Chronic disease index early warning notification method, system, equipment and medium

Abstract

The invention provides a chronic disease index early warning notification method, system and device and a medium, and belongs to the technical field of medical information. The method comprises the following steps: configuring and dynamically updating normal value ranges of health index items of different chronic disease types and crowd classifications, and generating versioned rule configuration data; receiving health index data uploaded by a patient, and performing data cleaning and standardization processing based on verification rules to generate standardized index time sequence data; matching from the rule configuration data through a rule matching engine based on the patient file data and the versioned rule configuration data, and generating personalized range reference data; performing comparative analysis on the standardized index time sequence data and the personalized range reference data to generate anomaly recognition result data; and based on the abnormal identification result data, generating structured early warning information in combination with historical data of the patient, and sending the structured early warning information to an information terminal of a responsible doctor through a multi-channel distribution strategy. According to the invention, the accuracy and timeliness of the chronic disease medical service are obviously improved.

Description

Technical Field

[0001] This invention belongs to the field of medical information technology, and more specifically relates to a method, system, device and medium for early warning notification of chronic disease indicators. Background Technology

[0002] With the accelerating aging of the population and changes in residents' lifestyles, the prevalence of chronic diseases such as hypertension, diabetes, hyperlipidemia, coronary heart disease, stroke, chronic obstructive pulmonary disease (COPD), chronic kidney disease, and cancer continues to rise, becoming a major public health issue seriously affecting people's health and quality of life. Against this backdrop, medical institutions at all levels have successively established chronic disease management information systems, aiming to track and manage patients' health indicators over the long term.

[0003] However, existing chronic disease management systems have revealed significant limitations in practical applications. Most current systems remain at the level of data collection and storage, primarily recording patient health indicators and performing basic statistical functions, generally lacking effective intelligent early warning mechanisms. These systems cannot automatically identify and assess risks associated with collected abnormal data, making it difficult for healthcare professionals to promptly grasp changes in patients' conditions. This passive data management model severely restricts the efficiency and effectiveness of chronic disease management.

[0004] More significantly, existing technological solutions rely excessively on manual judgment. Healthcare professionals must manually sift through massive amounts of patient data to identify abnormal indicators. This process is not only inefficient but also highly susceptible to overlooking crucial abnormalities due to visual fatigue or negligence. Furthermore, the lack of real-time alerts creates a significant time delay between the detection of abnormalities and the implementation of interventions, often resulting in missed opportunities for optimal treatment and increased health risks for patients.

[0005] Furthermore, existing systems have significant shortcomings in their early warning rule settings. Most systems use a uniform early warning threshold, failing to fully consider the diverse needs of different disease types, disease stages, and population characteristics. This rigid early warning rule leads to a large number of false alarms or missed alarms in actual operation, reducing the reliability of early warning information and affecting the normal work efficiency of medical staff. Summary of the Invention

[0006] To address the above problems, the present invention aims to provide a method, system, device, and medium for early warning notification of chronic disease indicators. By constructing a complete technical system encompassing versioned rule configuration, standardized data processing, intelligent rule matching, multi-dimensional anomaly analysis, and multi-channel early warning distribution, the invention achieves precise, automated, and intelligent management of early warning of chronic disease indicators from data collection to information delivery.

[0007] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, embodiments of this application provide a method for early warning notification of chronic disease indicators, including: Configure and dynamically update the normal value ranges of health indicator items for different types of chronic diseases and population categories, and generate versioned rule configuration data; Receive health indicator data uploaded by patients, perform data cleaning and standardization based on preset verification rules, and generate standardized indicator time series data; Based on patient record data and versioned rule configuration data, a rule matching engine is used to match the rule configuration data to generate personalized range reference data; The standardized indicator time series data is compared and analyzed with the personalized range reference data to generate anomaly identification result data; Based on the anomaly identification results, structured early warning information is generated by combining the patient's historical data and sent to the responsible doctor's information terminal through a multi-channel distribution strategy.

[0008] In an optional implementation, configuring and dynamically updating the normal value ranges of health indicator items for different chronic disease types and population categories, and generating versioned rule configuration data, includes: The system receives rule configuration data input by the administrator through a graphical user interface. The rule configuration data includes chronic disease type, population classification, health indicator triplet and normal value range parameters for each health indicator. The rule configuration data is persistently stored in a versioned configuration table of a relational database, and a time series of the configuration data is established through the version number field; When the rule configuration data is updated, the version number is automatically incremented and the new version of the rule configuration data is marked as effective, while the rule configuration data of the previous version is retained. The update event of the rule configuration data is broadcast to all relevant service nodes through the message queue, triggering each service node to synchronously update the rule cache data in memory.

