Nursing remote monitoring system for cardiovascular medicine department

Abstract

The invention discloses a cardiovascular medicine nursing remote monitoring system, and relates to the field of medical information technology and remote medical technology, the cardiovascular medicine nursing remote monitoring system comprises a remote electrocardio monitoring center, the remote electrocardio monitoring center is in communication connection with a cardiovascular data acquisition module, a cardiovascular risk prediction module and a cardiovascular health visualization module; the cardiovascular data acquisition module collects physiological data through a wearable sensor, the cardiovascular risk prediction module predicts the cardiovascular disease risk by using an elastic network regression analysis model and provides personalized suggestions, and the cardiovascular health visualization module displays the health trend and updates cloud data in real time. According to the remote nursing monitoring system for the cardiovascular medicine department, through real-time monitoring and data analysis, the precision and efficiency of cardiovascular disease management are improved, optimal configuration of medical resources is promoted, individuation and continuity of health management of patients are enhanced, communication and cooperation among medical teams are enhanced, and the medical management efficiency is improved. And higher-quality remote medical service is provided for the patient.

Description

Technical Field

[0001] The present invention relates to the fields of medical information technology and telemedicine technology, and in particular to a cardiovascular medicine nursing remote monitoring system. Background Art

[0002] Cardiovascular medicine nursing is a nursing work specifically for cardiovascular diseases, covering the treatment and rehabilitation of patients with cardiovascular diseases. Cardiovascular diseases include coronary heart disease, hypertension, arrhythmia, myocardial infarction, etc. These diseases often involve complex pathophysiological processes and require professional nursing to support the patient's rehabilitation. Cardiovascular medicine nursing is characterized by professionalism, technicality, risk and meticulousness. Nurses need to conduct a comprehensive assessment of the patient's condition and develop a personalized nursing plan, including condition observation, medication nursing, symptomatic nursing, rehabilitation guidance, etc. Condition observation includes monitoring of vital signs, observation of symptoms such as chest pain and palpitations, and observation of signs such as edema and peripheral circulation. Medication nursing requires nurses to be proficient in the dosage, method, effect and side effects of commonly used cardiovascular drugs, and to use drugs rationally according to the condition and pharmacology.

[0003] In order to solve the limitations of cardiovascular medicine nursing in real-time monitoring and analysis of patients' physiological data, the existing technology uses traditional manual monitoring and regular data collection. However, this method is not only inefficient, but also prone to inaccurate data recording and omission of key information, which makes it difficult for doctors to grasp the changes in patients' conditions in a timely and comprehensive manner, affecting the formulation and adjustment of treatment plans. In the process of cardiovascular medicine nursing, the patient's physiological data such as age, heart rate, blood pressure, etc. are important bases for evaluating the condition and formulating nursing measures. However, due to the limitations of manual monitoring, it is often impossible to achieve real-time monitoring and accurate analysis of these data, which affects the nursing effect. Therefore, in order to overcome the shortcomings of the existing technology, a remote monitoring system for cardiovascular medicine nursing is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a cardiovascular medicine nursing remote monitoring system to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: a remote monitoring system for cardiovascular internal medicine nursing, comprising a remote electrocardiogram monitoring center, wherein the remote electrocardiogram monitoring center is communicatively connected to a cardiovascular data acquisition module, a cardiovascular risk prediction module and a cardiovascular health visualization module;

[0006] The cardiovascular data acquisition module collects the patient's physiological data through a wearable sensor;

[0007] The cardiovascular risk prediction module constructs an elastic network regression analysis model, uses historical physiological data to learn and adjust model parameters, predicts the patient's cardiovascular disease risk score, and provides personalized treatment recommendations as needed;

[0008] The cardiovascular health visualization module constructs a visualization interface to display a patient's health status change trend chart, establishes a communication mechanism, updates patient information in a cloud database in real time, provides data reports, and supports collaborative communication between medical teams in multiple locations.

[0009] A further improvement of the technical solution of the present invention is that: in the cardiovascular data acquisition module, the process of collecting the patient's physiological data through the wearable sensor includes:

[0010] A heart rate sensor is worn on the patient's chest, and the changes in light absorption caused by blood flow are measured through photoplethysmography, the intensity of reflected light is detected, and the periodic changes in light absorption are analyzed to calculate the resting heart rate;

[0011] A blood pressure sensor is worn on the patient's upper arm, and the blood pressure is measured using the oscillometer method. The pressure fluctuation signal is recorded, and the systolic and diastolic blood pressure values ​​are obtained by analyzing the pressure fluctuation signal.

