Method for researching influence of lower limb movement on blood sugar of type II diabetes patient

Abstract

The invention discloses a method for researching the influence of lower limb movement on the blood sugar of a type II diabetes patient, and relates to the technical field of medical health. Comprising the following steps: S1, screening research objects: selecting patients diagnosed as T2DM; s2, CPET evaluation: performing CPET on the patient by using a professional cardiopulmonary exercise test system, and measuring cardiopulmonary function indexes of the patient, including anaerobic threshold and maximum oxygen uptake; individualized exercise intensity is formulated according to the data; s3, diet control: ensuring that the patient takes standardized breakfast before testing so as to reduce the influence of food intake on blood sugar fluctuation. According to the method, the patient is assessed in detail through the cardiopulmonary exercise test, the oxygen-free threshold, the maximum oxygen uptake and other key indexes are obtained, and the exercise intensity and mode meeting individual requirements can be formulated; according to blood glucose data and cardiopulmonary function indexes monitored in real time, the exercise scheme is dynamically adjusted, and reliability and safety are improved.

Description

Technical Field

[0001] The present invention relates to the field of medical health technology, and in particular to a method for studying the effect of lower limb exercise on blood sugar in patients with type II diabetes. Background Art

[0002] Type 2 diabetes is a common chronic metabolic disease, the pathophysiological characteristics of which are decreased insulin's ability to regulate glucose metabolism, accompanied by defective pancreatic β-cell function. Long-term hyperglycemia can lead to a variety of complications, such as cardiovascular disease and retinopathy. Therefore, developing effective blood sugar management strategies is crucial to improving patients' quality of life.

[0003] In recent years, exercise therapy has received increasing attention due to its positive effects on blood sugar control.

[0004] However, there is currently a lack of detailed research on individualized exercise programs, especially the evaluation of the immediate glucose-lowering effect of a single exercise session under safe conditions. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a research method for the effect of lower limb exercise on blood sugar in patients with type II diabetes.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A method for studying the effect of lower limb exercise on blood sugar in patients with type II diabetes, comprising the following steps:

[0008] S1: Research subject screening: patients diagnosed with T2DM were selected;

[0009] S2: CPET assessment: Use a professional cardiopulmonary exercise testing system to perform CPET on patients to measure their cardiopulmonary function indicators, including anaerobic threshold and maximum oxygen uptake; formulate individualized exercise intensity based on these data;

[0010] S3: Dietary control: Ensure that the patient eats a standardized breakfast before the test to reduce the impact of food intake on blood sugar fluctuations;

[0011] S4: Implementation of exercise plan: Based on the CPET results, develop an individualized exercise plan including exercise method, intensity and time; perform lower limb exercises according to the predetermined plan;

[0012] S5: Continuous blood glucose monitoring: continuously records the patient's blood glucose changes;

[0013] S6: Data analysis: The collected data include fasting blood glucose, postprandial peak blood glucose, blood glucose at the beginning and end of exercise, and lowest blood glucose before lunch; the difference and percentage of blood glucose changes at each time point are calculated, and ANOVA and paired sample t-test are performed to analyze the specific effects of exercise on blood glucose.

[0014] Preferably: in S2, the CPET evaluation specifically includes:

[0015] S21: Pre-assessment: Before the formal CPET assessment, basic health data, medication history, and previous exercise and disease history are collected;

[0016] S22: Formal CPET assessment: The assessment was performed using a standardized CPET protocol; participants underwent an exercise test of increasing intensity while continuously monitoring heart rate, blood pressure, respiratory rate, and oxygen saturation;

[0017] S23: Data Analysis and Reporting Phase: Preliminary data analysis is performed immediately after the test is completed to identify any abnormal reactions or indicators.