[0009] In one optional implementation, the step of receiving health indicator data uploaded by patients, performing data cleaning and standardization processing based on preset verification rules, and generating standardized indicator time-series data includes: Receive health indicator data uploaded by patients through the RESTful API interface, and extract the patient ID, the patient's health indicator items, the health indicator values ​​and the measurement timestamp. Based on the health indicator data, verify the integrity of the data structure of the health indicator data, and verify the rationality of the health indicator values; Standardization transformation is performed on the verified health indicator data. The data parser extracts the health indicator values ​​and their unit information from the health indicator data. The unit conversion formula is used to convert the health indicator values ​​from different sources into standard units of measurement. The time formatting tool is used to convert the measurement timestamps into the ISO 8601 standard format. The code mapping table maps the health indicator item names to the preset internal standard codes to generate standardized indicator data. Standardized indicator data are organized and stored in a time series database according to time series, forming complete standardized indicator time series data.

[0010] In an optional implementation, the step of generating personalized range reference data by matching patient record data and versioned rule configuration data through a rule matching engine from the rule configuration data includes: Based on standardized time-series data, obtain the patient ID and the patient's health indicator items; Based on the patient ID, query the patient record database to obtain the patient's complete disease diagnosis information and population classification tags as patient attribute data; Combine patient attribute data with patient health indicators to construct composite query conditions that include disease type, population classification, and patient health indicators; By using composite query conditions, the system first queries the rule cache data in the local service node. If the cache is not hit, it queries the versioned rule configuration data in the relational database to obtain the normal value range of the health indicator items corresponding to the patient's health indicator items, and generates personalized range reference data including upper and lower limits and applicable conditions.

[0011] In an optional implementation, the step of comparing and analyzing standardized indicator time-series data with personalized range reference data to generate anomaly identification result data includes: The health indicator values ​​of patients' health indicators are extracted from the standardized indicator time series data and used as the comparison indicator values; the upper and lower limits of the normal range of the corresponding health indicator items are extracted from the personalized range reference data. The numerical range comparator compares the value of the indicator to be compared with the normal range of the corresponding health indicator in real time; the trend analysis algorithm queries the historical data of the same health indicator from the time series database to calculate the short-term change rate; and the correlation analyzer is used to check the abnormal coordination of multiple related indicators of the value of the indicator to be compared. When the value of the indicator to be compared exceeds the normal range of the corresponding health indicator, the corresponding health indicator of the patient is regarded as an abnormal indicator and the abnormality level is marked as primary abnormality. When the abnormality level of an abnormal indicator item is primary abnormality and the corresponding short-term rate of change exceeds the threshold, the abnormality level is upgraded to intermediate abnormality. When the anomaly level of an abnormal indicator item is medium-level and multiple related indicators are abnormal at the same time, the anomaly level is upgraded to high-level composite anomaly. The patient ID, abnormal indicator items, corresponding abnormality levels, and measurement timestamps are encapsulated to generate abnormality identification result data.

[0012] In an optional implementation, the step of generating structured early warning information based on anomaly identification results data and combining it with patient historical data, and sending it to the responsible physician's information terminal through a multi-channel distribution strategy, includes: Based on the anomaly identification results, the patient record database is queried by patient ID to obtain basic patient information; relevant historical indicator data is extracted from the time series database according to the abnormal indicator items and measurement timestamps. Based on the anomaly level in the anomaly identification results data, select the corresponding early warning information template; The data binding device links and integrates patient basic information with abnormal identification results to generate integrated data. Generate trend charts of indicator changes based on historical indicator data using a trend analyzer. The integrated data is filled into a template format corresponding to the abnormality level by a template rendering engine, and an early warning information data packet is output. The early warning information data packet includes basic patient information, details of abnormal indicators, comparison of normal value ranges, indicator change trend chart, data reporting time and abnormality level. The warning information data packets are pushed to the online information terminal of the responsible doctor in real time through the WebSocket connection manager; at the same time, the warning information data packets are converted into a unified message format and delivered to the message queue through the message serialization processor; the message queue consumer service calls the SMS gateway API, WeChat API and email server SMTP protocol respectively to send the message to the mobile information terminal of the responsible doctor synchronously.