[0012] A further improvement of the technical solution of the present invention is that: in the cardiovascular data acquisition module, the process of preprocessing the acquired physiological data includes:

[0013] The collected resting heart rate and blood pressure data were denoised, and the denoising process included using a low-pass filter with a cutoff frequency of 5 Hz to filter out noise higher than the heart rate frequency, retaining the low-frequency heartbeat signal, using a moving average filter to smooth the pressure fluctuation signal, calculating the average value of five consecutive blood pressure sampling points as the new sampling point, and using the mean of the adjacent samples before and after to replace the abnormal values ​​in the heart rate and blood pressure data.

[0014] A further improvement of the technical solution of the present invention is that: in the cardiovascular data acquisition module, based on the physiological conditions of children of different age groups, the process of extracting features from the pre-processed physiological data includes:

[0015] The heart rate, systolic pressure and diastolic pressure are extracted as the main features, and the calculation process is as follows:

[0016] ;

[0017] ;

[0018] ;

[0019] Among them, N is the number of heartbeat peaks detected within a period of time, and the time interval is T seconds. and are the maximum and minimum pressure values, is the pressure fluctuation amplitude, and is a constant determined from the calibration of the device;

[0020] Threshold ranges for resting heart rate, systolic blood pressure and diastolic blood pressure are set for preschool children aged 3-5 years and school-age children aged 6-12 years respectively. If the physiological data collected from children of different age groups exceeds the corresponding normal range, the physiological data is considered abnormal and there is a risk of cardiovascular disease.

[0021] A further improvement of the technical solution of the present invention is that: in the cardiovascular risk prediction module, the elastic network regression analysis model is defined, and the process of setting the regularization parameters includes:

[0022] An elastic network regression analysis model was constructed to obtain preprocessed physiological data from the cardiovascular data acquisition module, including children's age, heart rate, systolic blood pressure, and diastolic blood pressure as input features of the elastic network regression analysis model. A risk score label for cardiovascular disease was assigned to each sample, and standardized so that features of different scales had the same weight.

[0023] Define cardiovascular disease risk score as the target variable, child age, heart rate, systolic blood pressure, and diastolic blood pressure as independent variables, and the objective function of elastic net regression is:

[0024] ;

[0025] Among them, MSE is the mean square error loss function, is the regularization strength parameter, is the mixing parameter, are the coefficients of the elastic network regression analysis model;

[0026] Initialize the regularization strength parameters and mixing parameters, perform hyperparameter tuning through grid search, use K-fold cross validation to evaluate the performance of the elastic network regression analysis model under different parameter combinations, calculate the average performance index, and select the optimal parameter combination.

[0027] A further improvement of the technical solution of the present invention is that in the cardiovascular risk prediction module, the process of training and evaluating the elastic network regression analysis model includes:

[0028] Fit the elastic net regression model to the training dataset and use gradient descent to minimize the objective function to find the parameter value that minimizes the loss , the calculation process is as follows:

[0029] ;

[0030] in, is the value of the current parameter j, is the learning rate, represents the rate of change of the loss function at the current parameter value, Represents an assignment symbol;

[0031] The test data set is used to calculate the performance indicators of the model, including mean square error and determination coefficient, to check the selection effect of input features.

[0032] A further improvement of the technical solution of the present invention is that: in the cardiovascular risk prediction module, the process of importing new data into the elastic network regression analysis model to predict the cardiovascular disease risk scores of preschool children and school-age children respectively includes:

[0033] Use the trained model to predict new patient data, import the newly collected resting heart rate, systolic blood pressure, and diastolic blood pressure data into the elastic network regression analysis model, and output the corresponding cardiovascular disease risk score. The calculation process is as follows:

[0034] ;

[0035] in, is the input feature vector for a new patient, is the value of the current parameter j, To create a risk score for cardiovascular disease.

[0036] A further improvement of the technical solution of the present invention is that: in the cardiovascular risk prediction module, the process of dividing the risk levels of cardiovascular disease risk scores for preschool children and school-age children includes:

[0037] The cardiovascular disease risk score for preschool children is divided into three stages: 0-21 points, 21-40 points, and 41-100 points. The cardiovascular disease risk score for school-age children is divided into three stages: 0-31 points, 31-60 points, and 61-100 points, corresponding to low risk, medium risk, and high risk levels respectively.