[0018] Preferably: in S3, the diet control specifically includes:

[0019] S31: Dietary planning: Develop a personalized diet plan based on the participant's health status, nutritional needs and preferences; the plan includes the total daily calorie intake, protein, fat and carbohydrate ratio and intake;

[0020] S32: Pre-meal blood glucose monitoring: Before each meal, participants use a blood glucose meter to measure their current blood glucose level and adjust the type and amount of food to be consumed based on the results;

[0021] S33: Dietary log record: Participants record dietary details every day, including food type, portion, meal time, and post-meal blood sugar changes.

[0022] Preferably, in S4, the implementation of the exercise plan specifically includes:

[0023] S41: Personalized exercise design: Design a specific exercise plan based on the CPET assessment results and individual needs, and specify the type, intensity, frequency and time of exercise;

[0024] S42: Warm up before exercise: Perform at least 5-10 minutes of warm-up before each exercise, including low-intensity aerobic exercise and dynamic stretching;

[0025] S43: Implementation of main exercise: Main exercise should be performed while the heart rate and exercise intensity are within the established target range, ensuring that the intensity and time specified in the personalized exercise prescription are achieved. During the exercise, heart rate, perceived exercise intensity and respiratory rate safety indicators are continuously monitored;

[0026] S44: Relaxation and recovery: After completing the main exercise, perform 5-10 minutes of cool-down activities and gradually reduce the intensity of exercise;

[0027] S45: Evaluation of post-exercise effects: By comparing blood sugar levels and cardiopulmonary function indicators before and after exercise, the impact of a single exercise session on blood sugar control and physical health status can be evaluated.

[0028] Preferably: in S6, the data analysis specifically includes:

[0029] S61: Data cleaning and preprocessing: Data cleaning and preprocessing are performed to eliminate possible erroneous readings and outliers to ensure the accuracy of downstream analysis;

[0030] S62: Statistical analysis: Perform detailed data analysis, including descriptive statistics, correlation analysis, and glycemic trend model construction;

[0031] S63: Visual display of results: Visually display the analysis results through charts and graphs;

[0032] S64: Personalized feedback report: Customize a personalized health report based on data analysis results.

[0033] Preferably, in S6, a random forest algorithm is used to perform data analysis, specifically including:

[0034] S61: Data preparation and preprocessing;

[0035] S62: Build a random forest model;

[0036] S621: Select a base learner: use a decision tree as a base learner and set parameters of the base learner;

[0037] S622: Ensemble strategy: Use the bagging strategy to generate multiple training subsets through the bootstrap method, each subset is used to train a decision tree model; combine the prediction results of all decision trees to improve the stability and generalization ability of the overall model;

[0038] S623: Model training: Train the random forest model on the labeled training data set and adjust the hyperparameters; use the cross-validation method to evaluate the performance of the model on different data sets;

[0039] S624: Model saving and loading: Save the trained random forest model to a file or database;

[0040] S63: Model evaluation and application.

[0041] Preferably: in said S61, data preparation and preprocessing specifically include:

[0042] Data collection: Continuous blood glucose data were collected from participants, including fasting, postprandial peak, and pre- and post-exercise blood glucose values;

[0043] Data cleaning: Check and process missing values ​​and outliers to ensure data integrity and accuracy; interpolate time series data to fill in missing blood sugar records;

[0044] Data standardization: Standardize continuous variables to eliminate the impact of different dimensions.

[0045] Preferably: the data preparation and preprocessing further includes:

[0046] Feature engineering: Construct new features based on medical knowledge, including dietary frequency, exercise intensity, and medication use; convert raw data into numerical data to facilitate model training.

[0047] Preferably, in S63, the model evaluation and application specifically includes:

[0048] Model evaluation indicators: Accuracy, recall, and F1 value indicators are used to comprehensively evaluate the performance of the model; the area under the ROC curve is calculated to evaluate the model's ability to distinguish between normal blood sugar and abnormal blood sugar;

[0049] Result visualization: Use graphical tools to display the model's prediction results and various indicators;

[0050] Clinical decision support: providing personalized health management recommendations and treatment plans based on the model’s prediction results;

[0051] Continuous optimization and updating: Regularly retrain and evaluate the model using the latest collected data to ensure the accuracy and timeliness of the model.