[0013] In one optional implementation, the chronic disease types include hypertension, diabetes, hyperlipidemia, coronary heart disease, stroke, chronic obstructive pulmonary disease, chronic kidney disease, and tumors; the population classification includes high-risk groups for chronic diseases and people diagnosed with chronic diseases; the health indicators include diastolic blood pressure, systolic blood pressure, fasting blood glucose, blood glucose one hour after a meal, blood glucose two hours after a meal, blood glucose three hours after a meal, total cholesterol, and blood oxygen saturation.

[0014] Secondly, embodiments of this application also provide a chronic disease indicator early warning notification system, including: The dynamic rule configuration module is used to configure and dynamically update the normal value range of health indicator items for different types of chronic diseases and population categories, and generate versioned rule configuration data. The indicator data standardization module is used to receive health indicator data uploaded by patients, perform data cleaning and standardization processing based on preset verification rules, and generate standardized indicator time series data. The personalized rule matching module is used to generate personalized range reference data by matching patient record data and versioned rule configuration data through the rule matching engine. The anomaly identification and analysis module is used to compare and analyze standardized indicator time series data with personalized range reference data to generate anomaly identification result data. The early warning distribution processing module is used to generate structured early warning information based on the anomaly identification results data and combined with the patient's historical data, and send it to the information terminal of the responsible doctor through a multi-channel distribution strategy.

[0015] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the chronic disease indicator early warning notification method as described in any of the above.

[0016] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the chronic disease indicator early warning notification method as described in any of the above.

[0017] As can be seen from the above technical solutions, the present invention has the following advantages: The chronic disease indicator early warning notification method provided in this application achieves real-time synchronization and maintenance of medical standard data by establishing a versioned dynamic rule configuration system; it ensures the quality and consistency of multi-source heterogeneous health indicator data by adopting multi-layer data verification and standardized processes; it generates personalized reference ranges based on individual patient characteristics through intelligent rule matching, improving the accuracy of early warning; it achieves intelligent determination of abnormality levels by using a multi-dimensional anomaly analysis mechanism combined with real-time numerical comparison, trend analysis, and collaborative detection of related indicators; and it ensures that different levels of abnormal information are delivered to the responsible physician in a timely and accurate manner through templated early warning information assembly and multi-channel intelligent distribution strategies. This constructs a fully automated and intelligent closed loop for chronic disease management from data collection to early warning delivery, significantly improving the efficiency and quality of medical services.

[0018] This application establishes a multi-layered data verification mechanism and a standardized processing flow, which enables effective cleaning and standardized transformation of multi-source heterogeneous health indicator data, significantly improving data quality and consistency between systems, and providing a reliable data foundation for subsequent analysis.

[0019] This application, based on the composite query conditions of patient attribute data and indicator items, and through a cache-first rule matching strategy, achieves efficient transformation from general rule configuration to individualized reference range, and constructs a precise personalized data processing pipeline.

[0020] This application adopts a multi-engine collaborative analysis architecture, including real-time comparison of numerical range comparators, time-series data processing of trend analysis algorithms, and multi-indicator collaborative detection of correlation analyzers, forming a three-dimensional analysis system covering static thresholds, dynamic trends, and correlation relationships, which greatly improves the accuracy and comprehensiveness of anomaly identification.

[0021] This application establishes a complete data processing pipeline, from data reception, standardization processing, rule matching, anomaly analysis to early warning generation, realizing fully automated data flow, effectively reducing manual intervention, and significantly improving data processing efficiency and system response speed.

[0022] This application adopts standardized data interface specifications, modular data processing components, and a unified data storage architecture, supporting the rapid integration of new disease rules, new indicators, and new analysis modules, and providing a flexible data processing infrastructure for the continuous evolution and functional expansion of the system. Attached Figure Description

[0023] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating the chronic disease indicator early warning notification method provided in this application.

[0025] Figure 2 This is a schematic diagram of the structure of the chronic disease indicator early warning and notification system provided in this application.

[0026] Figure 3 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0027] The various embodiments of this disclosure will be described more fully in the detailed steps of the chronic disease indicator early warning notification method described below. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0028] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] Please see Figure 1 The diagram shows a flowchart of a chronic disease indicator early warning notification method in a specific embodiment. The method includes: S1: Configure and dynamically update the normal value range of health indicators for different types of chronic diseases and population categories, and generate versioned rule configuration data.