[0038] A further improvement of the technical solution of the present invention is that: in the cardiovascular risk prediction module, the process of providing personalized treatment suggestions according to the predicted level of cardiovascular disease includes:

[0039] If the prediction result of cardiovascular disease is low risk, only regular physical examinations, a balanced diet, keeping warm, avoiding infection, and maintaining a good living environment are required. If the prediction result is medium risk, the frequency of physical examinations for preschool children and school-age children should be increased to once every three months and once every four months respectively, and regular echocardiograms should be performed. If the prediction result is high risk, hospitalization for observation and emergency treatment are required, intensive care should be used to ensure the stability of the vital signs of the examinee, and medication should be used to control symptoms and surgical intervention should be performed.

[0040] A further improvement of the technical solution of the present invention is that in the cardiovascular health visualization module, a visualization interface is constructed, a communication mechanism is established, patient information in a cloud database is updated in real time, data reports are provided, and a process of supporting collaborative communication between medical teams at multiple locations includes:

[0041] Obtain preprocessed heart rate, systolic blood pressure and diastolic blood pressure data from the cardiovascular data acquisition module, and use the visualization tool Matplotlib to build a user interface, wherein the user interface includes a title bar, a navigation bar and a chart area, and draws line graphs of the change trends of heart rate, systolic blood pressure and diastolic blood pressure, respectively, to display the changes of various physiological parameters over time, cardiovascular disease risk scores, cardiovascular disease risk levels and corresponding treatment recommendations;

[0042] Establish a communication mechanism to upload the patient's data to the cloud database in real time, and regularly update and synchronize to generate data reports containing statistical indicators, such as the average, maximum, minimum and standard deviation of the collected data. It supports export to PDF format and provides sharing functions and instant messaging tools to enable medical team members in different locations to collaborate and communicate, and jointly monitor and manage the patient's health status.

[0043] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:

[0044] 1. The present invention provides a remote monitoring system for cardiovascular internal medicine nursing. Through the combination of a cardiovascular data acquisition module and a wearable sensor, it realizes the continuous and accurate acquisition of the patient's physiological data, greatly improves the timeliness and accuracy of data acquisition, and provides doctors with a more reliable basis for diagnosis.

[0045] 2. The present invention provides a remote monitoring system for cardiovascular internal medicine nursing. The cardiovascular risk prediction module uses an advanced elastic network regression analysis model, combined with the patient's historical physiological data, to accurately predict the cardiovascular disease risk score and provide personalized treatment recommendations, which helps doctors intervene in advance, reduce the patient's risk of disease, and improve treatment effects.

[0046] 3. The present invention provides a remote monitoring system for cardiovascular internal medicine nursing. The cardiovascular health visualization module constructs an intuitive visualization interface, which not only facilitates doctors to quickly understand the changing trends of patients' health conditions, but also significantly enhances the sharing and utilization of medical resources by real-time updating of cloud databases and supporting collaborative communication between medical teams in multiple locations, thereby promoting the overall improvement of medical standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0048] Figure 1 A block diagram of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 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 are within the scope of protection of the present invention.

[0050] Examples, such as Figure 1 As shown, the present invention provides a remote monitoring system for cardiovascular internal medicine nursing, including a remote electrocardiogram monitoring center, wherein the remote electrocardiogram monitoring center is communicatively connected to a cardiovascular data acquisition module, a cardiovascular risk prediction module, and a cardiovascular health visualization module;

[0051] The cardiovascular data acquisition module collects the patient's physiological data through a wearable sensor. A heart rate sensor is worn on the patient's chest. The light absorption change caused by blood flow is measured by photoelectric volumetric pulse wave recording, the intensity of reflected light is detected, and the periodic change of light absorption is analyzed to calculate the resting heart rate. A blood pressure sensor is worn on the patient's upper arm. The blood pressure is measured by an oscillometer method. The pressure fluctuation signal is recorded. The systolic and diastolic pressure values ​​are obtained by analyzing the pressure fluctuation signal. The collected resting heart rate and blood pressure data are denoised. The denoising process includes using a low-pass filter with a cutoff frequency of 5 Hz to filter out noise higher than the heart rate frequency, retaining low-frequency heart rate signals, using a moving average filter to smooth the pressure fluctuation signal, calculating the average of five consecutive blood pressure sampling points as a new sampling point, and using the mean of the adjacent samples before and after to replace the abnormal values ​​in the heart rate and blood pressure data. The number of heart beats per minute, systolic pressure and diastolic pressure are extracted as the main features. The calculation process is as follows:

