Clinical intelligent monitoring exercise system suitable for cardiovascular medicine department

Abstract

The invention discloses a clinical intelligent monitoring exercise system suitable for the cardiovascular medicine department, and the system comprises a collection module which is used for collecting the static physiological data of a patient with a cardiovascular disease. By integrating the static physiological data, the dynamic physiological data and the historical exercise data of the patient and utilizing the personalized exercise ability evaluation model and the real-time exercise risk prediction model, intelligent, dynamic and personalized management of the exercise scheme of the patient with the cardiovascular disease is realized; according to the method, a scientific and safe initial exercise scheme can be generated based on individual conditions of patients, physiological changes can be sensed in real time in the exercise process, potential risks can be predicted, and scheme parameters can be dynamically adjusted, so that the risk that cardiovascular events are induced by exercise is reduced to the greatest extent while the exercise effect is guaranteed, and the exercise efficiency is improved. The safety, effectiveness and compliance of exercise of the patient are remarkably improved, and a more accurate and intelligent solution is provided for clinical rehabilitation management of cardiovascular diseases.

Description

Technical Field

[0001] This invention relates to the field of health monitoring technology, specifically to an intelligent monitoring exercise system suitable for clinical cardiovascular medicine. Background Technology

[0002] Cardiovascular disease is a leading cause of death and disability worldwide, severely impacting patients' quality of life and life expectancy. In cardiovascular clinical practice, appropriate physical exercise plays a crucial role in improving cardiac function, controlling disease progression, and promoting rehabilitation. However, traditional exercise guidance methods often lack personalization and real-time monitoring, failing to meet the high demands of modern medicine for precision and safety.

[0003] While current fitness equipment and wearable devices can provide basic physiological parameter monitoring, such as heart rate and blood oxygen saturation, most lack specific design features for cardiovascular diseases and fail to fully consider the unique needs of patients. These devices typically only record data and provide simple feedback, making it difficult to dynamically adjust exercise intensity and frequency based on individual differences. This can lead to insufficient or excessive exercise, increasing the burden on the heart and even triggering acute cardiovascular events.

[0004] Existing systems generally lack effective communication mechanisms with doctors, and patients often do not receive timely guidance and support from professional physicians when receiving exercise advice. Furthermore, due to a lack of advanced data analysis capabilities and predictive models, current technologies struggle to achieve comprehensive assessments of users' health status and early warnings of potential risks, thus limiting their application value in cardiovascular disease management. Summary of the Invention

[0005] To address the aforementioned technical problems, an intelligent monitoring and exercise system suitable for clinical cardiovascular medicine is provided. This technical solution resolves the issues raised in the background section.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] In a first aspect of the present invention, an intelligent monitoring and exercise system suitable for clinical cardiovascular medicine is provided, comprising:

[0008] The acquisition module is used to collect static physiological data, dynamic physiological data, and historical exercise data of patients with cardiovascular diseases.

[0009] The first generation module is used to generate the patient's current exercise ability assessment result based on the static physiological data, dynamic physiological data and historical exercise data through a preset personalized exercise ability assessment model.

[0010] The determination module is used to determine the patient's initial exercise plan based on the exercise ability assessment results and in conjunction with a preset disease type-exercise safety threshold library. The initial exercise plan includes at least the type of exercise, initial intensity, and duration.

[0011] The risk assessment module is used to collect dynamic physiological data in real time during the patient's exercise, and to process the dynamic physiological data through a real-time exercise risk prediction model to generate real-time risk assessment results.

[0012] The second generation module is used to dynamically adjust at least one parameter in the initial training plan based on the real-time risk assessment results to generate a target training plan.

[0013] The third generation module is used to generate feedback instructions containing exercise guidance information and risk warning information based on the target exercise program, and send the feedback instructions to the patient terminal.

[0014] Preferably, the static physiological data includes the patient's age, gender, height, weight, body fat percentage, resting heart rate, resting blood pressure, left ventricular ejection fraction, myocardial enzyme levels, and records of past cardiovascular events; the dynamic physiological data includes exercise heart rate, exercise blood pressure, blood oxygen saturation, ST segment changes on electrocardiogram, and the patient's subjective fatigue score; the historical exercise data includes the patient's exercise type, frequency, duration, post-exercise heart rate recovery time, and records of adverse exercise events over the past 30 days.

[0015] Preferably, the method for establishing the personalized athletic ability assessment model includes:

[0016] Acquire sample data from multiple cardiovascular disease patients, including static physiological data, dynamic physiological data, historical exercise data, and labeled exercise ability levels.