[0031] In this specific implementation, the core of this step lies in establishing a dynamically maintainable and version-managed indicator rule configuration system. First, a graphical user interface provides administrators with an intuitive configuration entry point. Administrators can select chronic disease types such as hypertension, diabetes, hyperlipidemia, coronary heart disease, stroke, chronic obstructive pulmonary disease, chronic kidney disease, and tumors; different population categories such as high-risk groups for chronic diseases and diagnosed chronic disease patients; and specific health indicators such as diastolic blood pressure, systolic blood pressure, fasting blood glucose, blood glucose one hour after meals, blood glucose two hours after meals, blood glucose three hours after meals, total cholesterol, and blood oxygen saturation. For each combination, corresponding normal value range parameters are set. These inputs, after being validated through a front-end form, are transmitted to the back-end service in JSON format as rule configuration data.

[0032] The backend service employs a versioned storage strategy to process received rule configuration data. Specifically, the rule configuration data is persistently stored in a versioned configuration table in a relational database such as MySQL. This table includes key fields such as version number, effective status, and creation timestamp, using the version number field to establish a time series of the configuration data. Each time a configuration is added or modified, the existing record is not directly overwritten; instead, a new version record is inserted, and the version number is automatically incremented. Simultaneously, the new version of the rule configuration data is marked as effective, while historical versions of the rule configuration data are retained.

[0033] For example, the backend service uses a versioned storage strategy to process the received rule configuration data. In terms of specific implementation, a `rule_configuration` table is created in the MySQL database using JPA entities. The table structure includes fields such as `id`, `version`, `disease_type`, `population_type`, `indicator_code`, `min_value`, `max_value`, `is_active`, and `create_time`. Optimistic locking is implemented using the `@Version` annotation to control version conflicts. Each time a configuration is added or modified, the system checks the current version number, inserts a new record with an incrementing version number, updates the `is_active` status, and retains historical version records for auditing and traceability.

[0034] To ensure the consistency of configuration data across service nodes, a configuration update event is generated when rule configuration data is updated. This event is broadcast to all relevant service nodes via a message queue such as RabbitMQ. Service nodes subscribed to this event automatically retrieve the latest effective version of the configuration data from the database after consuming the event, triggering all service nodes to synchronously update the rule cache data in their in-memory caches. This mechanism effectively avoids rule matching errors caused by inconsistent caches across nodes, ensuring the real-time performance and accuracy of the data.

[0035] For example, when the rule configuration data is updated, the event after the transaction is committed is listened to through the @EventListener annotation, and the RuleConfigUpdateEvent is published to the rule-config-update-exchange exchange. All service nodes that subscribe to this message consume the message through the @RabbitListener annotation, triggering each service node to synchronously update the data in its local Caffeine cache.

[0036] S2: Receives health indicator data uploaded by patients, performs data cleaning and standardization processing based on preset verification rules, and generates standardized indicator time series data.

[0037] In this specific implementation, this step is responsible for processing the raw indicator data from the patient's end, transforming it into high-quality, standardized time-series data usable by the system. Specifically, the data receiving layer uses a RESTful API interface as a unified entry point to receive health indicator data uploaded from the patient's terminal. Key information such as the patient ID, health indicator items, health indicator values, and measurement timestamps are extracted from the data packets.

[0038] Upon receiving the raw data, a data cleaning pipeline is immediately executed based on preset verification rules. The first step is data verification, which includes verifying the integrity of the health indicator data structure and the reasonableness of the health indicator values. Data that fails verification is logged and an error response is immediately returned.

[0039] At this point, a standardization transformation is performed on the verified health indicator data. A data parser extracts the health indicator values ​​and their units from the data, and a unit conversion formula is used to uniformly convert health indicator values ​​from different sources into standard units of measurement. Simultaneously, a time formatting tool is used to uniformly convert measurement timestamps to the ISO 8601 standard format, and a coding mapping table is used to uniformly map health indicator item names to preset internal standard codes, ultimately generating standardized indicator data.

[0040] For example, the data cleaning phase can employ the chain of responsibility pattern, constructing a cleaning pipeline that includes multiple processors such as NullValueFilter, RangeValidator, and UnitConverter. Specifically, this includes: using UnitUtils in Apache Commons Lang for unit conversion, using Java 8 DateTimeFormatter to uniformly convert various time formats to the ISO 8601 standard format, and standardizing indicator names using a pre-loaded indicator encoding mapping table (stored in a Redis hash table).

[0041] After the above processing, the standardized indicator data is organized and stored in a time series database such as InfluxDB, forming complete standardized indicator time series data, which provides a solid data foundation for subsequent data analysis.

[0042] S3: Based on patient record data and versioned rule configuration data, a rule matching engine is used to match the rule configuration data to generate personalized range reference data.

