optimization unit is called to perform optimization processing; The medical guidance optimization unit is used to generate multiple medical improvement plans based on the defects in the diagnosis results through an AI-driven model, and calculate the recommendation degree based on the diagnosis and treatment subjects in the target medical institution to generate the optimal medical improvement plan.

6. The AI-driven cardiovascular disease multidimensional data collaborative management system according to claim 5, characterized in that: The data feedback module is also used to provide feedback to the doctor when the diagnosis result of the target patient is judged to be free of defects.

7. The AI-driven cardiovascular disease multidimensional data collaborative management method is applied to the AI-driven cardiovascular disease multidimensional data collaborative management system as described in any one of claims 1 to 6 above, characterized in that: include: S1: Record the target patient’s historical cardiovascular disease data through a mobile diagnosis and treatment terminal and store them by category; S2: Obtain the diagnosis and treatment process information of the target medical institution, and build a medical guidance system corresponding to the target medical institution based on the diagnosis and treatment process information; S3: Match and manage the stored disease data of the target patient and the medical guidance system of the medical institution where the target patient seeks medical treatment based on the pre-built AI-driven model to generate medical guidance results; S4: Feedback the medical guidance results of the target patient to the target patient's mobile diagnosis and treatment terminal.

Images