Chronic disease whole-process dynamic health management system and method based on data driving

Abstract

The invention relates to the technical field of intelligent medical treatment, in particular to a chronic disease whole-process health management system and method based on data driving, and the system comprises a doctor management end, a cloud data center and a patient intelligent terminal. The doctor management end has the following functions: a voice interaction module, a communication module, a data analysis module, a closed-loop management module and a dynamic feedback module, and the communication module is used for transmitting a real-time data instruction to the cloud data center. The patient intelligent terminal has the following functions: a voice interaction module, a communication module, a data analysis module, a data acquisition module and a dynamic feedback module, and the communication module is used for transmitting a real-time data instruction to the cloud data center. According to the invention, a chronic disease management system taking data as a core is constructed, full-closed-loop management is realized, and the problems of intervention lag, model staticization and low cross-modal data utilization rate are solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical technology, and particularly relates to a closed-loop full-process health management system and method for chronic diseases integrating artificial intelligence (data), Internet of Things and big data technologies, covering the whole life cycle management of chronic disease prevention, diagnosis, intervention, feedback and dynamic optimization. Background Art

[0002] In the medical field, with the continuous progress of technology, people's demands for the medical experience and medical efficiency are also increasing, especially for the chronic disease group. The existing medical system relies on multi-terminal data collection and reminder, but lacks data-driven cross-modal data fusion and active decision-making capabilities, forming a situation of data islands and one-way management. At the same time, it leads to the lag of intervention for the chronic patient group, and it is impossible to predict the disease progression through data and generate intervention strategies in advance.

[0003] In such a background, the application of intelligent technology has become the key to improving medical services. Through artificial intelligence (data) technology, a chronic disease management system with data as the core and covering the whole closed loop of "data collection → intelligent diagnosis → personalized intervention → dynamic feedback → strategy dynamic optimization" can be constructed to solve the problems of lagging intervention, static model and low utilization rate of cross-modal data in the existing technology.

[0004] The present invention is improved and optimized on the basis of the existing technology, aiming to solve the problem that traditional chronic disease management relies on offline consultations and lacks real-time monitoring and dynamic adjustment capabilities, realizing the full-process closed-loop control of chronic disease management, and improving the timeliness of intervention through data dynamic optimization strategies. Summary of the Invention

[0005] In view of the defects or deficiencies in the existing technical solutions, it is expected to provide a data-driven full-process dynamic health management system and method for chronic diseases.

[0006] In a first aspect, a data-driven full-process dynamic health management system and method for chronic diseases includes a doctor management terminal, a cloud data center and a patient intelligent terminal.

[0007] The doctor management terminal is provided with a voice interaction function module, a communication module, a data intelligent analysis module, a closed-loop management module and a dynamic feedback module.

[0008] The voice interaction function module automatically executes according to the doctor's voice commands by collecting doctor instructions in real time; the communication module is used for transmitting data instructions between the local device and the cloud data center in real time; the data analysis module is used for multi-modal fusion analysis of data to generate health risk assessments, complication warnings, and personalized intervention suggestions; the closed-loop management module uses the data analysis results to push medication reminders, exercise plans, and dietary suggestions to the patient's intelligent terminal; the dynamic feedback module is used for receiving patient execution feedback data in real time and optimizing the intervention strategy through the policy generation engine algorithm.

[0009] The patient intelligent terminal is provided with a voice interaction function module, a communication module, a data intelligent analysis module, a data collection module, and a dynamic feedback module.

[0010] The voice interaction function module automatically executes according to the patient's voice commands by collecting patient voice information in real time; the communication module is used for transmitting data instructions between the local device and the cloud data center in real time; the data analysis module is used for multi-modal fusion analysis of data to generate health risk assessments, complication warnings, and personalized intervention suggestions; the closed-loop management module uses the data analysis results to send an abnormal alarm to the doctor's end; the dynamic feedback module is used for receiving the intervention feedback data pushed by the doctor in real time.

[0011] According to the technical solution provided by the embodiment of the present application, the voice interaction function module is based on the voice receiving device, voice calling device, voice data assistant, and abnormal voice reminder of the mobile phone.

[0012] According to the technical solution provided by the embodiment of the present application, the data intelligent analysis module uses multi-modal data fusion technology to analyze the collected data and identify the patient's health status, disease development trend, and potential risks.

[0013] According to the technical solution provided by the embodiment of the present application, the closed-loop management module generates a personalized intervention strategy based on data decision-making and ensures full-process closed-loop control from "analysis → execution → feedback", using the policy generation engine algorithm to generate intervention strategies (such as adjusting drug doses, customizing exercise plans), rather than relying on manually preset rules.

[0014] According to the technical solution provided by the embodiment of the present application, the dynamic feedback module optimizes the data model and intervention strategy based on the execution feedback data to form a continuously iterative learning system.