[0043] In this specific implementation, the aim of this step is to dynamically match a unique normal range for each patient's specific indicator. When it is necessary to process a certain indicator for a particular patient, the patient ID and the specific health indicator item are first obtained based on the standardized indicator time series data.

[0044] At this point, based on the patient ID, the patient record database is queried to obtain the patient's complete disease diagnosis information and population classification tags, which serve as patient attribute data. Then, the patient attribute data is combined with health indicator items to construct composite query conditions that include disease type, population classification, and health indicator items.

[0045] For example, based on the patient ID, MyBatis Plus is used to query the patient_profile table in the patient profile database to obtain the patient's complete disease diagnosis information and population classification labels as patient attribute data. Then, the patient attribute data is combined with health indicator items to construct a composite query condition that includes disease type (e.g., hypertension), population classification (e.g., confirmed cases), and health indicator item (e.g., systolic blood pressure).

[0046] In this step, the rule matching engine first queries the rule cache data in the local service node using the composite query conditions. If the cache is not found, it queries the versioned rule configuration data in the relational database to obtain the normal value range of the corresponding health indicator item. After a successful match, the engine generates personalized range reference data containing upper and lower limits and applicable conditions, providing a benchmark for the next step of comparative analysis.

[0047] For example, the `opsForHash` method of `RedisTemplate` is first used to query the rule cache data in the local service node, with the key format `rule_config:hypertension:confirmed population:systolic blood pressure`. If the cache is not found, the versioned rule configuration table in the relational database is queried using the `Select` annotation of `MyBatis`, adding the WHERE condition `disease_type` equal to hypertension, `population_class` equal to confirmed population, `indicator_code` equal to systolic blood pressure, and `is_active` set to true, to obtain the normal value range of the corresponding health indicator item. After a successful match, the engine generates a `PersonalizedRange` object containing upper and lower limits such as `minValue` of 90, `maxValue` of 140, and applicable conditions, providing a benchmark for the next comparative analysis.

[0048] S4: Compare and analyze the standardized indicator time series data with the personalized range reference data to generate anomaly identification result data.

[0049] In a specific implementation, this step is the core of the early warning decision-making process, identifying and evaluating abnormal indicators through multi-level judgment logic. The comparison analyzer first extracts health indicator values ​​from standardized indicator time-series data as the indicator values ​​to be compared, and at the same time extracts the corresponding upper and lower limits of the normal value range from personalized range reference data.

[0050] At this point, the core comparison operation is performed through a numerical range comparator, which compares the value of the indicator to be compared with the normal range in real time. When the indicator value exceeds the normal range, an advanced analysis process is initiated: a trend analysis algorithm is used to query historical data from the time series database to calculate the short-term rate of change, and a correlation analyzer is used to check for abnormal coordination among multiple related indicators.

[0051] For example, the core comparison operation is performed using a custom numerical range comparator, NumericRangeComparator. This uses simple numerical comparison logic to mark an anomaly if the value is less than the minimum or greater than the maximum. The values ​​of the indicators to be compared are compared to the normal range in real time. When an indicator value exceeds the normal range, an advanced analysis process is initiated: a linear regression-based trend analysis algorithm is used to query historical data from the InfluxDB time-series database over the past 7 days to calculate the short-term rate of change, the Slope calculation formula is used, and an Apriori-based correlation analyzer is employed to examine abnormal correlations between multiple related indicators, such as systolic and diastolic blood pressure.

[0052] In this step, a three-tiered anomaly detection mechanism was established: when an indicator exceeds the normal range, it is marked as a primary anomaly; when a primary anomaly occurs and the short-term rate of change exceeds a threshold, it is upgraded to an intermediate anomaly; when an intermediate anomaly occurs and multiple related indicators are simultaneously abnormal, it is upgraded to a high-level composite anomaly. Finally, the patient ID, abnormal indicator item, anomaly level, and measurement timestamp are encapsulated to generate anomaly identification result data.

[0053] For example, when an indicator exceeds the normal range (e.g., 145 > 140), it is marked as a primary abnormality (LEVEL_1). When a primary abnormality occurs and the short-term rate of change exceeds a threshold (e.g., the daily average rate of change is greater than 10%), it is upgraded to an intermediate abnormality (LEVEL_2). When an intermediate abnormality occurs and multiple related indicators are simultaneously abnormal (e.g., both systolic and diastolic blood pressure are abnormal), it is upgraded to a high-level composite abnormality (LEVEL_3). Finally, the patient ID, abnormal indicator item, abnormality level, and measurement timestamp are encapsulated to generate an AbnormalResult object. This object is constructed using the Builder pattern to ensure immutability and thread safety.

