Venous thromboembolism prevention exercise monitoring and guidance system based on cloud data interaction

Abstract

This invention discloses a cloud-based data interaction-based exercise monitoring and guidance system for venous thrombosis prevention, belonging to the field of medical and health technology. It includes a patient-side app for exercise monitoring, incentive feedback, intelligent error correction and guidance, and flexible reminders; a nurse-side app for patient risk stratification, personalized intervention plan generation, and closed-loop data management; a cloud server for data storage, processing, and analysis, and supports multi-terminal data synchronization and sharing; and a wearable device integrating high-precision sensors. This invention constructs a multi-terminal data interaction architecture based on a cloud server, achieving an efficient and stable data synchronization mechanism between the patient-side app, nurse-side app, and wearable device. Data synchronization latency is extremely short, and data upload frequency is reasonable and efficient. This innovative design ensures that patient exercise data can flow smoothly and in real-time between all terminals, enabling nurses to obtain the latest patient exercise status information immediately.

Description

Technical Field

[0001] This invention relates to the field of medical and health technology, and in particular to a cloud-based data interaction-based exercise monitoring and guidance system for venous thrombosis prevention. Background Technology

[0002] Venous thromboembolism (VTE), a serious threat to patients' lives and health, encompasses deep vein thrombosis (DVT) and pulmonary thromboembolism (PTE), and has a high incidence and mortality rate in all clinical departments. With the increasing aging of the population and the rising prevalence of various chronic diseases, the prevention of venous thrombosis has become increasingly important and urgent.

[0003] Currently, traditional methods of venous thrombosis prevention primarily rely on manual assessment and guidance from healthcare professionals. These professionals assess thrombosis risk by regularly inquiring about patients' exercise patterns and checking their physical indicators, and then provide corresponding exercise recommendations. However, this method has several limitations. Firstly, the timeliness of manual assessment and guidance is poor; healthcare professionals cannot monitor patients' exercise status and physiological changes in real time, making it difficult to adjust prevention plans promptly. For example, insufficient exercise or abnormal physiological changes in patients at night or when healthcare professionals are not present may go undetected, increasing the risk of thrombosis. Secondly, traditional methods lack personalization, making it difficult to develop precise prevention strategies based on each patient's specific circumstances. Different patients have different physical conditions, exercise abilities, and disease characteristics; uniform exercise recommendations may not meet individual needs, affecting the effectiveness of prevention.

[0004] Furthermore, while existing motion monitoring devices can record patients' movement data, their data collection and transmission methods have shortcomings. Some devices can only store data locally, requiring patients to manually export and submit the data to medical staff, a cumbersome process prone to data loss or errors. Some devices with wireless transmission capabilities suffer from high latency and poor stability when synchronizing data with different terminals (such as mobile apps and hospital information systems). Delayed data synchronization leads to lag in patient information access for medical staff, hindering timely intervention decisions and impacting the effectiveness of venous thrombosis prevention.

[0005] Finally, active patient participation and long-term adherence are crucial in the exercise monitoring process for venous thrombosis prevention. However, existing exercise monitoring guidance systems often lack effective incentive mechanisms, making it difficult to motivate patients. Patients may lack motivation to exercise regularly as prescribed, leading to inaccurate exercise monitoring data and ineffective implementation of prevention programs. Furthermore, family members play a vital supportive role in patient recovery, but existing systems rarely consider family involvement, failing to establish a collaborative family-hospital prevention model, further reducing patient adherence. A cloud-based data interaction-based exercise monitoring guidance system for venous thrombosis prevention is needed.

[0006] To address this, we have developed a cloud-based exercise monitoring and guidance system for venous thrombosis prevention. Summary of the Invention

[0007] The purpose of this invention is to solve the problems in the prior art by proposing a cloud-based data interaction-based exercise monitoring and guidance system for venous thrombosis prevention.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: A cloud-based data interaction-based exercise monitoring and guidance system for venous thrombosis prevention includes: The patient-side app is used for motion monitoring, incentive feedback, intelligent error correction and guidance, and gentle reminders; The nurse-side app is used for patient risk stratification, generation of personalized intervention plans, and closed-loop data management. Cloud servers are used for data storage, processing, and analysis, and support multi-device data synchronization and sharing; Wearable devices integrate high-precision sensors to collect patients' motion data in real time and upload it to a cloud server, while also having an abnormal situation warning function.