[0017] The sample data is preprocessed, including missing value imputation, outlier removal, and data normalization.

[0018] Based on the preprocessed sample data, a feature set is extracted, which includes physiological features, movement features, and historical risk features.

[0019] The feature set is input into the initial classification model, and a personalized sports ability assessment model is obtained through cross-validation training.

[0020] The personalized athletic ability assessment model is validated based on an independent test set. When the model's assessment accuracy reaches a preset threshold, the personalized athletic ability assessment model is determined.

[0021] Preferably, the extraction of feature sets based on preprocessed sample data includes:

[0022] The static physiological data are feature-encoded to generate physiological feature vectors;

[0023] The dynamic physiological data were analyzed in the time and frequency domains to extract the exercise physiological characteristics.

[0024] Statistical analysis is performed on the historical exercise data to generate exercise compliance characteristics and exercise risk characteristics;

[0025] The physiological feature vector, exercise physiological features, exercise compliance features, and exercise risk features are fused to obtain the feature set.

[0026] Preferably, the establishment of the real-time motion risk prediction model includes:

[0027] Real-time dynamic physiological data samples of cardiovascular disease patients and corresponding risk event annotations, including exercise-induced angina, arrhythmia and abnormally high blood pressure;

[0028] The real-time dynamic physiological data sample is segmented by a sliding window to generate physiological data segments with multiple time windows;

[0029] Feature extraction is performed on the physiological data segments of each time window to obtain a real-time physiological feature sequence;

[0030] The real-time physiological feature sequence is input into the initial time series prediction model and trained using the gradient descent algorithm to obtain the real-time motion risk prediction model.

[0031] The real-time motion risk prediction model is updated online based on real-time collected dynamic physiological data of patients. When the risk prediction F1 value of the model reaches a preset threshold, the real-time motion risk prediction model is determined.

[0032] Preferably, the feature extraction for each time window's physiological data segment includes:

[0033] Calculate the mean, standard deviation, and ratio of high-frequency to low-frequency components of heart rate variability within each time window.

[0034] Calculate the peak systolic blood pressure and the slope of diastolic blood pressure change during exercise within each time window;

[0035] Extract the ST segment depression or elevation values ​​of the electrocardiogram for each time window;

[0036] Based on patients' subjective fatigue scores, fatigue severity characteristics are generated.

[0037] The heart rate features, blood pressure features, ST segment features, and fatigue level features are combined to obtain the real-time physiological feature sequence.

[0038] Preferably, the calculation of the mean, standard deviation, and ratio of high-frequency to low-frequency components of heart rate variability within each time window is achieved using the following formula:

[0039] ;

[0040] ;

[0041] ;

[0042] in, The mean heart rate over the time window. For the i-th heart rate sample value, This represents the total number of sampling points within the time window. The standard deviation of heart rate within the time window; This represents the power ratio of the low-frequency to high-frequency components of heart rate variability. For low-frequency component power, This represents the power of the high-frequency component.

[0043] Preferably, the step of dynamically adjusting the initial training plan based on the real-time risk assessment results includes:

[0044] If the real-time risk assessment result is low risk, then the parameters in the initial training program remain unchanged;

[0045] If the real-time risk assessment result is medium risk, then reduce the exercise intensity and / or shorten the duration in the initial exercise program;

[0046] If the real-time risk assessment result is high risk, the current exercise is paused and a feedback instruction containing an emergency rest instruction is generated.

[0047] The risk assessment result is determined by comparing the risk probability output by the real-time risk prediction model with a preset risk threshold, which is pre-set based on the patient's disease type and cardiac function classification.

[0048] Preferably, the step of generating feedback instructions containing exercise guidance information and risk warning information based on the target exercise plan includes:

[0049] The target training program is analyzed to obtain the exercise type, intensity, duration, and rest interval of the current training cycle;

[0050] Based on the exercise type, intensity, duration, and rest interval, structured exercise guidance information is generated;

[0051] Obtain the current real-time risk assessment results, and generate corresponding risk warning information based on the real-time risk assessment results;

[0052] The exercise guidance information and the risk warning information are integrated according to a preset format to generate the feedback instruction.

[0053] In a second aspect of the invention, a smart monitoring exercise method suitable for clinical cardiovascular medicine is also provided, comprising:

[0054] Collect static physiological data, dynamic physiological data, and historical exercise data from patients with cardiovascular diseases;

[0055] Based on the static physiological data, dynamic physiological data, and historical exercise data, the patient's current exercise ability assessment result is generated through processing by a preset personalized exercise ability assessment model.

