Diabetes patient data management method and system based on big data

Abstract

The present invention discloses a method and system for managing diabetic patient data based on big data. It relates to the field of medical care, collects basic patient information and stable blood sugar data, obtains influencing factors by matching similar cases through a cloud database, and generates a personalized data collection plan; customizes user terminals and establishes data management containers, adaptively collects blood sugar and influencing factor data, calculates the degree of change and issues warnings through a sliding window algorithm; uses a time-varying weight model to dynamically update the weights of influencing factors, and generates intervention strategies based on the weights. The system includes modules such as a cloud server, an integrated management terminal, and a user terminal to achieve closed-loop management of data collection, analysis, and intervention. This solution uses big data analysis and a dynamic weight model to achieve personalized and precise management of diabetic patients, and can adjust collection strategies and intervention plans based on individual differences, thereby improving the accuracy of risk warnings and management efficiency.

Description

Technical Field

[0001] The present invention relates to the field of medical care, and in particular to a big data-based diabetic patient data management method and system. Background Art

[0002] Traditional diabetes management methods rely primarily on patient self-monitoring and regular medical visits, which present numerous limitations. For one thing, patients manually record blood sugar data, diet, exercise, and other information, which is not only cumbersome but also prone to incomplete and inaccurate records, making it difficult to fully reflect the patient's true condition. On the other hand, doctors base diagnoses and treatment plans on limited outpatient data, lacking a real-time, comprehensive understanding of the patient's daily condition, making it difficult to achieve personalized, precise management. Furthermore, traditional methods struggle to effectively capture the complex relationship between blood sugar fluctuations and various influencing factors, making it impossible to promptly identify potential risk factors and intervene.

[0003] In recent years, the rapid development of technologies such as big data, the Internet of Things, and artificial intelligence has provided new insights and approaches for diabetes management. Big data technologies can integrate vast amounts of patient data, including blood glucose monitoring data, physiological indicators, lifestyle habits, and environmental factors, and through in-depth analysis, uncover patterns and insights. IoT technology interconnects various sensors, enabling real-time and continuous data collection. Artificial intelligence algorithms can analyze and process complex data, constructing accurate predictive models and supporting personalized diabetes management.

[0004] However, existing diabetes data management systems still have several shortcomings. For example, their single data collection method fails to fully capture all factors affecting blood sugar levels; their limited data processing and analysis capabilities make it difficult to handle the real-time processing of massive amounts of data; and they lack dynamic adjustment and personalized management strategy generation mechanisms, making them difficult to adapt to individual patient differences and the dynamic changes in their condition. Therefore, a big data-based diabetes patient data management method and system is urgently needed to achieve more comprehensive, accurate, and dynamic diabetes management. Summary of the Invention

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a method for managing diabetic patient data based on big data, comprising the following steps:

[0006] Step 1: The integrated management terminal collects the patient's basic information and blood glucose data in a stable state. Based on the patient's basic information, the cloud data server obtains the patient's blood glucose influencing factors. Based on the patient's blood glucose influencing factors, the corresponding influencing factor data collection module information is obtained to generate the influencing factor data collection plan for the corresponding patient.

[0007] Step 2: Based on the data collection plan for the influencing factors of the corresponding patient, a user terminal for the corresponding patient is generated, the integrated management terminal generates a patient data management container, and communicates with the user terminal of the corresponding patient to send the patient's blood glucose data in a stable state to the patient data management container;

[0008] Step 3: The user terminal corresponding to the patient collects the patient's blood glucose data and influencing factor data according to the collection cycle, and obtains the degree of change in the blood glucose data at the start and end times of the influencing factor based on the blood glucose data and the influencing factor data; a risk warning is issued based on the degree of change in the blood glucose data, and the influencing factor data and the degree of change in the blood glucose data at the start and end times of the influencing factor are sent to the patient data management container;

[0009] Step 4: The patient data management container obtains the weight of the influencing factor affecting the blood sugar data based on the influencing factor data obtained in different periods and the degree of change in the blood sugar data at the start and end times of the influencing factor;

[0010] Step 5: Generate a patient blood glucose management strategy based on the weights of the various influencing factors affecting blood glucose data, and complete the data management of diabetic patients.

[0011] Furthermore, the integrated management terminal collects the patient's basic information and blood sugar data in a stable state, and obtains the patient's blood sugar influencing factors on the cloud data server based on the patient's basic information, including:

[0012] Collect patient identity information, medical history, medication records, and fasting / postprandial blood glucose baseline values for n consecutive hours through standardized forms;

[0013] The patient database of the cloud data server is called to match similar cases and obtain a set of influencing factors with a correlation greater than a threshold with the current patient's blood sugar fluctuation. The influencing factors include: dietary composition, exercise intensity, sleep quality, medication compliance, environmental temperature and humidity, and mood swing indicators;

[0014] A priority list of individualized influencing factors for patients is established, wherein the priority is calculated by a dynamic weighting algorithm, and the initial weight is a preset value.

[0015] Furthermore, the method of obtaining corresponding influencing factor data acquisition module information based on the patient's blood sugar influencing factors and generating an influencing factor data acquisition plan for the corresponding patient includes:

[0016] Construct a module configuration mapping table to associate each type of influencing factor with the corresponding acquisition module; generate an acquisition module activation sequence based on the priority list, and set the high-priority acquisition module to high-frequency sampling mode; and generate an acquisition module configuration file, including sampling frequency, data format standard, and outlier judgment threshold.