[0009] Preferably, the patient-side APP further includes: A personalized incentive system, including a tiered achievement system, visualization of rehabilitation progress, and incentives involving family members, enhances patients' motivation to exercise through social recognition, tangible benefits, and family bonds. The intelligent error correction and guidance module includes real-time motion guidance animations and error motion playback analysis, which help patients correct their movements independently through voice prompts, screen displays, and comparison images.

[0010] Preferably, the patient-side APP further includes: The flexible reminder and scenario adaptation module automatically pushes exercise reminders based on the patient's daily routine and status through intelligent time period recommendation and multi-scenario reminder triggering, reducing intrusive reminders.

[0011] Preferably, the nurse-side app further includes: The patient risk stratification and priority reminder module automatically generates a three-color risk label based on the patient's exercise data over the past 3 days, and immediately triggers a high-priority reminder for patients with red risk. The personalized intervention plan generation module includes dynamically adjusting goals and recommending communication scripts, automatically generating targeted intervention plans based on the patient's movement data and type.

[0012] Preferably, the nurse-side APP further includes: The data closed-loop and management tool module includes an intervention effect tracking form and a department summary report, which records the nurses' intervention time and method and the changes in the patients' achievement rate after intervention, and automatically generates a daily report on the department's patients' exercise achievement rate.

[0013] Preferably, the patient-side APP further includes an emotion recognition and incentive adjustment module. This module integrates an emotion recognition algorithm to analyze the patient's voice, facial expressions, or operating habits to determine their emotional state and automatically adjust incentive strategies.

[0014] Preferably, the patient-side APP further includes a virtual reality guidance module, which integrates virtual reality technology to provide patients with an immersive exercise experience, thereby increasing their interest in and adherence to exercise.

[0015] Preferably, the nurse-side APP also includes an intelligent prediction and early warning module. This module, by integrating machine learning algorithms, predicts the risk of thrombosis in the future based on the patient's historical exercise data and physiological indicators, and issues an early warning.

[0016] Preferably, the nurse-side APP also includes a multimodal interaction module, which supports communication in various forms such as voice, text, and images, thereby improving the efficiency and accuracy of doctor-patient communication.

[0017] Preferably, the wearable device further includes an abnormal situation warning module. This module integrates high-precision sensors and abnormal detection algorithms to monitor the patient's movement status in real time. When abnormal ankle vibration or a sudden increase in heart rate is detected, the exercise is immediately paused and a reminder is sent to the nurse's end.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. By constructing a multi-terminal data interaction architecture based on a cloud server, a highly efficient and stable data synchronization mechanism is achieved between the patient-side app, the nurse-side app, and the wearable device. Data synchronization latency is extremely low, and data upload frequency is reasonable and efficient. This innovative design ensures that patient movement data can flow smoothly and in real-time between all devices, allowing nurses to obtain the latest patient movement information immediately. Based on this, nurses can adjust intervention plans promptly according to the patient's actual situation, greatly improving the response speed and targeting of venous thrombosis prevention work, effectively reducing the potential risk of thrombosis, and providing stronger protection for patients' health.

[0019] 2. A meticulously crafted personalized incentive system within the patient-side app integrates various incentive methods, including a tiered achievement system, visualization of rehabilitation progress, and family-involved incentives. Different levels of achievement badges are scientifically awarded based on exercise goals achieved. This system effectively stimulates patients' intrinsic motivation to participate in exercise, significantly increasing their enthusiasm for actively engaging in physical activity. Patient satisfaction with the exercise monitoring and guidance system has greatly improved, and family members are more actively involved in the patient's rehabilitation process. By enhancing patient adherence to exercise, the system powerfully promotes the patient's rehabilitation progress and comprehensively improves the overall effectiveness of the venous thrombosis prevention exercise monitoring and guidance system.