[0056] Based on the exercise capacity assessment results and in conjunction with a pre-defined disease type-exercise safety threshold database, an initial exercise plan for the patient is determined. The initial exercise plan includes at least the type of exercise, initial intensity, and duration.

[0057] During the patient's exercise, their dynamic physiological data are collected in real time, and the dynamic physiological data is processed by a real-time exercise risk prediction model to generate real-time risk assessment results.

[0058] Based on the real-time risk assessment results, at least one parameter in the initial training program is dynamically adjusted to generate a target training program.

[0059] Based on the target exercise program, a feedback instruction containing exercise guidance information and risk warning information is generated and sent to the patient's terminal.

[0060] Compared with existing technologies, this invention provides an intelligent monitoring and exercise system suitable for clinical cardiovascular medicine, which has the following beneficial effects:

[0061] This invention integrates patients' static physiological data, dynamic physiological data, and historical exercise data, and utilizes personalized exercise capacity assessment models and real-time exercise risk prediction models to achieve intelligent, dynamic, and personalized management of exercise programs for cardiovascular disease patients. It can not only generate scientific and safe initial exercise programs based on individual patient conditions, but also perceive physiological changes and predict potential risks in real time during exercise, and dynamically adjust program parameters. This ensures the effectiveness of exercise while minimizing the risk of exercise-induced cardiovascular events, significantly improving the safety, effectiveness, and compliance of patient exercise, and providing a more precise and intelligent solution for the clinical rehabilitation management of cardiovascular diseases. Attached Figure Description

[0062] Figure 1 This is a schematic diagram of the method flow of S101-S106 in this invention;

[0063] Figure 2 This is a schematic diagram of the method flow for S201-S205 in this invention;

[0064] Figure 3 This is a schematic diagram of the method flow for S301-S304 in this invention;

[0065] Figure 4 This is a schematic diagram of the method flow for S401-S405 in this invention;

[0066] Figure 5 This is a schematic diagram of the method flow of S501-S505 in this invention;

[0067] Figure 6 This is a schematic diagram of the method flow for S601-S603 in this invention. Detailed Implementation

[0068] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0069] Example 1

[0070] Please refer to Figure 1 As shown, in a first aspect of the present invention, a smart monitoring exercise method suitable for clinical cardiovascular medicine is provided, comprising:

[0071] S101. Collect static physiological data, dynamic physiological data, and historical exercise data of patients with cardiovascular diseases;

[0072] S102. Based on static physiological data, dynamic physiological data, and historical exercise data, the patient's current exercise ability assessment results are generated through a pre-set personalized exercise ability assessment model.

[0073] S103. Based on the results of the exercise capacity assessment and in conjunction with the pre-set disease type-exercise safety threshold database, determine the patient's initial exercise plan. The initial exercise plan shall at least include the type of exercise, initial intensity, and duration.

[0074] S104. During the patient's exercise, their dynamic physiological data are collected in real time, and the dynamic physiological data is processed by a real-time exercise risk prediction model to generate real-time risk assessment results.

[0075] S105. Based on the real-time risk assessment results, dynamically adjust at least one parameter in the initial training plan to generate a target training plan;

[0076] S106. Based on the target exercise plan, generate feedback instructions that include exercise guidance information and risk warning information, and send the feedback instructions to the patient's terminal.

[0077] Those skilled in the art will understand that this invention integrates patients' static physiological data, dynamic physiological data, and historical exercise data, and utilizes personalized exercise capacity assessment models and real-time exercise risk prediction models to achieve intelligent, dynamic, and personalized management of exercise programs for cardiovascular disease patients. It can not only generate scientific and safe initial exercise programs based on individual patient conditions, but also perceive physiological changes in real time during exercise, predict potential risks, and dynamically adjust program parameters. This ensures the effectiveness of exercise while minimizing the risk of exercise-induced cardiovascular events, significantly improving the safety, effectiveness, and compliance of patient exercise, and providing a more precise and intelligent solution for the clinical rehabilitation management of cardiovascular diseases.

[0078] Static physiological data include the patient's age, sex, height, weight, body fat percentage, resting heart rate, resting blood pressure, left ventricular ejection fraction, myocardial enzyme levels, and records of past cardiovascular events; dynamic physiological data include exercise heart rate, exercise blood pressure, blood oxygen saturation, ST segment changes on electrocardiogram, and the patient's subjective fatigue score; historical exercise data includes the patient's exercise type, frequency, duration, post-exercise heart rate recovery time, and records of adverse exercise events over the past 30 days.