[0017] Furthermore, the user terminal corresponding to the patient collects the patient's blood glucose data and influencing factor data according to the collection period, and obtains the degree of change of the blood glucose data at the start and end times of the influencing factor based on the blood glucose data and the influencing factor data, including:

[0018] Adopting an adaptive sampling cycle: the basic cycle is a first set duration, and when it is detected that the blood sugar change rate exceeds the change rate threshold, encrypted sampling is performed, and the encrypted sampling cycle is a second set duration, and the second set duration is less than the first set duration;

[0019] The sliding window algorithm is used to calculate the degree of change. The window length is set to twice the period of the influencing factor. The degree of change is:

[0020] ΔG = Σ|G(t+τ)-G(t)| / (τ_max - τ_min)

[0021] Where G(t) is the blood glucose value and τ is the duration of the influencing factor.

[0022] Furthermore, the risk warning according to the degree of change in blood sugar data includes:

[0023] According to the degree of change in blood sugar data, the corresponding early warning strategy is called on the cloud data server, and the patient is warned according to the early warning strategy.

[0024] Furthermore, the patient data management container obtains the weight of the influencing factors affecting the blood sugar data based on the influencing factor data obtained in different periods and the degree of change in the blood sugar data at the start and end times of the influencing factors, including:

[0025] The time-varying weight calculation model is used to calculate the weights of factors affecting blood glucose data, and the weights are updated as follows:

[0026] W_i(t) = α·ΔG_i(t) / ΣΔG_j(t) + (1-α)·W_i(t-Δt)

[0027] Where α is the forgetting factor (0<α<1), Δt is the update cycle; W_i(t) is the dynamic influence weight of influencing factor i on blood glucose data at time t, which represents the contribution ratio of the i-th influencing factor to blood glucose fluctuations at time t, and the sum of the weights of all influencing factors ΣW_i(t)=1; ΔG_i(t) is the blood glucose change caused by influencing factor i at time t; ΣΔG_j(t) is the total blood glucose change caused by all influencing factors at time t; W_i(t-Δt) is the historical weight of influencing factor i in the previous calculation cycle (t-Δt).

[0028] Furthermore, the method of generating a patient blood glucose management strategy based on the obtained weights of the various influencing factors affecting the blood glucose data includes:

[0029] According to the weight of the influencing factors affecting blood glucose data, a priority list of influencing factor interventions is generated. For the influencing factors whose weights are greater than the weight threshold, the corresponding intervention strategies are obtained from the cloud data server. The intervention strategies corresponding to the influencing factors whose weights are greater than the weight threshold constitute the patient's blood glucose management strategy.

[0030] A big data-based diabetes patient data management system, which applies the big data-based diabetes patient data management method, includes a cloud data server, an integrated management terminal, a communication module, a user terminal, a risk assessment module, and a health status tracking module;

[0031] The cloud data server, integrated management terminal, user terminal, risk assessment module, and health status tracking module are respectively connected to the communication module for communication;

[0032] The cloud data server is used to provide a patient database and a policy database;

[0033] The integrated management terminal is used to customize the influencing factor data acquisition module in the user terminal according to the influencing factors of the patient's health data, and to manage the user management data and the user terminal;

[0034] The user terminal is used to collect patient management data;

[0035] The risk assessment module is used to perform risk assessment based on the patient's management data; the risk assessment includes a health risk assessment module and a data integrity assessment;

[0036] The health status tracking module is used to track the patient's health status based on patient management data and risk assessment.

[0037] Preferably, the user terminal includes an influencing factor data acquisition module, an identity information module, a location information acquisition module, a management data generation module, a data processing module and a communication device;

[0038] The influencing factor data acquisition module, identity information module, location information acquisition module, management data generation module and communication device are respectively connected to the data processing module;

[0039] The influencing factor data acquisition module is used to collect data on influencing factors that affect the patient's blood sugar index;

[0040] The identity information collection module is used to collect the patient's identity information;

[0041] The location information acquisition module is used to acquire the patient's location;

[0042] The management data generation module is used to generate user health management data based on the data collected by the user terminal during the management period.

[0043] The beneficial effects of the present invention are as follows: basic information and blood sugar baseline values of patients are collected through standardized forms, thereby ensuring the standardization and integrity of the initial data. The influencing factor data collection scheme is personalized and customized, and the collection module and sampling frequency are determined according to the specific situation of the patient, thereby realizing the comprehensive collection of various factors affecting blood sugar. The adaptive sampling cycle mechanism can increase the sampling frequency when blood sugar changes drastically, timely capture the rapid changes in blood sugar, and improve the accuracy and real-time nature of blood sugar data collection. At the same time, the determination and processing of abnormal values in the data collection process further ensure the quality of the data.

[0044] Through similar case matching and a dynamic weighting algorithm, a personalized priority list of influencing factors is established for each patient, enabling data collection and management to be tailored to their specific circumstances. A time-varying weight calculation model continuously updates the weights of influencing factors based on real-time data, reflecting the dynamic changes in the patient's condition. Weight-based personalized management strategies can provide precise intervention measures for factors that significantly impact a patient's blood sugar, improving the relevance and effectiveness of diabetes management.

[0045] By calculating the degree of change in blood glucose data using a sliding window algorithm, we can comprehensively capture the impact of influencing factors on blood glucose fluctuations throughout the entire process. Based on the degree of blood glucose change, corresponding early warning strategies are invoked, providing timely early warning of blood glucose risks. The risk assessment module not only focuses on changes in blood glucose itself but also comprehensively considers various influencing factors, improving the accuracy and comprehensiveness of risk assessments. Timely risk warnings can help patients and medical staff take timely measures to reduce the risk of complications.