[0015] According to the technical solution provided by the embodiment of the present application, the data collection module is responsible for real-time collection and standardized processing of multi-source heterogeneous data to provide high-quality input for the data model.

[0016] Advantages of the present invention:

[0017] The present invention relates to a data-driven dynamic health management system and method for the whole process of chronic diseases. By integrating multi-modal data perception, data dynamic decision-making, and distributed data optimization mechanism optimization technology, it realizes fully automatic closed-loop management from data collection to intervention strategy iteration. The system significantly improves the accuracy and timeliness of chronic disease management and is applicable to the intelligent prevention and control of chronic diseases such as diabetes and hypertension. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects, and advantages of the present application will become more apparent by reading the detailed description of the non-limiting embodiments with reference to the following drawings.

[0019] Figure 1 It is a schematic diagram of the principle for the realization of the functions of the management system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The present application will be further described in detail below with reference to the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related invention and are not intended to limit the invention. Additionally, it should be noted that for the sake of description, only the parts related to the invention are shown in the drawings.

[0021] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the drawings and embodiments.

[0022] A data-driven dynamic health management system and method for the whole process of chronic diseases includes a doctor management terminal, a cloud data center, and a patient intelligent terminal.

[0023] The doctor management terminal is provided with a voice interaction function module, a communication module, a data intelligent analysis module, a closed-loop management module, and a dynamic feedback module.

[0024] The voice interaction function module automatically executes according to the doctor's voice commands by collecting doctor instructions in real time; the communication module is used for transmitting data instructions between the doctor management terminal and the cloud data center in real time; the data analysis module is used for multi-modal fusion analysis of data to generate health risk assessment, complication warning, and personalized intervention suggestions; the closed-loop management module uses the data analysis results to push medication reminders, exercise plans, and diet suggestions to the patient intelligent terminal; the dynamic feedback module is used for receiving the patient's execution feedback data in real time and optimizing the intervention strategy through the strategy generation engine algorithm.

[0025] The patient intelligent terminal is provided with a voice interaction function module, a communication module, a data intelligent analysis module, a data collection module, and a dynamic feedback module.

[0026] The voice interaction function module collects patient voice information in real time and automatically executes according to the patient's voice commands; the communication module is used to transmit data instructions between real time and cloud data centers; the data analysis module is used to perform multimodal fusion analysis on the data to generate health risk assessments, complication warnings and personalized intervention recommendations; the closed-loop management module uses the data analysis results to send abnormal alarms to the doctor side; the dynamic feedback module is used to receive intervention feedback data pushed by the doctor in real time.

[0027] Embodiment 1:

[0028] As a common chronic disease, the management of hypertension requires long-term monitoring and dynamic intervention. Traditional management methods mainly rely on regular outpatient examinations and patient self-recording, which often leads to problems such as discontinuous data and delayed intervention. In order to solve these problems, this embodiment proposes a hypertension management system based on a data closed-loop system, which can achieve real-time monitoring, intelligent decision-making and dynamic optimization.

[0029] Patients use smart terminal devices, such as monitoring instruments and smart bracelets, to collect various types of data in real time, including physiological data (such as blood pressure, heart rate), behavioral data (such as diet, exercise), environmental data (such as air quality, temperature) and medical record data (such as medication history, medical records). These data will be transmitted to the data center for preprocessing to ensure their accuracy and reliability. The preprocessed data will be input into the data decision center, which uses machine learning algorithms to conduct in-depth analysis of the data to identify the patient's health status, disease development trends and potential risks. Based on these analysis results, the data decision center will generate personalized intervention strategies, including dietary recommendations, exercise plans, medication guidance, etc. These intervention strategies will be implemented through multi-terminal collaboration, including pushing early warning information or intelligent intervention recommendations to the patient terminal, and pushing patient vital signs details and risk assessment reports to the doctor management terminal. Doctors can review these reports and click "Confirm Execution" based on their own professional knowledge and experience, and the system will automatically synchronize the intervention strategy to the patient terminal.

[0030] Through the dynamic feedback module, the system can optimize the intervention strategy according to the patient's feedback and data changes. For example, patients can confirm the completion of medication through the terminal, with a check-in rate of up to 95%, and submit subjective symptom scores, indicating that dizziness has been alleviated. The system uses distributed data optimization mechanism technology to update the data algorithm model to eliminate possible confounding factors, such as patients reducing their drinking at the same time. Finally, the system generates a new intervention strategy, advising patients to reduce going out on foggy days and linking smart home devices to enhance air purification.