[0079] Please refer to Figure 2 As shown, the methods for establishing a personalized athletic ability assessment model include:

[0080] S201. Obtain sample data from multiple cardiovascular disease patients. The sample data includes static physiological data, dynamic physiological data, historical exercise data, and labeled exercise ability levels.

[0081] S202. Preprocess the sample data, including missing value imputation, outlier removal and data normalization.

[0082] S203. Based on the preprocessed sample data, extract the feature set, which includes physiological characteristics, movement characteristics, and historical risk characteristics.

[0083] S204. Input the feature set into the initial classification model and train it through cross-validation to obtain a personalized sports ability assessment model.

[0084] S205. Validate the personalized sports ability assessment model based on an independent test set. When the model's assessment accuracy reaches a preset threshold, the personalized sports ability assessment model is determined.

[0085] Please refer to Figure 3 As shown, feature sets are extracted based on preprocessed sample data, including:

[0086] S301. Perform feature encoding on static physiological data to generate physiological feature vectors;

[0087] S302. Perform time-domain and frequency-domain analysis on dynamic physiological data to extract exercise physiological characteristics;

[0088] S303. Perform statistical analysis on historical exercise data to generate exercise compliance characteristics and exercise risk characteristics;

[0089] S304. The physiological feature vector, exercise physiological features, exercise compliance features, and exercise risk features are fused to obtain the feature set.

[0090] Please refer to Figure 4 As shown, the establishment of the real-time motion risk prediction model includes:

[0091] S401. Obtain real-time dynamic physiological data samples of patients with cardiovascular diseases and corresponding risk event annotations. Risk events include exercise-induced angina, arrhythmia, and abnormally high blood pressure.

[0092] S402. Perform sliding window segmentation on the real-time dynamic physiological data sample to generate physiological data segments with multiple time windows;

[0093] S403. Extract features from the physiological data segments of each time window to obtain a real-time physiological feature sequence;

[0094] S404. Input the real-time physiological feature sequence into the initial time series prediction model, and train it through the gradient descent algorithm to obtain the real-time motion risk prediction model.

[0095] S405. The real-time motion risk prediction model is updated online based on the real-time collected dynamic physiological data of the patient. When the risk prediction F1 value of the model reaches the preset threshold, the real-time motion risk prediction model is determined.

[0096] Please refer to Figure 5 As shown, feature extraction is performed on the physiological data segments of each time window, including:

[0097] S501. Calculate the mean, standard deviation, and ratio of high-frequency to low-frequency components of heart rate variability within each time window.

[0098] S502. Calculate the peak systolic blood pressure and the slope of diastolic blood pressure change during exercise in each time window;

[0099] S503. Extract the depression or elevation value of the ST segment of the electrocardiogram for each time window;

[0100] S504. Generate fatigue level characteristics based on patients' subjective fatigue scores;

[0101] S505. Combine heart rate characteristics, blood pressure characteristics, ST segment characteristics, and fatigue level characteristics to obtain a real-time physiological characteristic sequence.

[0102] The mean, standard deviation, and ratio of high-frequency to low-frequency components of heart rate variability within each time window are calculated using the following formula:

[0103] ;

[0104] ;

[0105] ;

[0106] in, The mean heart rate over the time window. For the i-th heart rate sample value, This represents the total number of sampling points within the time window. The standard deviation of heart rate within the time window; This represents the power ratio of the low-frequency to high-frequency components of heart rate variability. For low-frequency component power, This represents the power of the high-frequency component.

[0107] Please refer to Figure 6 As shown, the initial training plan is dynamically adjusted based on real-time risk assessment results, including:

[0108] S601. If the real-time risk assessment result is low risk, then keep the parameters in the initial training plan unchanged.

[0109] S602. If the real-time risk assessment result is medium risk, reduce the intensity and / or shorten the duration of exercise in the initial training program.

[0110] S603. If the real-time risk assessment result is high risk, pause the current exercise and generate a feedback instruction containing an emergency rest instruction.

[0111] The risk assessment results are determined by comparing the risk probability output by the real-time risk prediction model with a preset risk threshold, which is pre-set based on the patient's disease type and cardiac function classification.