[0054] S5: Based on the anomaly identification results data, combined with the patient's historical data, structured early warning information is generated and sent to the responsible doctor's information terminal through a multi-channel distribution strategy.

[0055] In this specific implementation, this step is responsible for converting abnormal results into actionable alerts and delivering them to the responsible physician. First, basic information is obtained by querying the patient's file using the patient ID. Then, historical indicator data is extracted from the time-series database based on the abnormal indicator items and measurement timestamps. Finally, a trend analysis tool is used to generate a trend chart of indicator changes.

[0056] Then, based on the abnormality level, the corresponding early warning information template is selected. The patient's basic information and abnormality identification results are integrated through the data binder. The integrated data is then filled into the template format through the template rendering engine, and a complete early warning information data package containing the patient's basic information, details of abnormal indicators, comparison of normal value ranges, trend chart, reporting time and abnormality level is output.

[0057] In the multi-channel distribution phase, a WebSocket connection manager pushes alert information to doctors' online terminals in real time; simultaneously, a message serializer converts the information into a unified format and delivers it to a message queue. The message queue's consumer services operate in parallel, calling the SMS gateway API, WeChat API, and email server SMTP protocol to synchronously send alert information to the responsible doctor's mobile terminal, ensuring reliable information delivery.

[0058] For example, in the multi-channel distribution phase, Spring WebSocket's SimpMessagingTemplate pushes alert information to doctors' online terminals in real time, with the destination being ` / topic / alert / ` followed by the doctor's ID. Simultaneously, the Jackson library serializes the information into a unified format before delivering it to the RabbitMQ message queue. The message queue's consumer services work in parallel: the SMS consumer calls the Alibaba Cloud SMS API, using `DefaultProfile` to configure the access key; the WeChat consumer calls the Enterprise WeChat Webhook API, using `RestTemplate` to send a JSON request; and the email consumer connects to the SMTP server via JavaMailSender to send HTML emails, synchronously sending alert information to the responsible doctor's mobile terminal, ensuring reliable information delivery. Each consumer service uses the `@RabbitListener` annotation to listen to a specific queue and implements a retry mechanism to guarantee message reliability.

[0059] In this embodiment, by establishing a versioned and dynamically updatable rule configuration system, combined with multi-level data cleaning, standardization processing, and intelligent rule matching mechanisms, accurate monitoring of health indicators for multiple diseases and populations is achieved. A three-level anomaly early warning system is constructed using real-time comparison, trend analysis, and correlation judgment algorithms. Through a multi-channel asynchronous distribution strategy, the automation level, early warning accuracy, and real-time performance of chronic disease management are significantly improved, effectively reducing the burden of manual monitoring and providing doctors with timely, comprehensive, and tiered decision support.

[0060] like Figure 2As shown, the following are embodiments of the chronic disease indicator early warning notification system provided in this disclosure. This system and the chronic disease indicator early warning notification methods in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the chronic disease indicator early warning notification system, please refer to the embodiments of the chronic disease indicator early warning notification methods described above.

[0061] A chronic disease indicator early warning and notification system includes: The dynamic rule configuration module is used to configure and dynamically update the normal value range of health indicators for different types of chronic diseases and population categories, and generate versioned rule configuration data.

[0062] The indicator data standardization module is used to receive health indicator data uploaded by patients, perform data cleaning and standardization processing based on preset verification rules, and generate standardized indicator time series data.

[0063] The personalized rule matching module is used to generate personalized range reference data by matching patient record data and versioned rule configuration data through the rule matching engine.

[0064] The anomaly identification and analysis module is used to compare and analyze standardized indicator time-series data with personalized range reference data to generate anomaly identification results data.

[0065] The early warning distribution processing module is used to generate structured early warning information based on the anomaly identification results data and combined with the patient's historical data, and send it to the information terminal of the responsible doctor through a multi-channel distribution strategy.

[0066] The chronic disease indicator early warning notification system provided in this embodiment establishes a versioned rule configuration and dynamic update mechanism, realizing unified management of medical standard data; it adopts multi-layer verification and standardized processing procedures to ensure the quality consistency of multi-source heterogeneous data; it generates personalized reference ranges based on an intelligent rule matching engine, improving the accuracy of early warning; it realizes intelligent judgment of anomaly level through a multi-dimensional anomaly analysis model; and finally, it constructs a complete closed loop for early warning information processing by means of template assembly and multi-channel distribution mechanism, significantly improving the intelligence level of chronic disease management and the efficiency of medical services.

