Diabetes exercise rehabilitation guidance system

Abstract

The invention relates to a diabetes exercise rehabilitation guidance system, relates to the technical field of diabetes rehabilitation, and aims to provide a personalized and scientific exercise management scheme for diabetics. The system comprises a user individual feature data acquisition module, an evaluation and classification module, an exercise scheme generation module, a real-time monitoring module and a feedback and adjustment module. By collecting the physiological parameters of the user in real time, the system automatically analyzes the health condition of the user and classifies the user into low-risk, medium-risk and high-risk exercise crowds. Based on a classification result, the system uses a machine learning algorithm to generate a personalized exercise scheme, and the safety of the exercise process is ensured through dynamic monitoring. The real-time monitoring module of the system can monitor the physiological data of the user in the exercise process and give an alarm in time when an abnormality is found. Through connection with an information system of a medical institution, the system also supports a remote medical function, so that doctors can check health data of patients in real time and provide professional guidance.

Description

Technical Field

[0001] The invention relates to the technical field of diabetes rehabilitation, in particular to a diabetes exercise rehabilitation guidance system. Background Art

[0002] Diabetes is a chronic metabolic disease that is prevalent worldwide, and its main feature is persistent hyperglycemia. According to statistics released by the International Diabetes Federation (IDF), there are currently about 463 million adults (18 years and above) suffering from diabetes worldwide, and this number is expected to increase to 700 million by 2045. This disease not only affects the quality of life of patients, but also imposes a huge burden on the public health system, especially in the management of diabetes-related complications, such as cardiovascular disease, kidney disease, retinopathy and neuropathy.

[0003] The main types of diabetes include type 1 diabetes and type 2 diabetes. Type 1 diabetes usually occurs in children or adolescents and is caused by autoimmune destruction of pancreatic beta cells, resulting in insufficient insulin secretion. Relatively speaking, type 2 diabetes is a more common type and is usually closely related to genetic factors, environmental factors, eating habits and lifestyle. Studies have shown that obesity, lack of exercise, and poor eating habits are all important risk factors for type 2 diabetes.

[0004] Exercise rehabilitation for diabetic patients is an important part of comprehensive management. Appropriate physical activity can not only improve insulin sensitivity and lower blood sugar levels, but also help lose weight, improve cardiovascular health and enhance mental health. However, many diabetic patients face a series of challenges when exercising, such as high exercise intensity may lead to hypoglycemia, lack of targeted exercise plans may lead to poor exercise effects, and may even cause sports injuries. Therefore, it is crucial for every diabetic patient to develop a personalized exercise rehabilitation plan.

[0005] Traditional diabetes exercise rehabilitation programs often have problems such as insufficient personalization and lack of real-time monitoring and feedback. Many patients choose their own exercise programs and intensities without professional guidance, which may lead to insignificant exercise effects or even health risks. At the same time, when formulating exercise programs for patients, medical staff usually rely on experience and lack scientific analysis based on data, making it impossible to achieve accurate personalized treatment.

[0006] In recent years, with the advancement of technology, especially the development of wearable devices, mobile health applications and big data analysis, the management model of diabetes exercise rehabilitation has changed significantly. Wearable devices can monitor users' physiological data in real time, including heart rate, blood sugar, number of steps and exercise intensity, which provides a new solution for exercise management of diabetic patients. Mobile health applications integrate health management, exercise plans and doctor feedback through a user-friendly interface, allowing patients to easily record and monitor their health status.

[0007] In this context, the diabetes exercise rehabilitation guidance system based on smart devices came into being. The system integrates multiple functions such as user information collection, data analysis, exercise program generation and real-time monitoring, aiming to provide personalized and scientific exercise guidance for diabetic patients. By analyzing the user's physiological parameters and living habits, the system can automatically generate an exercise plan suitable for the patient, and monitor physiological indicators in real time during exercise to ensure the safety and effectiveness of exercise.

[0008] In addition, the diabetes exercise rehabilitation guidance system using machine learning and artificial intelligence technology can extract patterns from large amounts of data, thereby continuously optimizing exercise plans. The system's evaluation and classification module can analyze the user's exercise data in real time, divide patients into exercise groups with different risk levels, and tailor exercise plans for them. At the same time, the introduction of the fuzzy calculation method can address the adaptability issues of exercise rehabilitation for diabetic patients, and conduct real-time monitoring and dynamic evaluation in combination with individual physical parameters and the hospital's diabetes management platform.

[0009] The diabetes exercise rehabilitation guidance system can not only help patients develop scientific exercise plans, but also provide patients with professional health management advice through real-time interaction with doctors with the support of telemedicine. Doctors can view patients' exercise records, blood sugar changes and other physiological data through the system, adjust treatment plans in a timely manner, and improve patients' exercise rehabilitation effects.

