Cardiovascular disease artificial intelligence auxiliary diagnosis and treatment system based on Internet hospital

Abstract

The invention relates to the technical field of medical auxiliary systems, in particular to a cardiovascular disease artificial intelligence auxiliary diagnosis and treatment system based on an internet hospital. Comprising a health file module and a remote monitoring module. The virtual assistant module is used for assisting a doctor to interact with a patient and acquiring key medical information in advance; the risk prediction module is used for calculating the future cardiovascular event risk of the patient and performing early warning; and the health collaboration module integrates all data and synchronizes the data to a medical caregiver related to the patient. Through intelligent interaction of three dimensions of patient-cardiologist-virtual assistant, the application of the invention is beneficial for improving the efficiency and individuation level of medical services, and is beneficial for constructing a more efficient health management system. For a primary patient, the method assists cardiovascular specialists and non-cardiovascular professional medical workers in quickly constructing a cardiovascular disease diagnosis and treatment process; and for a re-consultation patient, cardiovascular event early warning is given in advance, so that potential medical negligence and potential health hazards are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of medical assistance systems, and in particular to an artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on an Internet hospital. Background Art

[0002] As the incidence of cardiovascular diseases increases year by year, especially in the context of an aging society and changes in lifestyle, the number of people suffering from cardiovascular diseases has increased sharply, including many elderly patients with multiple chronic diseases. Traditional cardiovascular disease diagnosis and treatment methods face many challenges such as diagnostic efficiency, accuracy and uneven distribution of medical resources.

[0003] The patent application number is CN201811207418.4, and it is recorded in the specification that "the present invention discloses a diagnosis and treatment decision system based on artificial intelligence, the system comprising: an interactive device and a host computer; the interactive device obtains the patient's clinical patient information, and sends the clinical patient information to the host computer, the clinical patient information includes clinical diagnosis and treatment information and auxiliary examination information; the host computer performs standardization processing on the clinical diagnosis and treatment information and auxiliary examination information to obtain standardized information in a preset format; the host computer searches for a preset decision tree according to the standardized information to obtain target diagnosis decision information corresponding to the standardized information. The preset decision tree identifies the clinical patient information of the patient and can quickly and accurately output the target diagnosis decision information. The pre-standardization of the clinical patient information further improves the search efficiency of the preset decision tree, so that it can assist doctors in rapid and standardized diagnosis and treatment. "Due to the particularity of cardiovascular disease, when making treatment decisions in the early stage, it is necessary to evaluate the patient's cardiovascular disease risk as a whole; in long-term treatment follow-up, it is necessary to combine the situation of each specific patient and conduct dynamic evaluation to ensure the adoption of the optimal treatment strategy; and when the patient has a sudden cardiovascular event, the risk stratification and early warning functions are particularly important because the treatment of the patient is time-sensitive. However, the current large model still has certain limitations in practical applications. In summary, the development of an artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on Internet hospitals is still a key issue that needs to be urgently solved in the field of medical auxiliary system technology. Summary of the invention

[0004] The purpose of the present invention is to solve the problem in the prior art that although the above-mentioned technology can greatly improve the diagnosis and treatment efficiency of primary doctors by automatically processing clinical data, constructing decision trees and providing diagnosis and treatment decisions through artificial intelligence technology, after the end of the medication in the treatment stage, patients will not choose to re-examine in time because they have no obvious discomfort reaction and work and life reasons, which leads to recurrence of the disease and affects the treatment effect.

[0005] To achieve the above-mentioned object, the present invention provides an artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on an Internet hospital, comprising: a health record module, which obtains patient personal information and medical record information based on the Internet hospital to obtain patient personalized data; Remote monitoring module, which pushes medication plans and medication questionnaires based on the patient's personalized data, as well as the patient's medication feedback and real-time data generated by remote wearable devices, including body temperature, heart rate variability, electrocardiogram, blood pressure, respiration, blood oxygen, and maximum oxygen uptake data; The risk prediction module, based on real-time data, warns patients of their recent and future cardiovascular event risks P:

[0006] Where: w i is the weight; x i is the i-th real-time data of the remote wearable device; σ(·) is the risk activation function, and the formula is: , μ is the empirical coefficient, ranging from 2 to 5, θ is the empirical coefficient, ranging from 0.5 to 1; k is the time attenuation factor, ranging from 0.1 to 0.5, t is the current time, t0 is the risk starting reference point of real-time data, which is set by the preset rules.