[0067] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0068] The chronic disease indicator early warning notification method provided in this application embodiment can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0069] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0070] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0071] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0072] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0073] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0074] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0075] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0076] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0077] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0078] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0079] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0080] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0081] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0082] The aforementioned electronic device realizes the chronic disease indicator early warning notification method of this application by constructing a full-process technical system covering versioned rule configuration, standardized data processing, intelligent rule matching, multi-dimensional anomaly analysis and multi-channel early warning distribution, thus achieving the beneficial effect of realizing accurate, automated and intelligent management of chronic disease indicator early warning.

[0083] The storage medium provided in this application stores a program product capable of implementing a method for early warning and notification of chronic disease indicators.

[0084] Methods for issuing early warnings about chronic disease indicators include: Configure and dynamically update the normal value ranges of health indicator items for different types of chronic diseases and population categories, and generate versioned rule configuration data; Receive health indicator data uploaded by patients, perform data cleaning and standardization based on preset verification rules, and generate standardized indicator time series data; Based on patient record data and versioned rule configuration data, a rule matching engine is used to match the rule configuration data to generate personalized range reference data; The standardized indicator time series data is compared and analyzed with the personalized range reference data to generate anomaly identification result data; Based on the anomaly identification results, structured early warning information is generated by combining the patient's historical data and sent to the responsible doctor's information terminal through a multi-channel distribution strategy.

[0085] In some possible implementations, the chronic disease indicator early warning notification method of this disclosure can be implemented as a program product that includes program code. When the program product is run on a terminal device, the program code is used to cause the terminal device to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0086] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0087] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A chronic disease index early warning notification method, characterized by, The application comprises the following steps: configuring and dynamically updating the normal value range of health indicator items of different chronic disease types and population classifications, generating versioned rule configuration data; receiving health indicator data uploaded by patients, cleaning and standardizing the data based on preset verification rules, and generating standardized indicator time series data; based on patient profile data and versioned rule configuration data, generating personalized range reference data by matching the rule configuration data through a rule matching engine; comparing and analyzing the standardized indicator time series data and the personalized range reference data to generate abnormal recognition result data; based on the abnormal recognition result data, generating structured warning information in combination with patient history data, and sending the information to the information terminal of the responsible doctor through a multi-channel distribution strategy.

2. The chronic disease index early warning notification method of claim 1, wherein, The application comprises the following steps: receiving rule configuration data input by an administrator through a graphical user interface, wherein the rule configuration data comprises a three-tuple of chronic disease type, population classification, and health indicator item, and the normal value range parameter of each health indicator item; persistently storing the rule configuration data in a versioned configuration table of a relational database, and establishing a time sequence of the configuration data through a version number field; when the rule configuration data is updated, automatically incrementing the version number and marking the new version of the rule configuration data as active, while retaining the historical version of the rule configuration data; broadcasting the update event of the rule configuration data to all related service nodes through a message queue, and triggering each service node to synchronously update the rule cache data in the memory.

3. The chronic disease index early warning notification method according to claim 2, characterized by, The application comprises the following steps: receiving health indicator data uploaded by a patient terminal through a RESTful API interface, and extracting the patient ID, health indicator item, health indicator value, and measurement timestamp from the health indicator data; verifying the data structure integrity of the health indicator data, and verifying the reasonableness of the health indicator value according to the health indicator data; performing standardization conversion on the verified health indicator data, extracting the health indicator value and unit information from the health indicator data through a data parser, uniformly converting the health indicator values from different sources into a standard unit of measurement using a unit conversion formula, uniformly converting the measurement timestamp into an ISO 8601 standard format using a time formatting tool, and uniformly mapping the health indicator item name to a preset internal standard code using an encoding mapping table, to generate standardized indicator data; organizing and storing the standardized indicator data in a time sequence in a time series database, to form complete standardized indicator time series data.

4. The chronic disease index early warning notification method according to claim 3, characterized by, The application comprises the following steps: based on the standardized indicator time series data, obtaining the patient ID and the health indicator item of the patient; based on the patient ID, querying the patient profile database to obtain the complete disease diagnosis information and population classification label of the patient as patient attribute data; The patient attribute data is combined with the health indicator item of the patient to construct a composite query condition including a disease type, a population classification, and the health indicator item of the patient. Through the composite query condition, the rule cache data in the local service node is first queried, and when the cache is not hit, the versioned rule configuration data in the relational database is queried to obtain the health indicator item normal value range corresponding to the health indicator item of the patient, and generate individualized range reference data including upper and lower limit values and applicable conditions.