[0010] In short, as the incidence of diabetes continues to rise, exercise rehabilitation is particularly important in diabetes management. By building a diabetes exercise rehabilitation guidance system based on intelligent technology, we can effectively improve the patient's exercise rehabilitation effect, reduce the incidence of diabetes-related complications, and ultimately improve the patient's quality of life. This system can not only fill the gaps in traditional treatment methods, but also provide a new direction for future diabetes management.

[0011] To this end, we designed a diabetes exercise rehabilitation guidance system to solve the above problems. Summary of the invention

[0012] The purpose of the present invention is to provide a diabetes exercise rehabilitation guidance system to address the deficiencies of the prior art and to solve the problems raised in the background technology.

[0013] To achieve the above object, the present invention provides the following technical solution: a diabetes exercise rehabilitation guidance system, comprising the following modules:

[0014] Data acquisition module: used to obtain the user's physiological parameters in real time, including but not limited to resting heart rate HR rest , maximum heart rate HR max , blood sugar level BG, blood pressure BP, body mass index BMI and exercise steps;

[0015] Assessment and classification module: used to classify users into low-risk, medium-risk and high-risk sports groups based on their physiological parameters and medical history;

[0016] Exercise plan generation module: Generates personalized exercise plans based on the user's individual characteristics and classification results. The plans include exercise type, intensity, frequency and duration;

[0017] Real-time monitoring module: used to monitor the user's physiological state during exercise and provide timely feedback to ensure safety;

[0018] Feedback and adjustment module: used to dynamically adjust the exercise plan based on the user's real-time monitoring data and exercise effect evaluation results.

[0019] As a preferred technical solution of the present invention, the data acquisition module realizes automatic collection and uploading of user physiological data by combining a wearable device with a smartphone application.

[0020] As a preferred technical solution of the present invention, the evaluation and classification module adopts a machine learning algorithm to automatically identify the user's health risk level by analyzing the user's physiological data.

[0021] As a preferred technical solution of the present invention, the machine learning algorithm includes a decision tree, a random forest or a support vector machine, and is optimized through a training set.

[0022] As a preferred technical solution of the present invention, the exercise plan generation module generates personalized exercise intensity according to the following formula:

[0023] I=HR rest +(HR max -HR rest )×k

[0024] Where I is the target exercise intensity, HR rest is the resting heart rate, HR max is the maximum heart rate, and k is the individual adjustment coefficient.

[0025] As a preferred technical solution of the present invention, the exercise program generation module also uses the following formula to determine the weekly exercise frequency:

[0026]

[0027] Among them, F is the weekly exercise frequency, G is the target number of steps, T is the patient's daily activity time, α is the adaptability coefficient, C is the target blood glucose level, and B is the current blood glucose level.

[0028] As a preferred technical solution of the present invention, the real-time monitoring module includes heart rate monitoring, blood sugar monitoring and exercise status recording, and can immediately issue an alarm when abnormal heart rate or blood sugar of the user is detected.

[0029] As a preferred technical solution of the present invention, the feedback and adjustment module calculates the sports rehabilitation index according to the following formula:

[0030]

[0031] Among them, R is the motor rehabilitation index, w i is the weight of each physiological index, x i is the corresponding physiological parameter value.

[0032] As a preferred technical solution of the present invention, the weight of the exercise rehabilitation index is calculated by the following formula:

[0033]

[0034] Among them, V i is the evaluation value of the ith physiological index.

[0035] As a preferred technical solution of the present invention, the system can generate a user's exercise history record and perform trend prediction by analyzing the user's long-term data. The formula is as follows:

[0036] ΔBG=f(I,t)+∈

[0037] Among them, ΔBG is the change in blood sugar, f(I, t) is the functional relationship between exercise intensity I and exercise time t, ∈ is the error term.

[0038] As a preferred technical solution of the present invention, the user interface of the system is designed to be user-friendly, allowing users to view real-time physiological data, exercise records and health advice.

[0039] As a preferred technical solution of the present invention, the system can share data with the information system of a medical institution to achieve remote medical support and health management.

[0040] Compared with the prior art, the beneficial effect of the present invention is that the diabetes exercise rehabilitation guidance system collects the user's physiological data in real time, such as heart rate, blood sugar level and BMI, and combines individual characteristics to generate a personalized exercise plan using data analysis and machine learning technology. This personalized plan not only takes into account the user's health status and exercise preferences, but also can be dynamically adjusted according to real-time monitoring data to ensure the rationality of exercise intensity and frequency, thereby maximizing the exercise effect and helping patients to safely and effectively control their blood sugar levels.

[0041] The system has a real-time monitoring module that can monitor the user's physiological indicators in real time during exercise and issue an alarm in time when an abnormality occurs. This function ensures the safety of patients during exercise and reduces health risks caused by exercise. In addition, the system also provides instant feedback on exercise effects, and users can make timely adjustments based on feedback information to further enhance the effectiveness and safety of exercise.

