Migraine nursing quality management system based on evidence-based

Abstract

The invention discloses a migraine nursing quality management system based on evidence-based, and relates to the technical field of intelligent management, and the system comprises a construction unit which is used for collecting an evidence-based database, carrying out the decomposition and cascading of evidence-based elements through a minimum evidence-based unit, constructing an evidence-based network, and adding evidence-based nodes; the evidence-based unit is used for establishing wireless connection between the wearable equipment and the nursing management platform, executing multi-source sensing uploading and triggering an evidence-based node to execute two-order matching to determine a state network; and the decision unit is used for importing the state network into a nursing evaluation module embedded in the nursing management platform, executing user state evaluation and nursing decision, determining a nursing management strategy and displaying the nursing management strategy, and is used for solving the technical problem that individualization, timeliness and user integrating degree of nursing management are limited in the prior art. Individual and high-timeliness management in the nursing period can be effectively improved, and the user integrating degree of nursing is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to an evidence-based migraine nursing quality management system. Background Art

[0002] In the migraine care process, existing nursing plans often rely on static templates and manual experience, making it difficult to adapt to changes in individual patient conditions in real time, resulting in delayed nursing responses and limited intervention effectiveness. Furthermore, traditional nursing information systems lack multidimensional data integration and dynamic decision-making capabilities, making it difficult to accurately reflect the combined impact of patient physiological changes and environmental factors. With the widespread application of wearable devices and medical knowledge bases, integrating real-time perception with evidence-based nursing concepts has become a key direction for improving nursing quality and efficiency.

[0003] Based on this, there is an urgent need to build a nursing management system that supports multi-source perception, dynamic evaluation and intelligent decision-making to achieve personalized, timely and user-friendly migraine nursing intervention management. Summary of the Invention

[0004] This application provides an evidence-based migraine care quality management system to address the technical problems of individualized care management, timeliness, and limited user compatibility in the existing technology.

[0005] In view of the above problems, the present application provides an evidence-based migraine nursing quality management system, which includes: a construction unit for collecting evidence-based databases, decomposing and cascading evidence-based elements with the smallest evidence-based units, constructing an evidence-based network, embedding the evidence-based network into a nursing management platform, and adding evidence-based nodes; an evidence-based unit for establishing a wireless connection between wearable devices and the nursing management platform, performing multi-source sensor upload, triggering evidence-based nodes to perform two-order matching based on the evidence-based network, and determining a state network, wherein the two-order matching is a first-order matching based on the evidence chain and the relationship between the chains, and a second-order matching based on the chain nodes; a decision-making unit for importing the state network into a nursing evaluation module embedded in the nursing management platform, performing user state evaluation and nursing decision-making, determining the nursing management strategy, and displaying it in a pop-up window on the platform interface.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: An embodiment of the present application provides an evidence-based migraine nursing quality management system, which includes a construction unit for collecting an evidence-based database, decomposing and cascading evidence-based elements with the smallest evidence-based unit, constructing an evidence-based network, embedding the evidence-based network into a nursing management platform, and adding evidence-based nodes; an evidence-based unit for establishing a wireless connection between a wearable device and the nursing management platform, performing multi-source sensor upload, triggering the evidence-based node to perform two-order matching based on the evidence-based network, and determining a state network, wherein the two-order matching is a first-order matching based on the evidence chain and the relationship between the chains, and a second-order matching based on the chain nodes; a decision-making unit for importing the state network into a nursing assessment module embedded in the nursing management platform, performing user state assessment and nursing decision-making, determining a nursing management strategy, and displaying the strategy in a pop-up window on the platform interface. The decision-making unit is used to solve the technical problems of limited individualization, timeliness, and user compatibility of nursing management in the prior art, and can effectively improve individualization and high-timeliness management within the nursing cycle and improve user compatibility of nursing. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A schematic diagram of the implementation process of an evidence-based migraine care quality management system is provided for this application; Figure 2 A structural diagram of an evidence-based migraine care quality management system is provided for this application.