[0052] Preferably, in the model evaluation index, the classification effect of the model on different categories is analyzed by confusion matrix to identify the main reasons for misclassification.

[0053] The beneficial effects of the present invention are:

[0054] 1. The present invention conducts a detailed assessment of the patient through a cardiopulmonary exercise test to obtain key indicators such as anaerobic threshold and maximum oxygen uptake, and can formulate an exercise intensity and method that meets individual needs; according to real-time monitored blood sugar data and cardiopulmonary function indicators, the exercise plan is dynamically adjusted to improve reliability and safety.

[0055] 2. Through in-depth analysis of continuous blood glucose data, the present invention discovers hidden hyperglycemia and hypoglycemia that are not easily detected by traditional monitoring methods, which is helpful for early intervention and prevention of complications; combined with multiple evaluation indicators, the performance of the model is comprehensively evaluated from multiple angles to ensure the accuracy and reliability of the results. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of a research method for the effect of lower limb exercise on blood sugar in patients with type II diabetes proposed by the present invention. DETAILED DESCRIPTION

[0057] The technical solution of the present invention is further described in detail below in conjunction with specific implementation methods.

[0058] Embodiment 1:

[0059] A method for studying the effect of lower limb exercise on blood sugar in patients with type II diabetes, comprising the following steps:

[0060] S1: Research subject screening: patients diagnosed with T2DM were selected, and patients with acute cardiovascular and cerebrovascular diseases, infectious diseases, and other diseases who were not suitable for exercise were excluded;

[0061] S2: CPET assessment: Use a professional cardiopulmonary exercise testing system to perform CPET on patients to measure their cardiopulmonary function indicators, including anaerobic threshold, maximum oxygen uptake, etc.; formulate individualized exercise intensity based on these data;

[0062] S3: Dietary control: Ensure that the patient eats a standardized breakfast before the test to reduce the impact of food intake on blood sugar fluctuations;

[0063] S4: Implementation of exercise plan: Based on the CPET results, develop an individualized exercise plan including exercise method, intensity and time; use a medical-grade precision power bicycle to perform lower limb exercises according to the predetermined power and time;

[0064] S5: Continuous blood glucose monitoring: Use the continuous blood glucose monitoring (CGMS) system to continuously record the patient's blood glucose changes throughout the study period; focus on blood glucose levels before and after exercise and before lunch;

[0065] S6: Data analysis: The collected data include fasting blood glucose, postprandial peak blood glucose, blood glucose at the beginning and end of exercise, and lowest blood glucose before lunch; calculate the difference and percentage of blood glucose changes at each time point, and use statistical software (such as SPSS) to perform ANOVA and paired sample t-test to analyze the specific impact of exercise on blood glucose.

[0066] Among them, in S2, CPET assessment specifically includes:

[0067] S21: Pre-assessment: Before the formal CPET assessment, basic health data, medication history, and previous exercise and disease history are collected; in addition, a basic physical examination is performed, including measurement of blood pressure, heart rate, and recording of resting electrocardiogram;

[0068] S22: Formal CPET assessment: The assessment was performed using a standardized CPET protocol; participants underwent an exercise test of increasing intensity while continuously monitoring heart rate, blood pressure, respiratory rate, and oxygen saturation.

[0069] S23: Data Analysis and Reporting Phase: Preliminary data analysis is performed immediately after the test is completed to identify any abnormal reactions or indicators.

[0070] Wherein, in said S3, the dietary control specifically includes:

[0071] S31: Dietary planning: Develop a personalized diet plan based on the participant's health status, nutritional needs and preferences; the plan includes the total daily calorie intake, protein, fat and carbohydrate ratio and intake;

[0072] S32: Pre-meal blood glucose monitoring: Before each meal, participants use a blood glucose meter to measure their current blood glucose level to ensure that it is within the appropriate range and adjust the type and amount of food to be consumed based on the results;

[0073] S33: Dietary log record: Participants record dietary details every day, including food type, portion, meal time, and post-meal blood sugar changes.