[0046] The system integrates multi-dimensional data, including patients' blood sugar data, influencing factors, medical history, and medication records, using big data analysis techniques to uncover patterns and insights. A time-varying weight calculation model dynamically analyzes the complex relationship between influencing factors and blood sugar, providing data support for a deeper understanding of the pathogenesis and progression of diabetes. The health status tracking module analyzes long-term data to create health status curves, providing a robust basis for evaluating treatment effectiveness and adjusting management strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flowchart of the big data-based diabetes patient data management method. DETAILED DESCRIPTION

[0048] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0049] The features and performance of the present invention are further described in detail below with reference to the embodiments.

[0050] like Figure 1 As shown, the data management method of diabetic patients based on big data

[0051] Step 1: The integrated management terminal collects patient information and generates a data collection plan for influencing factors

[0052] As the starting point for data collection and management, the integrated management terminal undertakes the important task of obtaining basic patient information and initial blood glucose data. When collecting basic patient information, a carefully designed standardized form is used to ensure the standardization and integrity of the data. This standardized form covers several key dimensions:

[0053] Patient identity information: including name, age, gender, contact information, ID number, etc. This information is the basis for identifying patients and ensuring that the data accurately corresponds to the patient.

[0054] Medical history records: Detailed records of the patient's diabetes onset time, past medical history, complications, etc., provide important historical reference for subsequent disease analysis and management.

[0055] Medication records: Record the type, dosage, and time of use of the hypoglycemic drugs currently used by the patient. The impact of drug factors on blood sugar is crucial, and accurate medication records are the basis for subsequent analysis.

[0056] Blood glucose baseline values: Set fasting / postprandial blood glucose baseline values for n consecutive hours. The n-hour period should be determined based on medical standards and clinical practice. Typically, a period that fully reflects the patient's blood glucose stability over a period of time is selected, such as 72 consecutive hours of fasting and postprandial blood glucose data. Continuous collection can reduce the impact of incidental factors on blood glucose values and provide more representative baseline data.

[0057] After obtaining basic patient information, the integrated management terminal uses this information to retrieve factors influencing the patient's blood sugar level from the cloud-based data server. The cloud-based data server stores a vast amount of patient data and medical knowledge, and similar cases are matched by accessing the patient database within. Advanced machine learning algorithms are employed to identify similar cases. For example, clustering algorithms can be used to group patients with similar characteristics (such as age, gender, medical history, and blood sugar levels). By calculating the similarity between the current patient's characteristics and those of other patients in the database, a set of influencing factors with a correlation greater than a preset threshold with the current patient's blood sugar fluctuations is obtained.

[0058] These influencing factors mainly include the following categories:

[0059] Dietary ingredients: Different food ingredients have different effects on blood sugar, such as the content and type of carbohydrates.

[0060] Exercise intensity: Exercise is an important factor affecting blood sugar. The intensity, time and method of exercise will have different effects on blood sugar.

[0061] Sleep quality: Lack of sleep or poor sleep quality may lead to blood sugar fluctuations.

[0062] Medication compliance: Whether the patient takes the medication correctly according to the doctor's instructions directly affects the blood sugar control effect.

[0063] Environmental temperature and humidity: Environmental factors may indirectly affect blood sugar by affecting the patient's physiological state.

[0064] Mood swing indicators: Drastic mood swings may lead to changes in hormone levels in the body, which in turn affects blood sugar.

[0065] After obtaining a set of influencing factors, a personalized priority list of influencing factors needs to be established for each patient. This process is achieved through a dynamic weighting algorithm, with initial weights preset based on medical research and clinical experience. The dynamic weighting algorithm adjusts weights based on various factors, such as the degree of influence of different influencing factors in similar cases and the individual characteristics of the patient. In this way, the relative importance of each influencing factor can be determined based on the patient's specific situation, providing a basis for the subsequent data collection plan.

[0066] Next, based on the patient's blood sugar influencing factors, the corresponding data collection module information is obtained and a corresponding collection plan is generated. First, a module configuration mapping table is constructed, associating each type of influencing factor with the corresponding collection module. For example, the collection of dietary composition may need to be linked to the diet recording module, and the collection of exercise intensity needs to be linked to the exercise monitoring module. Then, based on the previously established priority list, an activation sequence for the collection modules is generated. High-priority collection modules are set to high-frequency sampling mode to ensure more frequent acquisition of data on key influencing factors. Simultaneously, a detailed collection module configuration file is generated, including key parameters such as sampling frequency, data format standards, and outlier thresholds. The sampling frequency setting should be determined based on the characteristics of the influencing factor and medical requirements. For example, factors that are more sensitive to blood sugar fluctuations may require a higher sampling frequency. Standardizing data format standards facilitates subsequent data processing and analysis. The outlier threshold is used to identify and filter out abnormal data that may occur during the collection process.

[0067] Step 2: Generate a user terminal and establish a data management container

[0068] Based on the data collection plan for influencing factors generated in step 1, a dedicated user terminal is generated for the corresponding patient. The generation of the user terminal needs to consider the configuration of hardware and software to meet the functional requirements and data processing requirements of different acquisition modules. In terms of hardware, it is necessary to integrate corresponding sensors and communication modules, such as blood glucose meter sensors for collecting blood glucose data and acceleration sensors for collecting exercise intensity; in terms of software, it is necessary to install an adaptive operating system and application to realize data collection, processing and transmission functions.