[0052] ;

[0053] ;

[0054] ;

[0055] Among them, N is the number of heartbeat peaks detected within a period of time, and the time interval is T seconds. and are the maximum and minimum pressure values, is the pressure fluctuation amplitude, and It is a constant determined by the calibration of the equipment, which sets the threshold ranges of resting heart rate, systolic blood pressure and diastolic blood pressure for preschool children aged 3-5 years and school-age children aged 6-12 years. If the physiological data collected by children of different age groups exceeds the corresponding normal range, the physiological data is considered abnormal and there is a risk of cardiovascular disease;

[0056] Cardiovascular risk prediction module, builds an elastic network regression analysis model, uses historical physiological data to learn and adjust model parameters, predicts patients' cardiovascular disease risk scores, and provides personalized treatment recommendations as needed. The elastic network regression analysis model is built, and pre-processed physiological data is obtained from the cardiovascular data acquisition module, including children's age, heart rate, systolic blood pressure and diastolic blood pressure as input features of the elastic network regression analysis model. Each sample is given a corresponding risk score label for cardiovascular disease, and standardized so that features of different scales have the same weight. The cardiovascular disease risk score is defined as the target variable, and the child's age, heart rate, systolic blood pressure and diastolic blood pressure are independent variables. The objective function of the elastic network regression is:

[0057] ;

[0058] Among them, MSE is the mean square error loss function, is the regularization strength parameter, is the mixing parameter, Initialize the regularization strength parameter and the mixing parameter for the elastic net regression model coefficients, perform hyperparameter tuning through grid search, evaluate the performance of the elastic net regression model under different parameter combinations using K-fold cross validation, calculate the average performance index, select the best parameter combination, fit the elastic net regression model to the training data set, and use gradient descent to minimize the objective function to find the parameter value that minimizes the loss , the calculation process is as follows:

[0059] ;

[0060] in, is the value of the current parameter j, is the learning rate, represents the rate of change of the loss function at the current parameter value, Represents the assignment symbol. The performance indicators of the model are calculated using the test data set. The performance indicators include mean square error and determination coefficient. The selection effect of the input features is checked. The trained model is used to predict the new patient data. The newly collected resting heart rate, systolic blood pressure and diastolic blood pressure data are imported into the elastic network regression analysis model. The corresponding cardiovascular disease risk score is output. The calculation process is as follows:

[0061] ;

[0062] in, is the input feature vector for a new patient, is the value of the current parameter j, The risk scores for cardiovascular diseases are divided into three stages: 0-21 points, 21-40 points, and 41-100 points for preschool children, and 0-31 points, 31-60 points, and 61-100 points for school-age children, which correspond to low risk, medium risk, and high risk levels, respectively. If the predicted result of cardiovascular disease is low risk, only regular physical examinations, a balanced diet, keeping warm, avoiding infection, and maintaining a good living environment are required. If the predicted result is medium risk, the frequency of physical examinations for preschool children and school-age children should be increased to once every three months and once every four months, respectively, and echocardiograms should be performed regularly. If the predicted result is high risk, hospitalization for observation and emergency treatment are required, intensive care should be provided to ensure the stability of the vital signs of the subjects, and drugs should be used to control symptoms and surgical interventions should be performed.

[0063] The cardiovascular health visualization module builds a visualization interface to display the patient's health status change trend chart, establishes a communication mechanism, updates the patient information in the cloud database in real time, provides data reports, supports collaborative communication between medical teams in multiple locations, obtains pre-processed heart rate, systolic blood pressure and diastolic blood pressure data from the cardiovascular data acquisition module, and uses the visualization tool Matplotlib to build a user interface. The user interface includes a title bar, a navigation bar and a chart area, and draws line charts of the change trend of heart rate, systolic blood pressure and diastolic blood pressure respectively, showing the changes of various physiological parameters over time, cardiovascular disease risk scores, cardiovascular disease risk levels and corresponding treatment recommendations. A communication mechanism is established to upload the patient's data to the cloud database in real time, and regularly synchronizes and updates to generate data reports containing statistical indicators. The statistical indicators include the mean, maximum, minimum and standard deviation of the collected data, support export to PDF format, provide sharing functions and instant messaging tools, so that medical team members in different locations can collaborate and communicate to jointly monitor and manage the patient's health status.