[0007] Furthermore, the system also includes: The virtual assistant module uses an artificial intelligence chatbot to interact with patients regularly during medication periods based on personalized patient data and medication data to obtain interaction data; The health collaboration module establishes a common health management network and obtains the patient's permission to share medication data and the risk of delayed review with the patient's guardian.

[0008] Furthermore, the operation process of the health record module includes: Patients provide personal information when registering for an Internet hospital. At the same time, the Internet hospital connects data with the electronic medical record system of a traditional hospital through an API interface to obtain the patient's medical record information. Unstructured and structured databases are used to store the patient's personal information and medical record information. Data analysis is performed based on the patient's personal information and medical record information. Convolutional neural networks are used to extract feature data related to cardiovascular diseases, and then personalized patient data is obtained. Convolutional neural networks: ,in is the extracted feature vector, represents the patient's imaging data, To extract cardiovascular disease related features, For each structured data feature, is the regression coefficient.

[0009] Furthermore, the remote monitoring module operation process includes: Get personalization and regular updates through wearable devices; Use data mining and regression analysis to analyze the patient's personalized data, push medication plans, design medication questionnaires through the mobile application of the Internet hospital, and dynamically adjust the content of the medication questionnaire based on the patient's personalized data. Patients fill in and submit medication questionnaires through the mobile application of the Internet hospital. Regression analysis method: ,in Based on patient data He Shen The regression model of the number, is the error term, medication questionnaire: ,in Yes and Problem The associated weight matrix, is the patient data, Final set of questions.

[0010] Furthermore, the remote monitoring module operation process includes: Internet hospitals use artificial intelligence technology to automatically analyze the data submitted by patients in medication questionnaires, use support vector machines to classify the questionnaire data, and automatically identify adverse reactions. Then, they notify doctors to intervene further and optimize medication plans. By integrating patients’ medication plans with medication questionnaire feedback, comprehensive medication data is generated for optimization and adjustment: ,in is the current medication plan, is the adjusted medication plan, The dosage, type and schedule of medication are adjusted by doctors based on patient feedback data. Support vector machine: ,in Indicates Feedback, is the classification weight vector, is the bias term, It reflects the situation. is the slack variable, are input features.

[0011] The virtual assistant module is problem-oriented and builds the next diagnosis and treatment plan based on the patient's previous medical history, remote monitoring data, disease diagnosis, medication status, and the problems that need to be solved during this visit to help doctors make decisions quickly.

[0012] Furthermore, the operation process of the virtual assistant module includes: During regular interactions with patients, the artificial intelligence chatbot communicates with them in various forms, including text, voice, and pictures, and records and stores patients' interaction data in real time. The interaction data includes whether the patients take medication on time, whether adverse reactions occur, their tolerance to drugs, and their psychological state.

[0013] Furthermore, the health collaboration module operation process includes: In the Internet hospital, all medical system resources on different platforms are shared. The accounts of patients and guardians will be bound, and guardians can view the patient's health data in real time through the Internet hospital's mobile application and data sharing model. The health data includes the patient's medication history, medication rules, whether the review is on time, and the predicted risk of delayed review. The data sharing model: , where Shared data covers the risk of delayed review , medication data and interactive data , Health updates received by guardians, including real-time shared data and warning notifications .

[0014] Furthermore, the health collaboration module operation process includes: Guardians can view real-time updated health data through the Internet hospital's mobile application and receive early warning notifications about high-risk review delays. The Internet hospital also provides data analysis tools that allow guardians to track patients' health changes and medication use, providing basic data for guardians to make care decisions.