5. The chronic disease index early warning notification method according to claim 4, characterized by, The standardized index time series data is compared with the individualized range reference data to generate abnormal identification result data, including: The health indicator value of the health indicator item of the patient is extracted from the standardized index time series data as a to-be-compared index value; the upper limit value and the lower limit value of the corresponding health indicator item normal value range are extracted from the individualized range reference data; The to-be-compared index value is compared with the corresponding health indicator item normal value range in real time through a numerical range comparator; a trend analysis algorithm is used to query the historical data of the same health indicator item from the time series database to calculate a short-term change rate; an association analyzer is used to check the abnormal synergy of multiple related indicators of the to-be-compared index value; When the to-be-compared index value exceeds the corresponding health indicator item normal value range, the corresponding health indicator item of the patient is regarded as an abnormal indicator item, and the abnormal level is marked as a primary abnormality; When the abnormal level of the abnormal indicator item is a primary abnormality, and the corresponding short-term change rate exceeds a threshold value, the abnormal level is upgraded to a medium abnormality; When the abnormal level of the abnormal indicator item is a medium abnormality, and multiple associated indicators are abnormal at the same time, the abnormal level is upgraded to a high-level composite abnormality; The patient ID, the abnormal indicator item, the corresponding abnormal level, and the measurement timestamp are encapsulated to generate abnormal identification result data.

6. The chronic disease index early warning notification method of claim 5, wherein, Based on the abnormal identification result data, structured warning information is generated in combination with the patient historical data, and is sent to the information terminal of the responsible doctor through a multi-channel distribution strategy, including: Based on the abnormal identification result data, the patient archive database is queried based on the patient ID to obtain patient basic information data; the related historical indicator data is extracted from the time series database based on the abnormal indicator item and the measurement timestamp; Based on the abnormal level in the abnormal identification result data, a corresponding warning information template is selected; The patient basic information and the abnormal identification result data are associated and integrated through a data binder to generate integrated data; Based on the historical indicator data, an indicator change trend chart is generated through a trend analyzer; The integrated data is filled in according to the template format corresponding to the abnormal level through a template rendering engine to output a warning information data packet; the warning information data packet includes patient basic information, abnormal indicator details, normal value range comparison, indicator change trend chart, data reporting time, and abnormal level. The early warning information data packet is pushed to the online information terminal of the responsible doctor through the WebSocket connection manager; meanwhile, the early warning information data packet is converted into a unified message format through the message serialization processor and delivered to the message queue; the consumer service of the message queue respectively calls the short message gateway API, enterprise WeChat API and mail server SMTP protocol to synchronously send the message to the mobile information terminal of the responsible doctor.

7. The chronic disease index early warning notification method of claim 1, wherein, The chronic disease types include hypertension, diabetes, hyperlipidemia, coronary heart disease, stroke, chronic obstructive pulmonary disease, chronic kidney disease and tumor; the population classification includes chronic disease high-risk population and chronic disease diagnosed population; the health index items include diastolic pressure, systolic pressure, fasting blood glucose, one-hour postprandial blood glucose, two-hour postprandial blood glucose, three-hour postprandial blood glucose, total cholesterol and blood oxygen saturation.

8. A chronic disease indicator early warning notification system, comprising: The system adopts the chronic disease index early warning notification method according to any one of claims 1 to 7; The system comprises: A dynamic rule configuration module is configured to configure and dynamically update the normal value range of the health index items of different chronic disease types and population classifications, and generate versioned rule configuration data. An index data standardization module is configured to receive the health index data uploaded by the patient, perform data cleaning and standardization processing based on a preset verification rule, and generate standardized index time series data. A personalized rule matching module is configured to match the rule configuration data based on the patient archive data and the versioned rule configuration data through a rule matching engine, and generate personalized range reference data. An abnormality identification analysis module is configured to compare and analyze the standardized index time series data and the personalized range reference data, and generate abnormality identification result data. An early warning distribution processing module is configured to generate structured early warning information based on the abnormality identification result data and the patient history data, and send the information to the information terminal of the responsible doctor through a multi-channel distribution strategy.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the steps of the chronic disease index early warning notification method according to any one of claims 1 to 7.

10. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the steps of the chronic disease index early warning notification method according to any one of claims 1 to 7.

Images