[0074] Among them, in S4, the implementation of the exercise plan specifically includes:

[0075] S41: Personalized exercise design: Based on the CPET assessment results and individual needs, design a specific exercise plan to specify the type of exercise (such as aerobic exercise, resistance training), intensity (such as the percentage of maximum oxygen uptake), frequency (number of times per week) and duration (duration of each exercise);

[0076] S42: Warm up before exercise: Perform at least 5-10 minutes of warm-up before each exercise, including low-intensity aerobic exercise and dynamic stretching;

[0077] S43: Implementation of main exercise: Perform the main exercise while keeping the heart rate and exercise intensity within the established target range, ensuring that the intensity and time specified in the personalized exercise prescription are achieved. During the exercise, continuously monitor safety indicators such as heart rate, perceived exercise intensity, and respiratory rate;

[0078] S44: Relaxation and recovery: After completing the main exercise, perform 5-10 minutes of cool-down activities, gradually reduce the intensity of exercise, and perform static stretching exercises;

[0079] S45: Evaluation of post-exercise effects: By comparing blood sugar levels and cardiopulmonary function indicators before and after exercise, the impact of a single exercise session on blood sugar control and physical health status can be evaluated.

[0080] Among them, in S5, dynamic blood glucose monitoring specifically includes:

[0081] S51: Monitoring device placement: Select a continuous glucose monitoring device that is appropriate for the participant and ensure that it is properly installed on the designated part of the body;

[0082] S52: Daily data collection: The monitoring device collects blood glucose data in real time;

[0083] S53: Life event recording: Participants record daily life events such as diet, exercise, and medication in a specific diary or associated application. These data are synchronized with blood glucose data and used to analyze the relationship between blood glucose fluctuations and daily life.

[0084] Wherein, in said S6, data analysis specifically includes:

[0085] S61: Data cleaning and preprocessing: Data cleaning and preprocessing are performed to eliminate possible erroneous readings and outliers to ensure the accuracy of downstream analysis;

[0086] S62: Statistical analysis: Perform detailed data analysis, including but not limited to descriptive statistics, correlation analysis, and glycemic trend model construction;

[0087] S63: Visual display of results: Visually display the analysis results through charts and graphs;

[0088] S64: Personalized feedback report: Customize a personalized health report based on data analysis results.

[0089] Embodiment 2:

[0090] A method for studying the effect of lower limb exercise on blood sugar in patients with type II diabetes. Based on Example 1, in S6, a random forest algorithm is used for data analysis, specifically including:

[0091] S61: Data preparation and preprocessing;

[0092] S62: Build a random forest model;

[0093] S621: Select a base learner: use a decision tree as a base learner and set parameters of the base learner;

[0094] S622: Ensemble strategy: Use the bagging strategy to generate multiple training subsets through the bootstrap method, each subset is used to train a decision tree model; combine the prediction results of all decision trees to improve the stability and generalization ability of the overall model;

[0095] S623: Model training: Train the random forest model on the labeled training data set and adjust the hyperparameters to optimize the model performance; use the cross-validation method to evaluate the performance of the model on different data sets;

[0096] S624: Model saving and loading: Save the trained random forest model to a file or database;

[0097] S63: Model evaluation and application.

[0098] Among them, in said S61, data preparation and preprocessing specifically include:

[0099] Collect data: Collect participants' continuous blood glucose data, including fasting, post-meal peak, and blood glucose values ​​at key time points such as before and after exercise;

[0100] Data cleaning: Check and process missing values ​​and outliers to ensure data integrity and accuracy; interpolate time series data to fill in missing blood sugar records;

[0101] Feature engineering: construct new features based on medical knowledge, such as dietary frequency, exercise intensity, and medication use; convert raw data into numerical data to facilitate model training;

[0102] Data standardization: Standardize continuous variables to eliminate the impact of different dimensions and improve model training efficiency and prediction accuracy.