[0008] Explanation of reference numerals: construction unit 11 , evidence-based unit 12 , decision-making unit 13 . DETAILED DESCRIPTION

[0009] This application provides an evidence-based migraine care quality management system to solve the technical problems of individualized care management, timeliness and limited user compatibility in the existing technology.

[0010] Example: Figure 1 、 Figure 2 As shown, the present application provides an evidence-based migraine care quality management system, the system comprising: The construction unit 11 is used to collect the evidence-based database, decompose and cascade the evidence-based elements with the minimum evidence-based unit, build the evidence-based network, embed the evidence-based network into the nursing management platform, and add evidence-based nodes.

[0011] In the embodiment of the present application, the evidence-based database is a knowledge collection that integrates a large number of medical research results, nursing guidelines and nursing experience, and can be divided into two categories: a conceptual evidence-based sub-library and an empirical evidence-based sub-library. Among them, the conceptual evidence-based sub-library mainly covers standard nursing processes, pathological mechanisms and intervention criteria; while the empirical evidence-based sub-library is mainly based on historical cases, individual response feedback and efficacy data, and has strong practical guidance significance.

[0012] Furthermore, the evidence-based elements are decomposed and cascaded using the smallest evidence-based unit, where the smallest evidence-based unit refers to the basic evidence-based information granularity that cannot be further subdivided. For example, the increased frequency of migraine attacks may be related to sleep disorders, which is a smallest unit. Element decomposition refers to breaking down more complex evidence-based items into basic factors according to physiological, biochemical, behavioral and other dimensions, and performing causal chain cascade processing according to the pathogenesis, nursing sequence or intervention path to form an element sequence with front-end dependency. On this basis, an evidence-based network is constructed. The evidence-based network uses the above-mentioned decomposed and cascaded elements as nodes, and establishes boundary relationships between nodes through logical causal relationships, physiological correlations and nursing dependencies, forming a network structure that can be used for path query and reasoning matching.

[0013] For example, the sleep disorder node can be linked to nodes such as increased neurosensitivity and aggravated migraine through boundaries, forming a multi-level dependency path with clinical logic.

[0014] Subsequently, the evidence-based network is embedded in the nursing management platform, which is an integrated platform integrating nursing task configuration, patient status monitoring and decision support. The network is deployed in the platform database or knowledge engine in the form of a graph structure through an embedded module.

[0015] Finally, an evidence-based node is added. The evidence-based node is a functional unit newly added to the platform for triggering, calling and responding to the evidence-based network. It can initiate network reasoning, path search and other operations based on nursing tasks, user status or external trigger conditions to achieve knowledge-driven nursing strategy recommendations and ensure that the system can provide continuously optimized intervention guidance in dynamic nursing scenarios.

[0016] The evidence-based unit 12 is used to establish a wireless connection between the wearable device and the nursing management platform, perform multi-source sensor upload, trigger the evidence-based node to perform two-order matching based on the evidence-based network, and determine the state network, wherein the two-order matching is a first-order matching based on the evidence chain and the relationship between the chains, and a second-order matching based on the chain nodes.

[0017] In an embodiment of the present application, a wireless connection is first established between a wearable device and a care management platform. The wearable device includes a portable terminal with multiple built-in physiological and environmental sensors, which can collect the user's vital signs data in real time, such as heart rate, skin electrical response, sleep status, etc., and surrounding environment information, such as light, noise, temperature, etc.

[0018] During the specific implementation process, data is interconnected with the nursing management platform through low-power wireless communication protocols such as BLE or Wi-Fi to ensure the continuity of data collection and real-time transmission.

[0019] Subsequently, multi-source sensing upload is performed, that is, various types of heterogeneous sensor data collected by the wearable device are synchronized with timestamps, unified in coding format, and packaged and uploaded to the nursing management platform to form a set of multi-dimensional, multi-source time series data sets. Among them, multi-source sensing emphasizes the multidimensionality and synergy of data.