[0112] Based on the target training plan, feedback instructions containing exercise guidance information and risk warning information are generated, including:

[0113] Analyze the target training program to obtain the exercise type, intensity, duration, and rest intervals for the current training cycle;

[0114] Based on exercise type, intensity, duration, and rest intervals, structured exercise guidance information is generated.

[0115] Obtain the current real-time risk assessment results and generate corresponding risk warning information based on the real-time risk assessment results;

[0116] Exercise guidance information and risk warning information are integrated according to a preset format to generate feedback instructions.

[0117] In a second aspect of the invention, an intelligent monitoring and exercise system suitable for clinical cardiovascular medicine is also provided, comprising:

[0118] The data acquisition module is used to collect static physiological data, dynamic physiological data, and historical exercise data of patients with cardiovascular diseases.

[0119] The first generation module is used to generate the patient's current exercise ability assessment result based on static physiological data, dynamic physiological data, and historical exercise data through a preset personalized exercise ability assessment model.

[0120] The determination module is used to determine the patient's initial exercise plan based on the results of the exercise ability assessment and in combination with a preset disease type-exercise safety threshold library. The initial exercise plan includes at least the type of exercise, initial intensity, and duration.

[0121] The risk assessment module is used to collect dynamic physiological data in real time during the patient's exercise, and to process the dynamic physiological data through a real-time exercise risk prediction model to generate real-time risk assessment results.

[0122] The second generation module is used to dynamically adjust at least one parameter in the initial training plan based on the real-time risk assessment results, and generate the target training plan.

[0123] The third generation module is used to generate feedback instructions containing exercise guidance information and risk warning information based on the target exercise plan, and send the feedback instructions to the patient terminal.

[0124] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent monitoring and exercise system suitable for clinical cardiovascular medicine, characterized in that, include: The acquisition module is used to collect static physiological data, dynamic physiological data, and historical exercise data of patients with cardiovascular diseases. The first generation module is used to generate the patient's current exercise ability assessment result based on the static physiological data, dynamic physiological data and historical exercise data through a preset personalized exercise ability assessment model. The determination module is used to determine the patient's initial exercise plan based on the exercise ability assessment results and in conjunction with a preset disease type-exercise safety threshold library. The initial exercise plan includes at least the type of exercise, initial intensity, and duration. The risk assessment module is used to collect dynamic physiological data in real time during the patient's exercise, and to process the dynamic physiological data through a real-time exercise risk prediction model to generate real-time risk assessment results. The second generation module is used to dynamically adjust at least one parameter in the initial training plan based on the real-time risk assessment results to generate a target training plan. The third generation module is used to generate feedback instructions containing exercise guidance information and risk warning information based on the target exercise program, and send the feedback instructions to the patient terminal.

2. The intelligent monitoring and exercise system suitable for clinical cardiovascular medicine as described in claim 1, characterized in that, The static physiological data includes the patient's age, gender, height, weight, body fat percentage, resting heart rate, resting blood pressure, left ventricular ejection fraction, myocardial enzyme levels, and records of past cardiovascular events; the dynamic physiological data includes exercise heart rate, exercise blood pressure, blood oxygen saturation, ST segment changes on electrocardiogram, and the patient's subjective fatigue score; the historical exercise data includes the patient's exercise type, frequency, duration, post-exercise heart rate recovery time, and records of adverse exercise events over the past 30 days.

3. The intelligent monitoring and exercise system suitable for clinical cardiovascular medicine as described in claim 2, characterized in that, The method for establishing the personalized athletic ability assessment model includes: Acquire sample data from multiple cardiovascular disease patients, including static physiological data, dynamic physiological data, historical exercise data, and labeled exercise ability levels. The sample data is preprocessed, including missing value imputation, outlier removal, and data normalization. Based on the preprocessed sample data, a feature set is extracted, which includes physiological features, movement features, and historical risk features. The feature set is input into the initial classification model, and a personalized sports ability assessment model is obtained through cross-validation training. The personalized athletic ability assessment model is validated based on an independent test set. When the model's assessment accuracy reaches a preset threshold, the personalized athletic ability assessment model is determined.

4. The intelligent monitoring and exercise system suitable for clinical cardiovascular medicine as described in claim 3, characterized in that, The extraction of feature sets based on preprocessed sample data includes: The static physiological data are feature-encoded to generate physiological feature vectors; The dynamic physiological data were analyzed in the time and frequency domains to extract the exercise physiological characteristics. Statistical analysis is performed on the historical exercise data to generate exercise compliance characteristics and exercise risk characteristics; The physiological feature vector, exercise physiological features, exercise compliance features, and exercise risk features are fused to obtain the feature set.