[0103] Among them, in S63, the model evaluation and application specifically includes:

[0104] Model evaluation indicators: Use accuracy, recall, F1 value and other indicators to comprehensively evaluate the performance of the model; calculate the area under the ROC curve to evaluate the model's ability to distinguish between normal blood sugar and abnormal blood sugar; analyze the classification effect of the model on different categories through the confusion matrix to identify the main reasons for misclassification;

[0105] Result visualization: Use graphical tools to display the model's prediction results and various indicators, and use visualization methods such as heat maps and box plots to reveal the impact of different characteristics on blood sugar control;

[0106] Clinical decision support: Based on the model's prediction results, personalized health management advice and treatment plans are provided; for example, recommendations on strengthening exercise and adjusting diet are made for high-risk groups; for low-risk groups, the importance of maintaining the current lifestyle is emphasized;

[0107] Continuous optimization and updating: Regularly retrain and evaluate the model using the latest collected data to ensure the accuracy and timeliness of the model.

[0108] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for studying the effect of lower limb exercise on blood sugar in patients with type II diabetes, comprising: The steps include: S1: Research subject screening: patients diagnosed with T2DM were selected; S2: CPET assessment: Use a professional cardiopulmonary exercise testing system to perform CPET on patients to measure their cardiopulmonary function indicators, including anaerobic threshold and maximum oxygen uptake; Develop individualized exercise intensity based on these data; S3: Dietary control: Ensure that the patient eats a standardized breakfast before the test to reduce the impact of food intake on blood sugar fluctuations; S4: Implementation of exercise plan: Based on the CPET results, develop an individualized exercise plan including exercise method, intensity and time; perform lower limb exercises according to the predetermined plan; S5: Continuous blood glucose monitoring: continuously records the patient's blood glucose changes; S6: Data analysis: The collected data include fasting blood glucose, postprandial peak blood glucose, blood glucose at the beginning and end of exercise, and lowest blood glucose before lunch; the difference and percentage of blood glucose changes at each time point are calculated, and ANOVA and paired sample t-test are performed to analyze the specific effects of exercise on blood glucose.

2. The research method of the effect of lower limb exercise on blood sugar in patients with type II diabetes according to claim 1, characterized in that: In S2, CPET assessment specifically includes: S21: Pre-assessment: Before the formal CPET assessment, basic health data, medication history, and previous exercise and disease history are collected; S22: Formal CPET assessment: The assessment was performed using a standardized CPET protocol; participants underwent an exercise test of increasing intensity while continuously monitoring heart rate, blood pressure, respiratory rate, and oxygen saturation; S23: Data Analysis and Reporting Phase: Preliminary data analysis is performed immediately after the test is completed to identify any abnormal reactions or indicators.

3. The research method of the effect of lower limb exercise on blood sugar in patients with type II diabetes according to claim 1, characterized in that: In S3, the dietary control specifically includes: S31: Dietary planning: Develop a personalized diet plan based on the participant's health status, nutritional needs and preferences; the plan includes the total daily calorie intake, protein, fat and carbohydrate ratio and intake; S32: Pre-meal blood glucose monitoring: Before each meal, participants use a blood glucose meter to measure their current blood glucose level and adjust the type and amount of food to be consumed based on the results; S33: Dietary log record: Participants record dietary details every day, including food type, portion, meal time, and post-meal blood sugar changes.