[0020] For example, blood pressure fluctuation data and environmental noise levels collected at the same time can be used together as correlation indicators to determine the cause of the attack.

[0021] Next, after receiving this multi-source sensor data, the platform triggers the evidence-based nodes to perform two-order matching based on the evidence-based network. The evidence-based nodes are units embedded in the management platform for performing knowledge processing. Their function is to call upon the structures and paths in the evidence-based network to perform data-driven matching calculations. The two-order matching consists of two stages: first-order matching and second-order matching. The first-order matching is a structural matching based on evidence-based chains and inter-chain relationships. This involves matching the associated evidence-based chains within the network based on the symptom status reflected by the sensor data. For example, data patterns composed of emotional fluctuations and high noise exposure can activate the sympathetic nervous system stress chain and the external stimulus response chain. The second-order matching is a further matching based on chain nodes. Within the matched evidence-based chains, the specific activated nodes and response levels are further determined based on the node value accuracy, transition direction, and node strength, thereby locating the status nodes.

[0022] Finally, a state network is determined, that is, an individual state map generated by multi-source data. The state network is centered on the matched evidence chain nodes, reflecting the comprehensive evaluation of the current individual's physiological, psychological, and environmental three-dimensional state, providing knowledge support and reasoning basis for subsequent nursing decisions.

[0023] The decision unit 13 is used to import the status network into the nursing assessment module embedded in the nursing management platform, perform user status assessment and nursing decision-making, determine the nursing management strategy, and display it in a pop-up window on the platform interface.

[0024] In an embodiment of the present application, the state network is first imported into the nursing assessment module embedded in the nursing management platform. The state network is individualized health status information constructed through a two-order matching mechanism, which includes multiple state nodes and their label values that are associated with each other by time and causal logic, and can reflect the user's current comprehensive state under the influence of physiological, psychological and environmental interactions.

[0025] Among them, the nursing management platform is equipped with a nursing assessment module, which serves as the core functional unit for realizing intelligent assessment and auxiliary decision-making in the system. This module automatically deduces the nursing level and intervention requirements corresponding to the current state by calling parameters such as node weights, inter-node paths, and change trends in the state network.

[0026] Among them, the nursing assessment module is an executive function component. The following is a feasible construction method of the nursing assessment module: combining historical nursing data, nursing knowledge rules, etc., to determine the training samples, that is, taking state characteristics as input and evaluation results and nursing methods as output, and performing supervised training until convergence to obtain the constructed nursing assessment module.

[0027] Subsequently, user status assessment and nursing decision-making are performed, that is, evaluating whether the user is in a risky state or whether upgraded nursing measures are needed. For example, when sleep interruptions are frequent in the status network, skin electricity increases significantly and abnormal emotional labels co-occur, it can be inferred that the user has entered the prodromal stage of migraine; based on this assessment result, the module automatically determines the nursing management strategy, which includes multiple dimensions such as early warning prompts, behavioral guidance, medication recommendations or nursing intervention scheduling, and can generate corresponding levels of response plans according to the status level.

[0028] Finally, a pop-up window is displayed on the platform interface, that is, the nursing strategy content is pushed in the form of a visual pop-up window on the user side or the nursing staff's work interface. The pop-up window contains a status summary, risk level, intervention suggestions and operation options, ensuring that users or nursing staff can obtain accurate and timely nursing response information at the first time, thereby realizing individualized, intelligent and closed-loop management of migraine care.

[0029] Furthermore, the construction unit 11 is further configured to perform the following steps: decomposing the evidence-based elements using the minimum evidence-based unit includes: The evidence-based database includes a conceptual evidence-based sub-library and an empirical evidence-based sub-library; a first evidence-based element is determined, wherein the first evidence-based element is any evidence-based element in the evidence-based database; the first evidence-based element is decomposed into a minimum element unit to determine multiple decomposition elements; and for the entire nursing cycle, a trend chain is reconstructed for the multiple decomposition elements and added to the evidence chain set.