[0015] Beneficial Effects Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects: The present invention solves the limitation of large model application and the technical problem of being unfriendly to patients.

[0016] When used, the present invention is conducive to improving the quality and efficiency of medical services at the same time, and provides standardized full-cycle protection for the diagnosis, treatment, follow-up and prevention of cardiovascular diseases. Based on the data extraction and analysis of the health record module and the remote monitoring module, during the interaction between the virtual assistant and the patient, it can actively collect key information required for the diagnosis and treatment of cardiovascular diseases, aiming to provide cardiovascular doctors and non-specialized doctors with the next step of diagnosis and treatment strategies, and can provide early warning of cardiovascular event risks. The health collaboration module helps to build a more efficient health management system, allowing patients to enjoy more personalized treatment services while reducing potential medical accidents and health risks.

[0017] The present invention solves the static defects and risk delayed response problems of traditional models through the dual-engine design of σ(·) activation function and time-sensitive decision model, and forms a new cardiovascular early warning standard that is both in line with medical logic and has engineering practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a system diagram of an artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on an Internet hospital in the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] The present invention is further described in detail below in conjunction with the accompanying drawings: Example: like Figure 1 As shown, the present invention provides an artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on an Internet hospital, including: a health record module, which obtains patient personal information and medical record information based on the Internet hospital to obtain patient personalized data; Furthermore, the operation process of the health record module includes: Patients provide personal information when registering for an Internet hospital. At the same time, the Internet hospital connects data with the electronic medical record system of a traditional hospital through an API interface to obtain the patient's medical record information. Unstructured and structured databases are used to store the patient's personal information and medical record information. Data analysis is performed based on the patient's personal information and medical record information. Convolutional neural networks are used to extract feature data related to cardiovascular diseases, and then personalized patient data is obtained. Convolutional neural networks: ,in is the extracted feature vector, represents the patient's imaging data, To extract cardiovascular disease related features, For each structured data feature, is the regression coefficient; Specifically, the health record module uses convolutional neural network technology to process and extract features from patients' imaging data. Through multi-layer convolution and pooling operations, convolutional neural networks can effectively capture local features in images and perform global feature aggregation, thereby identifying relevant signs of cardiovascular disease. It is convenient to extract key features of cardiovascular disease from patients' imaging data, and together with the patient's basic information, it constitutes the patient's personalized health data, which is beneficial to improving the quality of medical services and providing strong guarantees for the early prevention and precise treatment of cardiovascular diseases.

[0022] The remote monitoring module pushes medication plans and medication questionnaires based on the patient's personalized data. After the patient submits the medication questionnaire, the medication data is obtained; Furthermore, the remote monitoring module operation process includes: Get personalization and regular updates through wearable devices; Use data mining and regression analysis to analyze the patient's personalized data, push medication plans, design medication questionnaires through the mobile application of the Internet hospital, and dynamically adjust the content of the medication questionnaire based on the patient's personalized data. Patients fill in and submit medication questionnaires through the mobile application of the Internet hospital. Regression analysis method: ,in Based on patient data He Shen The regression model of the number, is the error term, medication questionnaire: ,in Yes and Problem The associated weight matrix, is the patient data, Final Problem Set; Furthermore, the remote monitoring module operation process includes: Internet hospitals use artificial intelligence technology to automatically analyze the data submitted by patients in medication questionnaires, use support vector machines to classify the questionnaire data, and automatically identify adverse reactions. Then, they notify doctors to intervene further and optimize medication plans. By integrating patients’ medication plans with medication questionnaire feedback, comprehensive medication data is generated for optimization and adjustment: ,in is the current medication plan, is the adjusted medication plan, The dosage, type and schedule of medication are adjusted by doctors based on patient feedback data. Support vector machine: ,in Indicates Feedback, is the classification weight vector, is the bias term, It reflects the situation. is the slack variable, is the input feature; Specifically, the remote monitoring module builds a regression model through regression analysis of the patient's personalized data and pushes a medication plan to the patient. In addition, the patient's personalized data is combined with the medication plan using regression analysis methods, and the content of the medication questionnaire is dynamically adjusted to improve the matching degree between the content of the medication questionnaire and the patient's actual situation. After the patient submits the medication questionnaire, the Internet hospital will use artificial intelligence technology to automatically analyze the medication questionnaire for classification, which is conducive to improving the accuracy of identifying the patient's medication problems. The remote monitoring module not only realizes the automatic collection and analysis of medication data, but also identifies adverse reactions, which is conducive to improving the efficiency and safety of medication management. Through intelligent tracking of medication plans and optimization adjustments, patients can enjoy more personalized treatment services, which is conducive to reducing the health risks caused by improper medication or poor compliance.