4. The research method of the effect of lower limb exercise on blood sugar in patients with type II diabetes according to claim 3, characterized in that: In S4, the implementation of the exercise plan specifically includes: S41: Personalized exercise design: Design a specific exercise plan based on the CPET assessment results and individual needs, and specify the type, intensity, frequency and time of exercise; S42: Warm up before exercise: Perform at least 5-10 minutes of warm-up before each exercise, including low-intensity aerobic exercise and dynamic stretching; S43: Implementation of main exercise: Main exercise should be performed while the heart rate and exercise intensity are within the established target range, ensuring that the intensity and time specified in the personalized exercise prescription are achieved. During the exercise, heart rate, perceived exercise intensity and respiratory rate safety indicators are continuously monitored; S44: Relaxation and recovery: After completing the main exercise, perform 5-10 minutes of cool-down activities and gradually reduce the intensity of exercise; S45: Evaluation of post-exercise effects: By comparing blood sugar levels and cardiopulmonary function indicators before and after exercise, the impact of a single exercise session on blood sugar control and physical health status can be evaluated.

5. The research method of the effect of lower limb exercise on blood sugar in patients with type II diabetes according to claim 1, characterized in that: In S6, data analysis specifically includes: S61: Data cleaning and preprocessing: Data cleaning and preprocessing are performed to eliminate possible erroneous readings and outliers to ensure the accuracy of downstream analysis; S62: Statistical analysis: Perform detailed data analysis, including descriptive statistics, correlation analysis, and glycemic trend model construction; S63: Visual display of results: Visually display the analysis results through charts and graphs; S64: Personalized feedback report: Customize a personalized health report based on data analysis results.

6. The research method of the effect of lower limb exercise on blood sugar in patients with type II diabetes according to claim 1, characterized in that: In S6, a random forest algorithm is used to perform data analysis, specifically including: S61: Data preparation and preprocessing; S62: Build a random forest model; S621: Select a base learner: use a decision tree as a base learner and set parameters of the base learner; S622: Ensemble strategy: Use the bagging strategy to generate multiple training subsets through the bootstrap method, each subset is used to train a decision tree model; combine the prediction results of all decision trees to improve the stability and generalization ability of the overall model; S623: Model training: Train the random forest model on the labeled training data set and adjust the hyperparameters; use the cross-validation method to evaluate the performance of the model on different data sets; S624: Model saving and loading: Save the trained random forest model to a file or database; S63: Model evaluation and application.

7. A method for studying the effect of lower limb exercise on blood sugar in patients with type II diabetes according to claim 6, characterized in that: In S61, data preparation and preprocessing specifically include: Data collection: Continuous blood glucose data were collected from participants, including fasting, postprandial peak, and pre- and post-exercise blood glucose values; Data cleaning: Check and process missing values ​​and outliers to ensure data integrity and accuracy; interpolate time series data to fill in missing blood sugar records; Data standardization: Standardize continuous variables to eliminate the impact of different dimensions.

8. The method for studying the effect of lower limb exercise on blood sugar in patients with type II diabetes according to claim 7, characterized in that: The data preparation and preprocessing also include: Feature engineering: Construct new features based on medical knowledge, including dietary frequency, exercise intensity, and medication use; convert raw data into numerical data to facilitate model training.

9. The method for studying the effect of lower limb exercise on blood sugar in patients with type II diabetes according to claim 7, characterized in that: In S63, the model evaluation and application specifically includes: Model evaluation indicators: Accuracy, recall, and F1 value indicators are used to comprehensively evaluate the performance of the model; the area under the ROC curve is calculated to evaluate the model's ability to distinguish between normal blood sugar and abnormal blood sugar; Result visualization: Use graphical tools to display the model's prediction results and various indicators; Clinical decision support: providing personalized health management recommendations and treatment plans based on the model’s prediction results; Continuous optimization and updating: Regularly retrain and evaluate the model using the latest collected data to ensure the accuracy and timeliness of the model.

10. A method for studying the effect of lower limb exercise on blood sugar in patients with type II diabetes according to claim 9, characterized in that: Among the model evaluation indicators, the classification effect of the model on different categories is analyzed through the confusion matrix to identify the main reasons for misclassification.

Images