5. The intelligent monitoring and exercise system suitable for clinical cardiovascular medicine as described in claim 4, characterized in that, The establishment of the real-time motion risk prediction model includes: Real-time dynamic physiological data samples of cardiovascular disease patients and corresponding risk event annotations, including exercise-induced angina, arrhythmia and abnormally high blood pressure; The real-time dynamic physiological data sample is segmented by a sliding window to generate physiological data segments with multiple time windows; Feature extraction is performed on the physiological data segments of each time window to obtain a real-time physiological feature sequence; The real-time physiological feature sequence is input into the initial time series prediction model and trained using the gradient descent algorithm to obtain the real-time motion risk prediction model. The real-time motion risk prediction model is updated online based on real-time collected dynamic physiological data of patients. When the risk prediction F1 value of the model reaches a preset threshold, the real-time motion risk prediction model is determined.

6. The intelligent monitoring and exercise system suitable for clinical cardiovascular medicine as described in claim 5, characterized in that, The feature extraction for each time window's physiological data segment includes: Calculate the mean, standard deviation, and ratio of high-frequency to low-frequency components of heart rate variability within each time window. Calculate the peak systolic blood pressure and the slope of diastolic blood pressure change during exercise within each time window; Extract the ST segment depression or elevation values ​​of the electrocardiogram for each time window; Based on patients' subjective fatigue scores, fatigue severity characteristics are generated. The heart rate features, blood pressure features, ST segment features, and fatigue level features are combined to obtain the real-time physiological feature sequence.

7. The intelligent monitoring and exercise system suitable for clinical cardiovascular medicine as described in claim 6, characterized in that, The calculation of the mean, standard deviation, and ratio of high-frequency to low-frequency components of heart rate variability within each time window is achieved using the following formula: ； ； ； in, The mean heart rate over the time window. For the i-th heart rate sample value, This represents the total number of sampling points within the time window. The standard deviation of heart rate within the time window; This represents the power ratio of the low-frequency to high-frequency components of heart rate variability. For low-frequency component power, This represents the power of the high-frequency component.

8. The intelligent monitoring and exercise system suitable for clinical cardiovascular medicine as described in claim 7, characterized in that, The step of dynamically adjusting the initial training plan based on the real-time risk assessment results includes: If the real-time risk assessment result is low risk, then the parameters in the initial training program remain unchanged; If the real-time risk assessment result is medium risk, then reduce the exercise intensity and / or shorten the duration in the initial exercise program; If the real-time risk assessment result is high risk, the current exercise is paused and a feedback instruction containing an emergency rest instruction is generated. The risk assessment result is determined by comparing the risk probability output by the real-time risk prediction model with a preset risk threshold, which is pre-set based on the patient's disease type and cardiac function classification.

9. The intelligent monitoring and exercise system suitable for clinical cardiovascular medicine as described in claim 8, characterized in that, The step of generating feedback instructions based on the target training plan, including exercise guidance information and risk warning information, includes: The target training program is analyzed to obtain the exercise type, intensity, duration, and rest interval of the current training cycle; Based on the exercise type, intensity, duration, and rest interval, structured exercise guidance information is generated; Obtain the current real-time risk assessment results, and generate corresponding risk warning information based on the real-time risk assessment results; The exercise guidance information and the risk warning information are integrated according to a preset format to generate the feedback instruction.

10. A smart monitoring and exercise method suitable for clinical cardiovascular medicine, used to implement the smart monitoring and exercise system for clinical cardiovascular medicine as described in any one of claims 1-9, characterized in that, include: Collect static physiological data, dynamic physiological data, and historical exercise data from patients with cardiovascular diseases; Based on the static physiological data, dynamic physiological data, and historical exercise data, the patient's current exercise ability assessment result is generated through processing by a preset personalized exercise ability assessment model. Based on the exercise capacity assessment results and in conjunction with a pre-defined disease type-exercise safety threshold database, an initial exercise plan for the patient is determined. The initial exercise plan includes at least the type of exercise, initial intensity, and duration. During the patient's exercise, their dynamic physiological data are collected in real time, and the dynamic physiological data is processed by a real-time exercise risk prediction model to generate real-time risk assessment results. Based on the real-time risk assessment results, at least one parameter in the initial training program is dynamically adjusted to generate a target training program. Based on the target exercise program, a feedback instruction containing exercise guidance information and risk warning information is generated and sent to the patient's terminal.

Images