[0069] At the same time, the integrated management terminal generates a patient data management container. This is a logical unit dedicated to storing and managing patient data. Built on cloud computing technology, it boasts powerful data storage and processing capabilities. The data management container utilizes advanced database architectures, such as distributed databases, to address the storage and management needs of massive amounts of data while ensuring data security and reliability.

[0070] Next, a communication connection is established between the integrated management terminal and the corresponding patient user terminal. The communication module uses secure and reliable protocols, such as MQTT (Message Queuing Telemetry Transport), which is lightweight, low-power, and suitable for communication between IoT devices. During communication, data is encrypted using algorithms such as the Advanced Encryption Standard (AES) to ensure data security and privacy during transmission.

[0071] After establishing a communication connection, the integrated management terminal sends the patient's stable blood glucose data to the patient data management container. This initial blood glucose data serves as the patient's baseline data, providing a reference for subsequent data analysis and management. Data is formatted and verified before transmission to ensure accuracy and integrity.

[0072] Step 3: User terminals collect data, analyze the degree of change, and issue risk warnings

[0073] The patient's user terminal collects the patient's blood sugar data and influencing factor data according to the set collection period. In order to improve the efficiency and accuracy of data collection, an adaptive sampling period mechanism is adopted. The basic period is set to a first set duration, which is determined according to the routine medical monitoring requirements and the actual needs of data collection. For example, it can be set to 30 minutes. When it is detected that the blood sugar change rate exceeds the pre-set change rate threshold, the encrypted sampling mode is automatically triggered. At this time, the encrypted sampling period is the second set duration, and the second set duration is less than the first set duration. For example, it can be set to 5 minutes. This adaptive sampling method can reduce the sampling frequency when blood sugar changes are relatively stable, reduce power consumption and data volume; and increase the sampling frequency when blood sugar changes drastically, capture rapid changes in blood sugar in time, and improve the real-time and accuracy of the data.

[0074] After obtaining blood sugar data and influencing factor data, it is necessary to obtain the degree of change in blood sugar data at the start and end times of the influencing factor based on these data. Here, a sliding window algorithm is used to calculate the degree of change, and the window length is set to twice the effect period of the influencing factor. This is because considering that the impact of the influencing factor on blood sugar may have a certain delay and duration, setting the window length to twice the effect period can more comprehensively capture the impact of the influencing factor on blood sugar changes throughout the process. The calculation formula for the degree of change is:

[0075] ΔG = Σ|G (t+τ)-G (t)| / (τ_max - τ_min)

[0076] Where G(t) represents the blood glucose level at time t, τ is the duration of the influencing factor, and τ_max and τ_min are the maximum and minimum durations of the influencing factor, respectively. By calculating the sum of the absolute changes in blood glucose levels within the sliding window and dividing it by the duration of the influencing factor, a quantitative indicator reflecting the degree of blood glucose change is obtained.

[0077] Risk warnings are issued based on the calculated degree of change in blood sugar data. First, warning strategies corresponding to different degrees of blood sugar change are pre-stored on the cloud data server. These warning strategies are developed based on medical knowledge and clinical experience and include different warning levels (such as low risk, medium risk, and high risk) and corresponding warning measures. After the user terminal calculates the degree of blood sugar change, it sends it to the cloud data server. The server invokes the corresponding warning strategy based on the degree of change and issues a warning to the patient through the user terminal. Warning methods can include sound prompts, app push notifications, SMS reminders, etc., to ensure that patients can be aware of their blood sugar risk status in a timely manner.

[0078] Step 4: Calculate the weight of influencing factors on blood glucose data

[0079] The patient data management container receives the influencing factor data and the corresponding blood glucose data change degree of different periods from the user terminal, and then uses the time-varying weight calculation model to calculate the weight of the influencing factor on the blood glucose data. The formula of the time-varying weight calculation model is:

[0080] W_i (t) = α・ΔG_i (t) / ΣΔG_j (t) + (1-α)・W_i(t-Δt)

[0081] α is the forgetting factor, ranging from 0 to 1, and is used to adjust the weight ratio between new and historical data. A larger α indicates a greater emphasis on the impact of current data; a smaller α indicates a greater influence of historical data. Δt is the update period, determined based on the frequency of data collection and actual needs; for example, it can be set to 1 day. W_i(t) represents the dynamic impact weight of influencing factor i on blood glucose data at time t, reflecting the contribution of the i-th influencing factor to blood glucose fluctuations at time t. ΣΔG_j(t) is the total blood glucose change caused by all influencing factors at time t. By dividing the blood glucose change corresponding to each influencing factor, ΔG_i(t), by the total change, we obtain the relative contribution of each influencing factor in the current period. This is then multiplied by the forgetting factor α and added to the historical weight W_i(t-Δt) multiplied by (1-α) to obtain the updated weight.

[0082] This time-varying weight calculation model has the following advantages: it can continuously update the weights based on new data over time, reflecting the dynamic changes in the impact of influencing factors on blood sugar; the introduction of the forgetting factor enables the model to adapt to changes in the patient's condition and the emergence of new influencing factors, thereby improving the flexibility and adaptability of the model; at the same time, by considering historical weights, the continuity and stability of weight changes are maintained, avoiding drastic changes in weights caused by fluctuations in individual data.