[0042] The system supports connection with the information system of medical institutions, enabling data sharing and telemedicine support. Doctors can view patients' exercise records and physiological data in real time through the system, thereby providing more accurate health management suggestions. This remote interaction not only improves the communication efficiency between patients and doctors, but also enables timely adjustment of treatment plans, effectively reduces the risk of diabetes-related complications, and comprehensively improves patients' health management level and quality of life. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a structural block diagram of a diabetes exercise rehabilitation guidance system proposed by the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] The following is combined with Figure 1 With reference to the accompanying drawings and a number of embodiments, specific embodiments of the present invention are described in detail.

[0046] Example 1: Exercise rehabilitation program based on individual characteristics

[0047] User Information:

[0048] Age: 55

[0049] Gender: Male

[0050] History of diabetes: 10 years

[0051] Resting heart rate: 80 beats / minute

[0052] BMI: 28kg / m 2

[0053] Blood sugar level: 9.0mmol / L

[0054] Blood pressure: 135 / 85 mmHg

[0055] Exercise habits: Occasionally jogging

[0056] step:

[0057] Data collection: Users wear smart bracelets and upload data such as resting heart rate, blood sugar level and step count to the cloud database in real time via Bluetooth.

[0058] Assessment and classification: The system analyzes the user's physiological parameters and assesses the user's risk level using the following formula:

[0059]

[0060] Based on the user's evaluation results, they are classified as "medium-risk sports people".

[0061] Exercise plan generation: The exercise plan generation module generates personalized exercise plans based on the user's classification results and individual characteristics, including aerobic exercise and strength training. The calculation of exercise intensity is as follows:

[0062] I=HR rest +(HR max -HR rest )×k

[0063] The recommended regimen is aerobic exercise (such as brisk walking) 3 times a week, 30 minutes each time.

[0064] Real-time monitoring and feedback: When the user is exercising, the system monitors the heart rate and blood sugar data in real time. If the heart rate exceeds the set maximum value (such as 150 beats per minute), the system will immediately issue an alarm.

[0065] Feedback and adjustment: Based on the user's exercise feedback and exercise effect evaluation, the system will dynamically adjust the intensity and duration of the next exercise to ensure safe and effective exercise.

[0066] Example 2: Long-term monitoring and evaluation

[0067] User Information:

[0068] Age: 62

[0069] Gender: Female

[0070] History of diabetes: 20 years

[0071] Resting heart rate: 75 beats / minute

[0072] BMI: 30kg / m 2

[0073] Blood sugar level: 10.5mmol / L

[0074] Blood pressure: 140 / 90 mmHg

[0075] Exercise habits: Lack of exercise

[0076] step:

[0077] Data collection: Users regularly monitor their physiological data through wearable devices, and the system automatically synchronizes the user's examination results and medical advice information.

[0078] Evaluation and classification: The user’s physiological parameters are evaluated as “high-risk sports people” through algorithms.

[0079] The following formula is used to assess sports risk:

[0080] P = f(A, C, H)

[0081] Among them, P is the sports risk index, A is age, C is the complication situation, and H is the cardiopulmonary health status.

[0082] Exercise plan generation: Generate a suitable low-intensity exercise plan based on the user's health status and classification results. Recommended aerobic exercise includes brisk walking for 30 minutes a day, combined with simple strength training.

[0083] Real-time monitoring and feedback: The system monitors the user's heart rate and blood sugar in real time. If the heart rate is abnormal, the system will immediately issue an alarm and suggest that the user take necessary rest or adjust their diet. Feedback and adjustment: The system generates an exercise effect evaluation report every week, and dynamically adjusts the exercise plan based on blood sugar changes and user feedback to ensure personalized adaptation.

[0084] Example 3: Remote medical support system

[0085] User Information:

[0086] Age: 70

[0087] Gender: Male

[0088] History of diabetes: 25 years

[0089] Resting heart rate: 85 beats / minute

[0090] BMI: 32kg / m 2

[0091] Blood sugar level: 11.0mmol / L

[0092] Blood pressure: 150 / 95 mmHg

[0093] Exercise habits: occasionally participate in activities.

[0094] step:

[0095] Data collection: Through the link to the hospital information system, the system obtains the user's health data in real time, including the latest test results and doctor's advice.

[0096] Assessment and classification: The system conducts a health assessment on the user and classifies them as a “high-risk sports person”.

[0097] Use machine learning algorithms to dynamically analyze users' physiological data to improve classification accuracy.

[0098] Exercise plan generation: The exercise plan generation module formulates a personalized exercise plan suitable for the user and calculates the exercise rehabilitation index using the following formula:

[0099]

[0100] Among them, R is the motor rehabilitation index, w i is the weight of each physiological index, x i is the corresponding user parameter. Real-time monitoring and feedback: When the user is exercising, the system monitors and records the data in real time, and provides encouraging feedback when the user's heart rate reaches the target heart rate range.