[0064] First, the patient needs to wear a dedicated wearable sensor that can collect the patient's heart rate, blood pressure and other physiological data in real time, and transmit this data wirelessly to the remote ECG monitoring center. Subsequently, the cardiovascular data acquisition module of the remote ECG monitoring center receives and stores this data. Next, the cardiovascular risk prediction module uses the stored historical physiological data to predict the patient's cardiovascular disease risk through the constructed elastic network regression analysis model and generates a corresponding risk score. Based on the risk score, the system will provide personalized treatment recommendations for doctors' reference. Finally, the cardiovascular health visualization module will build an intuitive visualization interface to display the patient's health status change trend chart, through which doctors and other medical team members can view the patient's health data in real time. At the same time, the system will also update the patient's information in the cloud database in real time and provide data reports to support collaborative communication between medical teams in multiple locations, and jointly provide patients with high-quality care services.

[0065] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A remote monitoring system for cardiovascular nursing, characterized by: It includes a remote ECG monitoring center, which is communicatively connected to a cardiovascular data acquisition module, a cardiovascular risk prediction module, and a cardiovascular health visualization module; The cardiovascular data acquisition module collects the patient's physiological data through a wearable sensor; The cardiovascular risk prediction module constructs an elastic network regression analysis model, uses historical physiological data to learn and adjust model parameters, predicts the patient's cardiovascular disease risk score, and provides personalized treatment recommendations as needed; The cardiovascular health visualization module constructs a visualization interface to display a patient's health status change trend chart, establishes a communication mechanism, updates patient information in a cloud database in real time, provides data reports, and supports collaborative communication between medical teams in multiple locations.

2. A cardiovascular nursing remote monitoring system according to claim 1, characterized in that: In the cardiovascular data acquisition module, the process of collecting the patient's physiological data through the wearable sensor includes: A heart rate sensor is worn on the patient's chest, and the changes in light absorption caused by blood flow are measured through photoplethysmography, the intensity of reflected light is detected, and the periodic changes in light absorption are analyzed to calculate the resting heart rate; A blood pressure sensor is worn on the patient's upper arm, and the blood pressure is measured using the oscillometer method. The pressure fluctuation signal is recorded, and the systolic and diastolic blood pressure values ​​are obtained by analyzing the pressure fluctuation signal.

3. A cardiovascular nursing remote monitoring system according to claim 2, characterized in that: In the cardiovascular data acquisition module, the process of preprocessing the collected physiological data includes: The collected resting heart rate and blood pressure data were denoised, and the denoising process included using a low-pass filter with a cutoff frequency of 5 Hz to filter out noise higher than the heart rate frequency and retain the low-frequency heart rate signal, using a moving average filter to smooth the pressure fluctuation signal, calculating the average value of five consecutive blood pressure sampling points as the new sampling point, and using the mean of the adjacent samples to replace the abnormal values ​​in the heart rate and blood pressure data.

4. A cardiovascular nursing remote monitoring system according to claim 3, characterized in that: In the cardiovascular data acquisition module, the process of extracting features from the pre-processed physiological data based on the physiological conditions of children of different age groups includes: The heart rate, systolic pressure and diastolic pressure are extracted as the main features, and the calculation process is as follows: ； ； ； Among them, N is the number of heartbeat peaks detected within a period of time, and the time interval is T seconds. and are the maximum and minimum pressure values, is the pressure fluctuation amplitude, and is a constant determined from the calibration of the device; Threshold ranges for resting heart rate, systolic blood pressure and diastolic blood pressure are set for preschool children aged 3-5 years and school-age children aged 6-12 years respectively. If the physiological data collected from children of different age groups exceeds the corresponding normal range, the physiological data is considered abnormal and there is a risk of cardiovascular disease.