[0083] When calculating weights, data preprocessing is required, including outlier removal and data smoothing, to reduce the impact of data noise on the weight calculation. Statistical methods, such as the 3σ principle, can be used to identify and remove outliers. Methods such as moving averages can be used to smooth data and improve data quality.

[0084] Step 5: Generate patient blood glucose management strategy

[0085] Based on the weights of the influencing factors on the blood glucose data obtained in step 4, the patient's blood glucose management strategy is generated. First, the influencing factors are sorted according to the weights to generate a priority list for intervention of the influencing factors. The influencing factors with greater weights have a greater impact on blood glucose, so they should be given priority during intervention. A weight threshold is set, and the influencing factors with weights greater than the threshold are taken as the main intervention targets. The setting of the weight threshold needs to be combined with medical knowledge and clinical experience. For example, it can be set to 0.1, that is, the influencing factors with a weight greater than 0.1 are considered to have a significant impact on blood glucose.

[0086] Then, for each influencing factor with a weight greater than the weight threshold, the corresponding intervention strategy is obtained from the policy database of the cloud data server. The policy database stores a wealth of intervention strategies, which are developed by medical experts based on a large number of clinical cases and research results. These strategies are scientific and effective. Different influencing factors correspond to different intervention strategies. For example, for the influencing factors of dietary composition, possible intervention strategies include developing a personalized diet plan, controlling carbohydrate intake, and rationally matching meals. For the influencing factors of exercise intensity, intervention strategies may include developing an exercise plan suitable for the patient's physical condition and determining the intensity, time, and frequency of exercise.

[0087] The intervention strategies corresponding to each eligible influencing factor are integrated to form a patient's blood sugar management strategy. The resulting management strategy is personalized and can be tailored to the patient's specific situation, focusing on factors that have the greatest impact on blood sugar and providing precise intervention measures. At the same time, the management strategy also needs to take into account individual patient differences, such as age, physical condition, and lifestyle habits, to ensure the feasibility and effectiveness of the strategy.

[0088] Diabetes patient data management system based on big data

[0089] The big data-based diabetes patient data management system applies the above-mentioned management method, and mainly includes cloud data servers, integrated management terminals, communication modules, user terminals, risk assessment modules, health status tracking modules and other components. Each module is connected through the communication module.

[0090] The cloud-based data server is the system's data core, providing both a patient database and a policy database. The patient database stores a vast amount of patient information, including basic information, medical history records, medication records, blood glucose monitoring data, and influencing factor data. This data originates from various integrated management terminals and user terminals, and through data cleaning, integration, and storage, a rich patient data resource is formed. The policy database stores various intervention and early warning strategies, which serve as crucial foundations for the system's generation of management strategies and risk warnings. The cloud-based data server utilizes a distributed storage architecture to meet the storage needs of massive amounts of data while ensuring high data availability and scalability. Furthermore, it is equipped with a powerful data processing and analysis engine capable of supporting complex data analysis and model calculations.

[0091] The integrated management terminal is mainly used to customize the influencing factor data acquisition module in the user terminal based on the influencing factors of the patient's health data, and to manage the user management data and user terminals. It provides a friendly user interface to facilitate operation by medical staff. When customizing the acquisition module, the integrated management terminal configures the corresponding acquisition module parameters, such as sampling frequency, data format, etc., based on the patient influencing factors and priority list obtained in step one. At the same time, the integrated management terminal is also responsible for managing the user terminal, including terminal registration, configuration updates, status monitoring, etc., to ensure the normal operation of the user terminal. In addition, the integrated management terminal can also perform preliminary analysis and display of the patient's management data to provide decision support for medical staff.

[0092] The user terminal is a device directly facing patients and is used to collect patient management data. It includes the following main modules:

[0093] Influencing factor data acquisition module: used to collect data on various influencing factors that affect the patient's blood sugar indicators, and equipped with corresponding sensors according to different influencing factors, such as blood glucose meter sensors, motion sensors, sleep monitoring sensors, etc.

[0094] Identity information module: used to collect and store the patient's identity information to ensure that the data accurately corresponds to the patient.

[0095] Location information collection module: Using positioning technologies such as GPS or Beidou to collect the patient's location information, which is of great significance for analyzing the impact of environmental factors on blood sugar and conducting positioning rescue in emergency situations.

[0096] Management data generation module: Based on the data collected by the user terminal during the management cycle, data integration and processing are performed to generate user health management data.

[0097] Data processing module: It is the core processing unit of the user terminal, responsible for processing, analyzing and storing the data collected by each module, and controlling the working status of each module.

[0098] Communication device: used to realize data transmission between user terminal and communication module, supporting multiple communication modes such as 4G, 5G, Wi-Fi, etc., to ensure stable data transmission.

[0099] The risk assessment module is used to conduct risk assessments based on the patient's management data, including health risk assessments and data integrity assessments. Based on the degree of blood sugar changes and other relevant data in step three, combined with the risk assessment model in the cloud data server, the health risk assessment module assesses the patient's health status, determines whether the patient is at risk of hypoglycemia, hyperglycemia, or other complications, and assigns a corresponding risk level. The data integrity assessment module checks the collected data and assesses the integrity and quality of the data, such as whether the data collection frequency meets the requirements and whether there are missing values, etc., to provide a reliable data foundation for subsequent data analysis and management.

[0100] The health status tracking module tracks patients' health status based on patient management data and risk assessment results. By analyzing patients' long-term blood sugar data, influencing factors, and risk assessment results, it plots a health status curve, visually displaying their blood sugar control and health trends. The health status tracking module can also identify patterns in patients' health status, promptly identify potential health issues, and provide a basis for adjusting management strategies. Furthermore, the health status tracking module provides patients with health reports, helping them understand their health status and improving their self-management awareness.