[0023] The virtual assistant module uses an artificial intelligence chatbot to interact with patients regularly during medication periods based on personalized patient data and medication data to obtain interaction data; The virtual assistant module is problem-oriented and builds the next diagnosis and treatment plan based on the patient's previous medical history, remote monitoring data, disease diagnosis, medication status, and the problems that need to be solved during this visit to help doctors make decisions quickly.

[0024] Furthermore, the operation process of the virtual assistant module includes: In regular interactions with patients, AI chatbots communicate with patients in a variety of forms, including text, voice, and pictures, and record and store patients’ interaction data in real time. The interaction data includes whether the patient takes medication on time, whether adverse reactions occur, drug tolerance, and psychological state. Specifically, the virtual assistant module aims to regularly interact with patients based on the personalized data and medication data of patients through artificial intelligence chatbots, so that patients take medicine on time and provide timely feedback on their health status. Through reinforcement learning technology, the interaction strategy with patients is dynamically adjusted to improve medication compliance and treatment effect. The artificial intelligence chatbot will set the interaction time points with patients according to the personalized medication schedule of patients. These time points are strictly matched with the medication time of patients to ensure that patients can receive reminders and provide feedback at the appropriate time, forming a complete set of interactive data streams. Through reinforcement learning algorithms, the chatbot can adjust the interaction strategy with patients according to the results of the interaction. In the interaction with patients, the artificial intelligence chatbot communicates with patients in a variety of ways, including text, voice and pictures, making the interaction process more vivid and easy to understand. At the same time, the artificial intelligence chatbot will record and store the patient's interaction data in real time, and the interaction data will be fed back to the patient's attending physician, providing doctors with a more comprehensive patient health status and facilitating timely adjustment of treatment plans. The virtual assistant module not only improves patients' medication compliance, but also effectively promotes the interaction between patients and medical teams. By dynamically adjusting the interaction strategy, patients' trust and compliance in treatment are enhanced. At the same time, doctors can understand patients' medication reactions and health changes through interactive data, optimize treatment plans, and help reduce the occurrence of adverse reactions. For patients, regular interactive reminders can not only promote timely medication, but also help them better understand the precautions for drug use, which is conducive to improving the overall effect of treatment. Through intelligent interaction, it is conducive to improving the efficiency and personalization of medical services and building a more efficient health management system.

[0025] The risk prediction module, based on real-time data, warns patients of their recent and future cardiovascular event risks P:

[0026] Where: w i is the weight; x i is the i-th real-time data of the remote wearable device; σ(·) is the risk activation function, and the formula is: , μ is the empirical coefficient, ranging from 2 to 5, θ is the empirical coefficient, ranging from 0.5 to 1; k is the time attenuation factor, ranging from 0.1 to 0.5, t is the current time, t0 is the risk starting reference point of real-time data, which is set by the preset rules.

[0027] Take the acute heart failure scenario as an example: Timeline: The patient suddenly developed paroxysmal nocturnal dyspnea (time base point t0) Sequence of events: 03:00 Wearable device detects SpO2<90% → Feature x1 activated 03:15 Smart medicine box not opened according to prescription → Feature x2 activated 03:30 Voice interaction recognition detected "out of breath" → Feature x3 activated The value of P is calculated using the above formula.