[0031] Embodiment 2:

[0032] Diabetes is a chronic disease that requires long-term management and precise control. Effective blood glucose management can not only prevent complications but also significantly improve the quality of life of patients. This embodiment proposes a closed-loop diabetes management system based on artificial intelligence. By integrating a continuous glucose monitor and an intelligent insulin pump, the system realizes real-time monitoring, intelligent decision-making, and dynamic optimization for diabetes patients. Data collection is the foundation of the system. The continuous glucose monitor (CGM) uploads blood glucose values every 5 minutes, ensuring the real-time and continuity of blood glucose data. The intelligent insulin pump records the dose and time of each injection, providing key data for subsequent analysis. In addition, patients record their dietary situations through the terminal, further enriching the data sources.

[0033] In terms of data decision-making, we use graph neural networks (GNNs) to analyze the dynamic relationships among blood glucose, diet, and insulin. GNNs can deeply explore the complex interactions among these variables and predict the changing trends of blood glucose. Based on these predictions, the system can dynamically adjust the basal rate of insulin and recommend low-carbohydrate recipes suitable for patients to achieve precise control of blood glucose.

[0034] Feedback optimization is an important part of the system. We use the Bayesian optimization method to adjust the model parameters according to the blood glucose fluctuation curve (such as a 20% reduction in the postprandial peak). This optimization process makes the system's predictions more accurate and the intervention measures more effective, thus improving the personalization and precision of diabetes management. The effectiveness data show that the system has achieved remarkable results in diabetes management. The glycated hemoglobin (HbA1c) of patients has decreased from 8.5% to 6.9%, and the hypoglycemia events have been reduced by 70%. These data fully prove the effectiveness and practicality of the system and demonstrate the great potential of artificial intelligence in diabetes management.

Claims

1. A data-driven dynamic health management system and method for the whole process of chronic diseases, characterized in that, It includes a doctor management terminal, a cloud data center, and a patient intelligent terminal: The doctor management terminal is provided with a voice interaction function module, a communication module, a data intelligent analysis module, a closed-loop management module, and a dynamic feedback module; The voice interaction function module automatically executes according to the doctor's voice commands by collecting doctor instructions in real time; The communication module is used for transmitting data instructions to and from the cloud data center in real time; the data analysis module is used for multi-modal fusion analysis of data to generate health risk assessments, complication warnings, and personalized intervention suggestions; The closed-loop management module uses the data analysis results to push medication reminders, exercise plans, and diet suggestions to the patient intelligent terminal; The dynamic feedback module is used for receiving patient execution feedback data in real time and optimizing the intervention strategy through the policy generation engine algorithm; The patient intelligent terminal is provided with a voice interaction function module, a communication module, a data intelligent analysis module, a data collection module, and a dynamic feedback module; The voice interaction function module automatically executes according to the patient's voice commands by collecting the patient's voice information in real time; The communication module is used for transmitting data instructions to and from the cloud data center in real time; the data analysis module is used for multi-modal fusion analysis of data to generate health risk assessments, complication warnings, and personalized intervention suggestions; the closed-loop management module uses the data analysis results to send an abnormal alarm to the doctor terminal; The dynamic feedback module is used for receiving the intervention feedback data pushed by the doctor in real time.

2. The data-driven full-process dynamic health management system and method for chronic diseases according to claim 1, characterized in that: The voice interaction function module is based on the voice receiving device, voice calling device, voice data assistant, and abnormal voice reminder of a mobile phone.

3. A data-driven dynamic health management system and method for the whole process of chronic diseases according to claim 1, characterized in that: The data intelligent analysis module uses multi-modal data fusion technology to analyze the collected data to identify the patient's health status, disease development trend, and potential risks.

4. A data-driven dynamic health management system and method for the whole process of chronic diseases according to claim 1, characterized in that: The closed-loop management module generates personalized intervention strategies based on data decisions and ensures full-process closed-loop control from "analysis → execution → feedback", and uses the policy generation engine algorithm to generate intervention strategies (such as adjusting drug doses, customizing exercise plans), rather than relying on manually preset rules.

5. A data-driven dynamic health management system and method for the whole process of chronic diseases according to claim 1, characterized in that: The dynamic feedback module optimizes the data model and intervention strategy based on the execution feedback data to form a continuously iterative learning system.

6. A data-driven dynamic health management system and method for the whole process of chronic diseases according to claim 1, characterized in that: The data collection module is responsible for real-time collection and standardized processing of multi-source heterogeneous data to provide high-quality input for the data model.

7. A data-driven full-process dynamic health management system and method for chronic diseases has the following characteristics: It is completed by using the modules described in any one of claims 1-6, and realizes fully automatic closed-loop management from data collection to intervention strategy iteration through technologies that integrate multi-modal data perception, data dynamic decision-making, and distributed data optimization mechanisms. The system significantly improves the accuracy and timeliness of chronic disease management and is applicable to the intelligent prevention and control of chronic diseases such as diabetes and hypertension.

Images