[0101] The communication module serves as the bridge connecting the various system components, responsible for data transmission and communication between the cloud data server, integrated management terminal, user terminal, risk assessment module, and health status tracking module. It supports multiple communication protocols and technologies, selecting the appropriate communication method based on the needs of different modules and communication scenarios. For example, for communication between the user terminal and the communication module, wireless communication technologies such as 4G, 5G, or Wi-Fi are used, considering that the user terminal may be mobile and has power consumption requirements. For communication between the cloud data server and other modules, wired network communication technology is used due to the large data volume and high stability requirements. The communication module also needs to have security mechanisms such as data encryption, identity authentication, and access control to ensure the security and privacy of data during transmission and prevent data leakage and unauthorized access.

[0102] Example 1: Personalized management case of middle-aged male patients with type 2 diabetes

[0103] 1. Patient Basic Condition

[0104] Mr. Zhang, a 45-year-old patient, has been diagnosed with type 2 diabetes for three years. His BMI is 27.5 kg / m², and his medical history suggests hyperlipidemia. He is currently taking metformin (500 mg three times daily) combined with acarbose (50 mg three times daily). The integrated management terminal collects his fasting and postprandial blood glucose data for 72 consecutive hours using a standardized form. The baseline fasting blood glucose range is 7.8-8.5 mmol / L, and the baseline two-hour postprandial blood glucose range is 11.2-13.0 mmol / L.

[0105] 2. Collection of influencing factors and determination of priorities

[0106] Matching similar cases: The cloud-based data server used the K-means clustering algorithm to match 100 patients with similar age, BMI, and medication regimen to Mr. Zhang. It was found that dietary carbohydrate intake (38%), sedentary time (27%), and nighttime sleep duration (15%) were the main influencing factors with a correlation exceeding the threshold (0.7).

[0107] Dynamic weight calculation: The initial weights were set to diet (0.4), exercise (0.3), and sleep (0.2). Combined with Mr. Zhang's diet record of excessive daily carbohydrate intake (an average of 280g / day, far exceeding the recommended value of 200g / day) and average daily sedentary time (8.5 hours), the priority list after the dynamic weighting algorithm was adjusted was: dietary composition (0.45), exercise intensity (0.32), and sleep quality (0.23).

[0108] 3. Data Collection Plan and Terminal Configuration

[0109] Module activation sequence: The high-priority dietary composition collection module (associated with the smart diet record APP) is set to real-time sampling mode, and the food barcode needs to be scanned after each meal to enter the carbohydrate content; the exercise intensity collection module (integrated accelerometer) is set to a high-frequency sampling of 10 minutes / time to monitor sedentary time and walking steps.

[0110] Sampling parameter configuration: The sleep quality acquisition module (wrist smart bracelet) uses a basic cycle of 30 minutes. When the heart rate variability (HRV) is detected to be lower than 50ms after falling asleep, an encrypted sampling cycle of 5 minutes is triggered to record the duration of deep sleep / light sleep.

[0111] 4. Blood Glucose Change Analysis and Risk Warning

[0112] Adaptive sampling trigger: At 2:00 PM on the third day, the user terminal detected that Mr. Zhang's blood glucose change rate after a meal reached 0.8 mmol / L / 10 min (exceeding the threshold of 0.5 mmol / L / 10 min). The encrypted sampling cycle was initiated, and three consecutive blood glucose values were collected within 5 minutes (12.5 → 13.2 → 14.1 mmol / L).

[0113] Sliding window calculation: Taking carbohydrate intake (75g) at lunch (12:00-12:30) as the influencing factor, the action period was set to 2 hours, and the window length was 4 hours (10:00-14:00), it was calculated that ΔG=Σ|G(t+τ)-G(t)| / (2h-0h)= (|8.2-7.8|+|9.5-8.2|+…+|14.1-13.2|) / 2h=1.2mmol / L / h, triggering a medium-risk warning (sharp increase in blood sugar), and the user terminal pushed an intervention prompt "It is recommended to walk for 15 minutes immediately" through the APP.

[0114] 5. Weight Update and Management Strategy Generation

[0115] Calculation of time-varying weights: On the 7th day, α=0.6, Δt=1 day, ΔG_i (t) caused by dietary factors on that day=1.8mmol / L, total ΔG_j (t) of all factors=2.5mmol / L, historical weight W_i (t-Δt)=0.45, then the updated dietary weight W_i(t)=0.6×(1.8 / 2.5)+(1-0.6)×0.45=0.432+0.18=0.612.

[0116] Management strategy generation: The weight threshold is set to 0.1, and diet (0.612) and exercise (0.285) are the main intervention factors. The cloud strategy database retrieves the corresponding intervention plan:

[0117] Dietary intervention: Develop a low-carbohydrate diet plan (daily carbohydrate ≤ 180g) and recommend a list of foods with a GI value of < 55;

[0118] Exercise intervention: Set a sedentary reminder (stand for 3 minutes every hour) and accumulate 30 minutes of moderate-intensity exercise every day (such as brisk walking).