[0028] Decision Response: When P exceeds the threshold, execute: Prioritize the delivery of emergency treatment instructions to the doctor's workstation; Simultaneously activate the family emergency notification system; The emergency vehicle dispatch system is pre-activated (nearest ambulance within 5 kilometers).

[0029] Through the above formula, a time-sensitive decision-making model is obtained. In the existing technology, the fixed time window cannot capture immediate risks. This solution constructs a "time lens" effect, which makes the amplification factor of recent events reach 3.2 times (when k=0.15), and the influence decays to 12% of the initial value after 72 hours.

[0030] How to obtain the time base point: Take the scenario of high blood pressure in the morning for example: Timeline: 05:30:00 - The smart bracelet detected slight limb movements (a sign of waking up in the morning); 05:32:18 - Sensors built into the pillow capture changes in breathing rate; 05:33:45 - The millimeter-wave radar detected the movement of standing beside the bed; 05:34:02 - Body fat scale records weight data (first measurement after getting up in the morning); 05:35:15 - The wrist blood pressure monitor measured 158 / 102 mmHg.

[0031] Time-based arbitration process: According to the patient's condition and the data available, the time when the millimeter-wave radar detects the bedside standing action can be set as the time base point.

[0032] The present invention adopts σ(·) as the activation function to map all data to the range of 0-1. Through parameterized nonlinear mapping, while retaining the rigor of the mathematical model, it is highly consistent with the dual capture needs of the medical field for progressive risk evolution and sudden threshold events.

[0033] The present invention solves the static defects and risk delayed response problems of traditional models through the dual-engine design of σ(·) activation function and time-sensitive decision model, and forms a new cardiovascular early warning standard that is both in line with medical logic and has engineering practicality.

[0034] The health collaboration module establishes a common health management network and obtains the patient's permission to share medication data and the risk of delayed review with the patient's guardian; Furthermore, the health collaboration module operation process includes: In the Internet hospital, all medical system resources on different platforms are shared. The accounts of patients and guardians will be bound, and guardians can view the patient's health data in real time through the Internet hospital's mobile application and data sharing model. The health data includes the patient's medication history, medication rules, whether the review is on time, and the predicted risk of delayed review. The data sharing model: , where Shared data covers the risk of delayed review , medication data and interactive data , Health updates received by guardians, including real-time shared data and warning notifications ; Furthermore, the health collaboration module operation process includes: Guardians can view real-time updated health data through the Internet hospital's mobile application and receive early warning notifications about high-risk review delays. The Internet hospital also provides data analysis tools to allow guardians to track patients' health changes and medication status, providing basic data for guardians to make care decisions. Specifically, when a patient registers at an Internet hospital, his or her guardian's account will be bound to form a data sharing channel. Guardians can view the patient's health data in real time through the Internet hospital's mobile application. These data include the patient's medication history, medication patterns, whether they have been reviewed on time, and the predicted risk of delayed reviews. The data sharing channel not only allows guardians to fully understand the patient's medication and health status, but also to promptly detect the risk of delayed reviews. This is conducive to taking timely measures when patients exhibit high-risk behaviors such as delayed reviews, to avoid recurrence of the disease due to delays, greatly reducing the risk of patients forgetting to review or delaying reviews, and reducing potential medical accidents and health risks.

[0035] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on an Internet hospital, characterized in that: include: The health record module obtains the patient's personal information and all previous medical records inside and outside the hospital based on the Internet hospital to obtain the patient's integrated medical data; Remote monitoring module, which pushes medication plans and medication questionnaires based on the patient's personalized data, as well as the patient's medication feedback and real-time data generated by remote wearable devices, including body temperature, heart rate variability, electrocardiogram, blood pressure, respiration, blood oxygen, and maximum oxygen uptake data; The risk prediction module, based on real-time data, warns patients of their recent and future cardiovascular event risks P: Where: w i is the weight; x i is the i-th real-time data of the remote wearable device; σ(·) is the risk activation function, and the formula is: , μ is the empirical coefficient, ranging from 2 to 5, θ is the empirical coefficient, ranging from 0.5 to 1; k is the time attenuation factor, ranging from 0.1 to 0.5, t is the current time, t0 is the risk starting reference point of real-time data, which is set by the preset rules.