[0101] Feedback and Adjustment: Through the telemedicine module, doctors can conduct video consultations with users, adjust exercise plans based on real-time data, and provide health management advice.

[0102] Example 4: Comprehensive health management

[0103] User Information:

[0104] Age: 50

[0105] Gender: Female

[0106] History of diabetes: 8 years

[0107] Resting heart rate: 78 beats / minute

[0108] BMI:26kg / ㎡

[0109] Blood sugar level: 7.5mmol / L

[0110] Blood pressure: 125 / 80 mmHg

[0111] Exercise habits: 3 times a week

[0112] step:

[0113] Data collection: Users monitor their heart rate, blood sugar and steps in real time through smart bracelets and mobile phone applications, and synchronize them to the cloud regularly.

[0114] Exercise plan generation: Users monitor their heart rate, blood sugar and steps in real time through smart bracelets and mobile phone applications, and synchronize them to the cloud regularly.

[0115] Assessment and classification: The system assesses the user as a "medium-risk sports person" based on their physiological data. The user classification is dynamically updated by regularly monitoring changes in blood sugar levels.

[0116] The exercise program generated by the exercise program generation module includes 3 aerobic exercises (such as cycling) and 2 strength training sessions per week.

[0117] Real-time monitoring and feedback: While the user is exercising, the system monitors and records data in real time and immediately issues an alarm when abnormal indicators are detected.

[0118] Feedback and adjustment: After the user completes the exercise, the system generates an exercise effect evaluation report, analyzes blood sugar change trends, and gives personalized diet and exercise recommendations.

[0119] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in the field. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A diabetes exercise rehabilitation guidance system, characterized in that: Contains the following modules: Data acquisition module: used to obtain the user's physiological parameters in real time, including but not limited to resting heart rate HR rest , maximum heart rate HR max , blood sugar level BG, blood pressure BP, body mass index BMI and exercise steps; Assessment and classification module: used to classify users into low-risk, medium-risk and high-risk sports groups based on their physiological parameters and medical history; Exercise plan generation module: Generates personalized exercise plans based on the user's individual characteristics and classification results. The plans include exercise type, intensity, frequency and duration; Real-time monitoring module: used to monitor the user's physiological state during exercise and provide timely feedback to ensure safety; Feedback and adjustment module: used to dynamically adjust the exercise plan based on the user's real-time monitoring data and exercise effect evaluation results.

2. The diabetes exercise rehabilitation guidance system according to claim 1, characterized in that: The data acquisition module combines the wearable device with the smartphone application to achieve automatic collection and uploading of the user's physiological data.

3. The diabetes exercise rehabilitation guidance system according to claim 1, characterized in that: The assessment and classification module uses a machine learning algorithm to automatically identify the user's health risk level by analyzing the user's physiological data.

4. The diabetes exercise rehabilitation guidance system according to claim 3, characterized in that: The machine learning algorithms include decision trees, random forests or support vector machines, and are optimized using a training set.

5. The diabetes exercise rehabilitation guidance system according to claim 1, characterized in that: The exercise program generation module generates personalized exercise intensity according to the following formula: I=HR rest +(HR max -HR rest )×k Where I is the target exercise intensity, HR rest is the resting heart rate, HR max is the maximum heart rate, and k is the individual adjustment coefficient.

6. The diabetes exercise rehabilitation guidance system according to claim 5, characterized in that: The exercise program generation module also uses the following formula to determine the weekly exercise frequency: Among them, F is the weekly exercise frequency, G is the target number of steps, T is the patient's daily activity time, α is the adaptability coefficient, C is the target blood glucose level, and B is the current blood glucose level.

7. The diabetes exercise rehabilitation guidance system according to claim 1, characterized in that: The real-time monitoring module includes heart rate monitoring, blood sugar monitoring and exercise status recording.

8. The diabetes exercise rehabilitation guidance system according to claim 1, characterized in that: The feedback and adjustment module calculates the exercise rehabilitation index according to the following formula: Among them, R is the motor rehabilitation index, w i is the weight of each physiological index, x i is the corresponding physiological parameter value.

9. The diabetes exercise rehabilitation guidance system according to claim 8, characterized in that: The weight of the exercise rehabilitation index is calculated by the following formula: Among them, V i is the evaluation value of the ith physiological index.

10. The diabetes exercise rehabilitation guidance system according to any one of claims 1 to 9, characterized in that: The system can generate a user's sports history record and make trend predictions by analyzing the user's long-term data. The formula is as follows: ΔBG=f(I,t)+∈ Among them, ΔBG is the change in blood sugar, f(I,t) is the functional relationship between exercise intensity I and exercise time t, and ∈ is the error term.

Images