[0119] Example 2: Dynamic management of elderly female patients with type 1 diabetes

[0120] 1. Patient Basic Condition

[0121] The patient, 68-year-old Grandma Li, had a 10-year history of type 1 diabetes and hypertension. She used an insulin pump (basal rate of 0.5 U / h, with bolus doses calculated based on carbohydrate intake). The integrated management terminal collected her blood sugar data for 72 consecutive hours. The baseline fasting blood sugar range was 6.5-7.2 mmol / L, with a nighttime nadir of 3.8 mmol / L (at 2:00 AM).

[0122] 2. Collection of influencing factors and determination of priorities

[0123] Similar case matching: The cloud data server matched 80 elderly patients with type 1 diabetes through a hierarchical clustering algorithm and found that the insulin pump basal rate setting (correlation 0.85), nighttime sleep apnea index (correlation 0.78), and medication compliance (insulin injection standardization, correlation 0.72) were the main influencing factors.

[0124] Dynamic weight calculation: The initial weights were set to insulin (0.5), sleep (0.3), and compliance (0.2). Combined with Grandma Li's nocturnal hypoglycemia record and mild sleep apnea (AHI = 12 times / hour) shown by sleep monitoring, the adjusted priority list was: insulin basal rate (0.55), sleep quality (0.3), and medication compliance (0.15).

[0125] 3. Data Collection Plan and Terminal Configuration

[0126] Module activation sequence: The insulin basal rate acquisition module (which directly reads the insulin pump setting parameters) is set to real-time synchronization mode, updating the basal rate and high-dose data every 15 minutes; the sleep quality acquisition module (with integrated blood oxygen saturation sensor) uses a basal cycle of 15 minutes. When the blood oxygen saturation is less than 90% for 5 minutes, an encrypted sampling cycle of 1 minute is triggered.

[0127] Abnormal value threshold setting: The abnormal value judgment threshold of blood glucose data is set to <3.9mmol / L (hypoglycemia) and >16.7mmol / L (hyperglycemia), and the abnormal fluctuation threshold of insulin pump basal rate is set to ±0.1U / h (compared with the same period of the previous day).

[0128] 4. Blood Glucose Change Analysis and Risk Warning

[0129] Adaptive sampling trigger: At 1:30 a.m. on the 5th day, the user terminal detected that Grandma Li's blood sugar dropped from 5.2mmol / L to 4.1mmol / L (rate of change 0.7mmol / L / 15min), and the blood oxygen saturation was 90% (lasting 10 minutes). The encrypted sampling cycle started, and blood sugar was collected every 1 minute (4.1→3.9→3.8mmol / L).

[0130] Sliding window calculation: Taking the nighttime basal insulin rate (0.5 U / h) as the influencing factor, the action cycle is set to 4 hours (23:00-3:00), and the window length is 8 hours (21:00-5:00). The calculation result is ΔG=Σ|G(t+τ)-G(t)| / (4h-0h)= (|5.8-6.2|+|5.2-5.8|+…+|3.8-4.1|) / 4h=0.6mmol / L / h. Triggering a high-risk warning (hypoglycemia combined with sleep apnea), the user terminal simultaneously activates the sound and light alarm, and sends an emergency notification to the family's mobile phone.

[0131] 5. Weight Update and Management Strategy Generation

[0132] Calculation of time-varying weights: On the 10th day, α = 0.4 (the elderly pay more attention to the stability of historical data), Δt = 12 hours, ΔG_i (t) caused by insulin factors on that day = 1.0 mmol / L (hypoglycemia event), total ΔG_j (t) = 1.5 mmol / L, historical weight W_i (t-Δt) = 0.55, then the updated insulin weight W_i(t) = 0.4×(1.0 / 1.5)+(1-0.4)×0.55≈0.267+0.33=0.597.

[0133] Management strategy generation: The weight threshold is set to 0.1, and insulin (0.597) and sleep (0.28) are the main intervention factors. The cloud strategy database retrieves the corresponding intervention plan:

[0134] Insulin intervention: Lower the basal rate to 0.4 U / h between midnight and 3:00 a.m. and set the hypoglycemia warning threshold at 4.5 mmol / L (to trigger intervention in advance);

[0135] Sleep intervention: It is recommended to wear a home non-invasive ventilator, avoid large-dose insulin injections 2 hours before bedtime, and adjust the nighttime blood sugar monitoring cycle to 30 minutes / time.

Claims

1. A method for managing diabetic patient data based on big data, characterized in that: The steps include: Step 1: The integrated management terminal collects the patient's basic information and blood glucose data in a stable state. Based on the patient's basic information, the cloud data server obtains the patient's blood glucose influencing factors. Based on the patient's blood glucose influencing factors, the corresponding influencing factor data collection module information is obtained to generate the influencing factor data collection plan for the corresponding patient. Step 2: Based on the data collection plan for the influencing factors of the corresponding patient, a user terminal for the corresponding patient is generated, the integrated management terminal generates a patient data management container, and communicates with the user terminal of the corresponding patient to send the patient's blood glucose data in a stable state to the patient data management container; Step 3: The user terminal corresponding to the patient collects the patient's blood glucose data and influencing factor data according to the collection cycle, and obtains the degree of change in the blood glucose data at the start and end times of the influencing factor based on the blood glucose data and the influencing factor data; a risk warning is issued based on the degree of change in the blood glucose data, and the influencing factor data and the degree of change in the blood glucose data at the start and end times of the influencing factor are sent to the patient data management container; Step 4: The patient data management container obtains the weight of the influencing factor affecting the blood sugar data based on the influencing factor data obtained in different periods and the degree of change in the blood sugar data at the start and end times of the influencing factor; Step 5: Generate a patient blood glucose management strategy based on the weights of the various influencing factors affecting blood glucose data, and complete the data management of diabetic patients; The patient data management container obtains the weight of the influencing factors affecting the blood sugar data based on the influencing factor data obtained in different periods and the degree of change in the blood sugar data at the start and end times of the influencing factors, including: The time-varying weight calculation model is used to calculate the weights of factors affecting blood glucose data, and the weights are updated as follows: W_i(t) = α·ΔG_i(t) / ΣΔG_j(t) + (1-α)·W_i(t-Δt) Where α is the forgetting factor (0<α<1), Δt is the update cycle; W_i(t) is the dynamic influence weight of influencing factor i on blood glucose data at time t, which represents the contribution ratio of the i-th influencing factor to blood glucose fluctuations at time t, and the sum of the weights of all influencing factors ΣW_i(t)=1; ΔG_i(t) is the blood glucose change caused by influencing factor i at time t; ΣΔG_j(t) is the total blood glucose change caused by all influencing factors at time t; W_i(t-Δt) is the historical weight of influencing factor i in the previous calculation cycle (t-Δt).