[0030] In an embodiment of the present application, the evidence-based database includes a conceptual evidence-based sub-library and an empirical evidence-based sub-library. The conceptual evidence-based sub-library is based on standardized knowledge such as literature research, clinical guidelines and pathological models, and is mainly used to provide theoretical support and nursing process specifications; the empirical evidence-based sub-library collects historical case data, user feedback and intervention result data in real-world nursing scenarios, focusing on reflecting individual differences and dynamic response laws. The two types of sub-libraries complement each other and together constitute a knowledge system that supports multidimensional reasoning.

[0031] On this basis, the first evidence-based factor is identified. This first evidence-based factor is any knowledge item in the database, which can be a key node in a symptom-intervention-outcome chain. For example, decreased sleep quality before a migraine attack is a typical evidence-based factor. Next, this first evidence-based factor is decomposed into its smallest element unit to identify multiple decomposed elements. The smallest element unit refers to the basic information factor that cannot be further decomposed, such as sleep onset delay >30 minutes, nocturnal awakenings ≥2 times, and subjective sleep score <60. Through this decomposition process, complex elements can be converted into structured and measurable data dimensions, facilitating subsequent path construction and automatic matching.

[0032] Furthermore, for the entire nursing cycle, the trend chain of the multiple decomposition elements is reconstructed, that is, according to the time stages covered by the nursing activities, such as the evaluation period, intervention period, and follow-up period, the above decomposition elements are chain-sorted according to their change sequence and intervention response mechanism, and a trend path combining time-driven and causal-driven is constructed.

[0033] Finally, the trend chain is added to the evidence-based chain set, which is a structured knowledge graph collection composed of multiple evidence-based paths. It is used to support subsequent state matching, node reasoning and intervention strategy generation, and enhance the system's dynamic identification and accurate response capabilities to individual migraine states.

[0034] Furthermore, the construction unit 11 is further configured to perform the following steps: Constructing an evidence-based network includes: Determine the element correlation of the decomposed elements, wherein the element correlation includes physiological state correlation and nursing correlation; combine the evidence chain set, use the evidence chain as the entity and the element correlation as the relationship, reconstruct the evidence-based database, and determine the evidence-based network.

[0035] In this example, we first determine the relevance of the decomposed elements. These elements are the basic evidence-based factors broken down into their smallest units. These elements are derived from structured information items extracted from the conceptual and empirical evidence-based sub-libraries. To construct a logically connected evidence-based structure, we need to identify the inherent connections between the decomposed elements, i.e., the relevance of the elements.

[0036] Among them, the element correlation specifically includes two dimensions: physiological state correlation and nursing correlation: the physiological state correlation refers to the co-occurrence or causal dependency of two or more decomposed elements in the physiological process of the human body. For example, the increased frequency of nighttime awakenings and autonomic dysfunction can establish physiological correlation through neural regulation mechanisms; the nursing correlation refers to the linkage between elements in nursing operations, nursing pathways or intervention goals. For example, dietary inducement identification and dietary behavior intervention have clear process continuity and goal consistency, which is a typical nursing correlation.

[0037] Furthermore, after completing the identification of element relevance, the evidence-based database is reconstructed in conjunction with the evidence-based chain set, using the evidence-based chain as the entity and the element relevance as the relationship. An evidence-based chain is a knowledge path constructed from multiple decomposed elements in a logical order or physiological evolution path, and is the basic unit supporting the generation of nursing assessments and intervention strategies. During the reconstruction process, the system treats each evidence-based chain as an entity node in the graph structure and constructs connecting edges between chains and between nodes within a chain based on the correlations established between elements, thereby achieving knowledge reorganization from discrete data items to an organic network structure. This process not only preserves the knowledge depth in the original evidence-based database, but also enhances the system's reasoning and generalization capabilities through structural reconstruction.