[0020] 3. The intelligent prediction and early warning module of the nurse's app, leveraging advanced machine learning algorithms, comprehensively analyzes patients' historical movement data and physiological indicators to accurately predict the risk of thrombosis in the near future. When the predicted risk reaches a high level, the system will promptly issue an early warning. This function allows nurses to detect potential thrombosis risks in patients in advance, thus having more time to develop and implement intervention measures. Through early intervention, the probability of thrombosis in patients is effectively reduced, the occurrence of thrombosis-related complications is decreased, patient health and safety are effectively protected, and the quality and level of medical services are significantly improved. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating the exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction proposed in this invention. Detailed Implementation

[0022] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0023] This system consists of four parts: a patient-side app, a nurse-side app, a cloud server, and wearable devices. The patient-side app, installed on the patient's mobile device, is responsible for motion monitoring, incentive feedback, intelligent error correction guidance, and gentle reminders. The nurse-side app, deployed on the nurse's mobile device, enables patient risk stratification, personalized intervention plan generation, and closed-loop data management. The cloud server, located in the cloud, handles data storage, processing, and analysis, and supports multi-device data synchronization with minimal latency. Wearable devices (such as smart bracelets) integrate high-precision sensors to collect patients' movement data (steps) in real time. Exercise duration Heart rate (etc.) and upload them to the cloud server, data upload frequency .

[0024] After the system is operational, patient movement data is uploaded to the cloud server in real time, and nurses can view it instantly via their mobile app. Testing revealed a data synchronization delay. The average time is 0.8 seconds, which meets the needs of real-time monitoring, and the completeness rate of patient motion data reaches over 99%.

[0025] The personalized incentive system encompasses a tiered achievement system, visualization of rehabilitation progress, and incentives for family involvement. The tiered achievement system awards different levels of achievement badges based on the patient's exercise goals achieved, with the exercise goal achievement rate... The calculation formula is:

[0026] in, This refers to the actual duration of exercise. The goal is to achieve a certain amount of exercise time. Rehabilitation progress is visualized through charts showing the patient's exercise progress and goal achievement; family involvement and incentives are provided, inviting family members to participate and fostering emotional bonds.

[0027] The intelligent error correction and guidance module includes real-time motion guidance animations and playback analysis of incorrect movements. During patient movement, the wearable device collects motion data in real time, compares it with a standard motion library, and calculates the motion error rate. :

[0028] in, The number of incorrect actions. This represents the total number of actions. When an error is detected, a real-time action guidance animation is played via the patient's app, and a replay of the incorrect action is displayed.

[0029] The flexible reminder and scenario adaptation module automatically pushes exercise reminders based on the patient's daily routine and condition through intelligent time-slot recommendations and multi-scenario reminder triggers. For example, a morning exercise reminder is pushed after waking up in the morning (6:00-8:00), and a stretching exercise reminder is pushed during work breaks (every 90 minutes). Reminder acceptance rate. The calculation formula is:

[0030] in, To receive a certain number of reminders, This represents the number of reminders sent.

[0031] The patient risk stratification and priority reminder module automatically generates a three-color risk label (red, yellow, green) based on the patient's exercise data from the past 3 days. Risk Score The calculation formula is:

[0032] in, , , The weights are respectively the exercise target achievement rate, exercise duration fluctuation, and number of abnormal heart rate events; The formula for calculating the fluctuation in exercise duration is as follows: , For the number of days, For the first Daily exercise duration The average exercise duration over 3 days; This represents the number of times heart rate abnormalities occurred. Risk levels are categorized based on risk scores: red indicates high-risk patients, triggering immediate, high-priority alerts; yellow indicates medium-risk patients, receiving periodic alerts; and green indicates low-risk patients, requiring routine management.

[0033] The personalized intervention plan generation module automatically generates targeted intervention plans based on the patient's exercise data and type. For example, for patients with insufficient exercise duration, it suggests increasing the exercise duration. The calculation formula is:

[0034] For patients with high error rates, provide guidance on corrective actions, and the frequency of such guidance should be [not specified]. Based on action error rate Sure, ,in is a coefficient.

[0035] The emotion recognition and incentive adjustment module integrates emotion recognition algorithms to analyze patients' voice, facial expressions, or operational habits to determine their emotional state (positive, negative, or neutral). Emotional scoring is also included. The calculation formula takes into account speech features (pitch). Speech rate ), facial expressions (smile frequency) Frowning frequency ) and operating habits (operation speed) Operational accuracy ):

[0036] in, , , , , , Weights are assigned to each feature. Emotional states are categorized based on emotion scores; challenging tasks are added for positive emotions, while encouraging words are provided for negative emotions.

[0037] The virtual reality guidance module integrates virtual reality technology to provide patients with an immersive exercise experience. Patients wear VR devices and perform exercise training in a virtual environment, such as simulating outdoor running, with running distances measured virtually. Compared with actual exercise energy consumption There is a corresponding relationship, which can be confirmed by formula. calculate.