2. The method for managing diabetic patient data based on big data according to claim 1, characterized in that: The integrated management terminal collects the patient's basic information and blood sugar data in a stable state, and obtains the patient's blood sugar influencing factors on the cloud data server based on the patient's basic information, including: Collect patient identity information, medical history, medication records, and fasting / postprandial blood glucose baseline values for n consecutive hours through standardized forms; The patient database of the cloud data server is called to match similar cases and obtain a set of influencing factors with a correlation greater than a threshold with the current patient's blood sugar fluctuation. The influencing factors include: dietary composition, exercise intensity, sleep quality, medication compliance, environmental temperature and humidity, and mood swing indicators; A priority list of individualized influencing factors for patients is established, wherein the priority is calculated by a dynamic weighting algorithm, and the initial weight is a preset value.

3. The method for managing diabetic patient data based on big data according to claim 1, characterized in that: The method of obtaining corresponding influencing factor data acquisition module information based on the patient's blood sugar influencing factors and generating the influencing factor data acquisition plan for the corresponding patient includes: Construct a module configuration mapping table to associate each type of influencing factor with the corresponding acquisition module; generate an acquisition module activation sequence based on the priority list, and set the high-priority acquisition module to high-frequency sampling mode; and generate an acquisition module configuration file, including sampling frequency, data format standard, and outlier judgment threshold.

4. The method for managing diabetic patient data based on big data according to claim 1, characterized in that: The user terminal corresponding to the patient collects the patient's blood sugar data and influencing factor data according to the collection period, and obtains the degree of change of the blood sugar data at the start and end times of the influencing factor based on the blood sugar data and the influencing factor data, including: Adopting an adaptive sampling cycle: the basic cycle is a first set duration, and when it is detected that the blood sugar change rate exceeds the change rate threshold, encrypted sampling is performed, and the encrypted sampling cycle is a second set duration, and the second set duration is less than the first set duration; The sliding window algorithm is used to calculate the degree of change. The window length is set to twice the period of the influencing factor. The degree of change is: ΔG = Σ|G(t+τ)-G(t)| / (τ_max - τ_min) Where G(t) is the blood glucose value and τ is the duration of the influencing factor.

5. The method for managing diabetic patient data based on big data according to claim 1, characterized in that: The risk warning according to the degree of change in blood sugar data includes: According to the degree of change in blood sugar data, the corresponding early warning strategy is called on the cloud data server, and the patient is warned according to the early warning strategy.

6. The method for managing diabetic patient data based on big data according to claim 1, characterized in that: The method of generating a patient blood glucose management strategy based on the weights of the various influencing factors affecting the blood glucose data includes: According to the weight of the influencing factors affecting blood glucose data, a priority list of influencing factor interventions is generated. For the influencing factors whose weights are greater than the weight threshold, the corresponding intervention strategies are obtained from the cloud data server. The intervention strategies corresponding to the influencing factors whose weights are greater than the weight threshold constitute the patient's blood glucose management strategy.

7. A diabetes patient data management system based on big data, characterized in that: The method for managing diabetic patient data based on big data according to any one of claims 1 to 6 is applied, comprising a cloud data server, an integrated management terminal, a communication module, a user terminal, a risk assessment module, and a health status tracking module; The cloud data server, integrated management terminal, user terminal, risk assessment module, and health status tracking module are respectively connected to the communication module for communication; The cloud data server is used to provide a patient database and a policy database; The integrated management terminal is used to customize the influencing factor data acquisition module in the user terminal according to the influencing factors of the patient's health data, and to manage the user management data and the user terminal; The user terminal is used to collect patient management data; The risk assessment module is used to perform risk assessment based on the patient's management data; the risk assessment includes a health risk assessment module and a data integrity assessment; The health status tracking module is used to track the patient's health status based on patient management data and risk assessment.

8. The big data-based diabetes patient data management system according to claim 7, characterized in that: The user terminal includes an influencing factor data acquisition module, an identity information module, a location information acquisition module, a management data generation module, a data processing module and a communication device; The influencing factor data acquisition module, identity information module, location information acquisition module, management data generation module and communication device are respectively connected to the data processing module; The influencing factor data acquisition module is used to collect data on influencing factors that affect the patient's blood sugar index; The identity information collection module is used to collect the patient's identity information; The location information acquisition module is used to acquire the patient's location; The management data generation module is used to generate user health management data based on the data collected by the user terminal during the management period.

Images