2. According to claim 1, an artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on an Internet hospital is characterized in that: The system further comprises: The virtual assistant module uses an artificial intelligence chatbot to interact with patients regularly during medication periods based on personalized patient data and medication data to obtain interaction data; Health collaboration module: 1) Realize data interoperability and sharing among different medical platforms; 2) Obtain patient permission to share medication data and the risk of delayed review with patient guardians by establishing a common health management network.

3. According to claim 1, an artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on an Internet hospital is characterized in that: The operation process of the health record module includes: Patients provide personal information when registering for an Internet hospital. At the same time, the Internet hospital connects data with the electronic medical record system of a traditional hospital through an API interface to obtain the patient's medical record information. Unstructured and structured databases are used to store the patient's personal information and medical record information. Data analysis is performed based on the patient's personal information and medical record information. Convolutional neural networks are used to extract feature data related to cardiovascular diseases, and then personalized patient data is obtained. Convolutional neural networks: ,in is the extracted feature vector, represents the patient's imaging data, To extract cardiovascular disease related features, For each structured data feature, is the regression coefficient.

4. According to claim 1, an artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on an Internet hospital is characterized in that: The remote monitoring module operation process includes: Get personalization and regular updates through wearable devices; Use data mining and regression analysis to analyze the patient's personalized data, push medication plans, design medication questionnaires through the mobile application of the Internet hospital, and dynamically adjust the content of the medication questionnaire based on the patient's personalized data. Patients fill in and submit medication questionnaires through the mobile application of the Internet hospital. Regression analysis method: ,in Based on patient data He Shen The regression model of the number, is the error term, medication questionnaire: ,in Yes and Problem The associated weight matrix, is the patient data, Final set of questions.

5. According to claim 2, an artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on an Internet hospital is characterized in that: The remote monitoring module operation process includes: Internet hospitals use artificial intelligence technology to automatically analyze the data submitted by patients in medication questionnaires, use support vector machines to classify the questionnaire data, and automatically identify adverse reactions. Then, they notify doctors to intervene further and optimize medication plans. By integrating patients’ medication plans with medication questionnaire feedback, comprehensive medication data is generated for optimization and adjustment: ,in is the current medication plan, is the adjusted medication plan, The dosage, type and schedule of medication are adjusted by doctors based on patient feedback data. Support vector machine: ,in Indicates Feedback, is the classification weight vector, is the bias term, It reflects the situation. is the slack variable, are input features.

6. The artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on Internet hospitals according to claim 5 is characterized in that: The operation process of the virtual assistant module includes: During regular interactions with patients, the artificial intelligence chatbot communicates with them in various forms, including text, voice, and pictures, and records and stores patients' interaction data in real time. The interaction data includes whether the patients take medication on time, whether adverse reactions occur, their tolerance to drugs, and their psychological state.

7. The artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on Internet hospitals according to claim 6 is characterized in that: The operation process of the health collaboration module includes: In the Internet hospital, all medical system resources on different platforms are shared. The accounts of patients and guardians will be bound, and guardians can view the patient's health data in real time through the Internet hospital's mobile application and data sharing model. The health data includes the patient's medication history, medication rules, whether the review is on time, and the predicted risk of delayed review. The data sharing model: , where Shared data covers the risk of delayed review , medication data and interactive data , Health updates received by guardians, including real-time shared data and warning notifications .

8. The artificial intelligence-assisted diagnosis and treatment system for cardiovascular diseases based on Internet hospitals according to claim 7 is characterized in that: The operation process of the health collaboration module includes: Guardians can view real-time updated health data through the Internet hospital's mobile application and receive early warning notifications about high-risk review delays. The Internet hospital also provides data analysis tools that allow guardians to track patients' health changes and medication use, providing basic data for guardians to make care decisions.

Images