[0038] The intelligent prediction and early warning module integrates machine learning algorithms (such as logistic regression models) to predict and warn patients based on their historical exercise data (exercise achievement rate). Exercise duration ) and physiological indicators (heart rate) ,blood pressure This predicts the risk of thrombosis within a future period (e.g., 7 days). Thrombosis risk predictor value. The calculation formula is:

[0039] in, These are the model parameters, obtained through training with historical data. When predicting risk... When the value exceeds the threshold of 0.7, an early warning will be issued.

[0040] The abnormal situation early warning module integrates high-precision sensors and abnormal detection algorithms to monitor the patient's movement status in real time. When it detects ankle vibration amplitude... Exceeding the set threshold (e.g., 5 m / s²) or a sudden increase in heart rate, the magnitude of the increase in heart rate Exceeding the set threshold Calculate the anomaly score when (e.g., 30 times / minute). :

[0041] in, , Weighting of ankle vibration and heart rate elevation. When abnormal scores... If the threshold of 1 is exceeded, the exercise reminder will be immediately paused and pushed to the nurse's end via the patient's app.

[0042] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A cloud-based data interaction-based exercise monitoring and guidance system for venous thrombosis prevention, characterized in that: include: The patient-side app is used for motion monitoring, incentive feedback, intelligent error correction and guidance, and gentle reminders; The nurse-side app is used for patient risk stratification, generation of personalized intervention plans, and closed-loop data management. Cloud servers are used for data storage, processing, and analysis, and support multi-device data synchronization and sharing; Wearable devices integrate high-precision sensors to collect patients' motion data in real time and upload it to a cloud server, while also having an abnormal situation warning function.

2. The exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction according to claim 1, characterized in that, The patient-side app also includes: A personalized incentive system, including a tiered achievement system, visualization of rehabilitation progress, and incentives involving family members, enhances patients' motivation to exercise through social recognition, tangible benefits, and family bonds. The intelligent error correction and guidance module includes real-time motion guidance animations and error motion playback analysis, which help patients correct their movements independently through voice prompts, screen displays, and comparison images.

3. The exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction according to claim 1, characterized in that, The patient-side app further includes: The flexible reminder and scenario adaptation module automatically pushes exercise reminders based on the patient's daily routine and status through intelligent time period recommendation and multi-scenario reminder triggering, reducing intrusive reminders.

4. The exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction according to claim 1, characterized in that, The nurse-side app also includes: The patient risk stratification and priority reminder module automatically generates a three-color risk label based on the patient's exercise data over the past 3 days, and immediately triggers a high-priority reminder for patients with red risk. The personalized intervention plan generation module includes dynamically adjusting goals and recommending communication scripts, automatically generating targeted intervention plans based on the patient's movement data and type.

5. The exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction according to claim 1, characterized in that, The nurse-side app further includes: The data closed-loop and management tool module includes an intervention effect tracking form and a department summary report, which records the nurses' intervention time and method and the changes in the patients' achievement rate after intervention, and automatically generates a daily report on the department's patients' exercise achievement rate.

6. The exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction according to claim 1, characterized in that, The patient-side APP also includes an emotion recognition and incentive adjustment module. This module integrates an emotion recognition algorithm to analyze the patient's voice, facial expressions, or operating habits to determine their emotional state and automatically adjust incentive strategies.

7. The exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction according to claim 1, characterized in that, The patient-side app also includes a virtual reality guidance module, which integrates virtual reality technology to provide patients with an immersive exercise experience, thereby increasing their interest in and adherence to exercise.

8. The exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction according to claim 1, characterized in that, The nurse-side app also includes an intelligent prediction and early warning module. This module integrates machine learning algorithms to predict the risk of thrombosis in the future based on the patient's historical exercise data and physiological indicators, and issues early warnings in advance.

9. The exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction according to claim 1, characterized in that, The nurse-side app also includes a multimodal interaction module, which supports communication in various forms such as voice, text, and images, improving the efficiency and accuracy of doctor-patient communication.

10. The exercise monitoring and guidance system for venous thrombosis prevention based on cloud data interaction according to claim 1, characterized in that, The wearable device also includes an abnormal situation warning module. This module integrates high-precision sensors and abnormal detection algorithms to monitor the patient's movement status in real time. When abnormal ankle vibration or a sudden increase in heart rate is detected, the exercise is immediately paused and a reminder is sent to the nurse's end.

Images