5. A cardiovascular nursing remote monitoring system according to claim 4, characterized in that: In the cardiovascular risk prediction module, the process of defining the elastic network regression analysis model and setting the regularization parameters includes: An elastic network regression analysis model was constructed to obtain preprocessed physiological data from the cardiovascular data acquisition module, including children's age, heart rate, systolic blood pressure, and diastolic blood pressure as input features of the elastic network regression analysis model. A risk score label for cardiovascular disease was assigned to each sample, and standardized so that features of different scales had the same weight. Define cardiovascular disease risk score as the target variable, child age, heart rate, systolic blood pressure, and diastolic blood pressure as independent variables, and the objective function of elastic net regression is: ； Among them, MSE is the mean square error loss function, is the regularization strength parameter, is the mixing parameter, are the coefficients of the elastic network regression analysis model; Initialize the regularization strength parameters and mixing parameters, perform hyperparameter tuning through grid search, use K-fold cross validation to evaluate the performance of the elastic network regression analysis model under different parameter combinations, calculate the average performance index, and select the optimal parameter combination.

6. A cardiovascular nursing remote monitoring system according to claim 5, characterized in that: In the cardiovascular risk prediction module, the process of training and evaluating the elastic network regression analysis model includes: Fit the elastic net regression model to the training dataset and use gradient descent to minimize the objective function to find the parameter value that minimizes the loss , the calculation process is as follows: ； in, is the value of the current parameter j, is the learning rate, represents the rate of change of the loss function at the current parameter value, Represents an assignment symbol; The test data set is used to calculate the performance indicators of the model, including mean square error and determination coefficient, to check the selection effect of input features.

7. A cardiovascular nursing remote monitoring system according to claim 6, characterized in that: In the cardiovascular risk prediction module, the process of importing new data into the elastic network regression analysis model to predict the cardiovascular disease risk scores of preschool children and school-age children respectively includes: Use the trained model to predict new patient data, import the newly collected resting heart rate, systolic blood pressure, and diastolic blood pressure data into the elastic network regression analysis model, and output the corresponding cardiovascular disease risk score. The calculation process is as follows: ； in, is the input feature vector for a new patient, is the value of the current parameter j, To create a risk score for cardiovascular disease.

8. A cardiovascular nursing remote monitoring system according to claim 7, characterized in that: In the cardiovascular risk prediction module, the process of grading the risk levels of cardiovascular disease risk scores for preschool children and school-age children includes: The cardiovascular disease risk score for preschool children is divided into three stages: 0-21 points, 21-40 points, and 41-100 points. The cardiovascular disease risk score for school-age children is divided into three stages: 0-31 points, 31-60 points, and 61-100 points, corresponding to low risk, medium risk, and high risk levels respectively.

9. A cardiovascular nursing remote monitoring system according to claim 8, characterized in that: In the cardiovascular risk prediction module, the process of providing personalized treatment suggestions according to the predicted level of cardiovascular disease includes: If the prediction result of cardiovascular disease is low risk, only regular physical examinations, a balanced diet, keeping warm, avoiding infection, and maintaining a good living environment are required. If the prediction result is medium risk, the frequency of physical examinations for preschool children and school-age children should be increased to once every three months and once every four months respectively, and regular echocardiograms should be performed. If the prediction result is high risk, hospitalization for observation and emergency treatment are required, intensive care should be used to ensure the stability of the vital signs of the examinee, and medication should be used to control symptoms and surgical intervention should be performed.

10. A cardiovascular nursing remote monitoring system according to claim 9, characterized in that: In the cardiovascular health visualization module, the process of constructing a visualization interface, establishing a communication mechanism, updating patient information in the cloud database in real time, providing data reports, and supporting collaborative communication between medical teams at multiple locations includes: Obtain preprocessed heart rate, systolic blood pressure and diastolic blood pressure data from the cardiovascular data acquisition module, and use the visualization tool Matplotlib to build a user interface, wherein the user interface includes a title bar, a navigation bar and a chart area, and draws line graphs of the change trends of heart rate, systolic blood pressure and diastolic blood pressure, respectively, to display the changes of various physiological parameters over time, cardiovascular disease risk scores, cardiovascular disease risk levels and corresponding treatment recommendations; Establish a communication mechanism to upload the patient's data to the cloud database in real time, and regularly update and synchronize to generate data reports containing statistical indicators, such as the average, maximum, minimum and standard deviation of the collected data. It supports export to PDF format and provides sharing functions and instant messaging tools to enable medical team members in different locations to collaborate and communicate, and jointly monitor and manage the patient's health status.

Images