[0038] Finally, the evidence-based network is determined. The evidence-based network is a graphical, traversable, multi-dimensional nursing knowledge structure, which contains multiple nodes (i.e., decomposition elements), multiple paths (i.e., evidence chains) and edge weight relationships (i.e., element relevance measurement). It is used to support the subsequent system to perform state recognition, node matching, path reasoning and nursing strategy generation under the drive of user data, thereby realizing knowledge guidance and intelligent support for the migraine nursing process.

[0039] Furthermore, the evidence-based unit 12 is further configured to perform the following steps: The evidence-based node is triggered to perform a two-order matching based on the evidence-based network to determine a state network, including: Identify multi-source sensor data and determine a sensor vector, wherein the sensor vector is a vector value and a variation direction of each sensor data; perform a first-order matching based on an evidence chain and an inter-chain relationship based on the sensor vector and the evidence elements to determine a first matching result; perform node matching within the evidence chain based on the vector value to determine a second matching result; and determine the state network based on the first matching result and the second matching result.

[0040] Wherein, a label value is generated according to the changing direction, and the state network is identified according to the label value.

[0041] In an embodiment of the present application, multi-source sensor data is first identified and a sensor vector is determined. The multi-source sensor data is individual health monitoring data obtained in real time through wearable devices and environmental acquisition modules, covering physiological indicators such as heart rate, skin electrical response, sleep cycle, and environmental parameters such as light, temperature, noise level and other dimensions; after feature extraction and standardization of such data, a corresponding sensor vector is constructed. The sensor vector includes two core components: one is a vector value, which is used to represent the numerical state of various sensor parameters at the current sampling moment; the other is a transition direction, that is, the change trend of the sensor parameter relative to the historical data, such as rising, falling or stable, which is used to reflect the dynamic evolution process of the individual state. For example, the heart rate vector rises from 70bpm to 85bpm, and the transition direction is a positive change.

[0042] Furthermore, after obtaining the sensor vector, a first-order matching based on the evidence chain and the relationship between chains is performed according to the sensor vector and the evidence elements. In this step, by extracting the symptom characteristics and trend changes reflected in the sensor vector, the group of evidence elements associated with it is identified across the evidence chain range, and by calculating the matching degree and co-occurrence relationship between the elements, a first-order matching is completed within the knowledge graph level, that is, multiple evidence chain entities that are highly relevant to the current perception state are determined to form a first matching result. For example, when the sensor vector shows an increase in skin electricity, a decrease in sleep score, and a sharp fluctuation in light intensity, the two evidence chains of the sympathetic hypersensitivity chain and the environmental induced chain can be activated.

[0043] Next, the system performs node matching within the evidence chain based on the vector value to determine a second matching result. Node matching involves comparing the actual value of the sensor vector with predefined indicator thresholds or state characteristics in the knowledge base, node by node, within the evidence chain identified by the first matching result. This identifies the set of nodes currently in the active state, forming the second matching result. For example, in the sympathetic hypersensitivity chain, if the current skin electrode value exceeds the established threshold of 70μS and is accompanied by an increased heart rate, it can be confirmed that the autonomic nervous system activation node has been matched.

[0044] Based on the matching results of these two dimensions, the first and second matching results are further used to determine the state network. This is the current user state constructed by integrating chain-level identification and node-level matching, reflecting the mapping structure of their physiological and environmental states in the evidence-based graph. This state network, centered around the currently activated evidence-based chains and nodes, expresses the individual's health status through weighted associations and trend markers.

[0045] Furthermore, based on the evolutionary direction, a label value is generated. This label value is used to mark the evolutionary direction and risk level of the state node. For example, a continuously positive evolutionary direction can be associated with an increasing risk label. Finally, based on the label value, the state network is identified. This label information is superimposed on the state network node structure. This information is then used by the subsequent nursing assessment module to perform risk identification, trend prediction, and personalized nursing strategy generation, thereby achieving both improved interpretability and responsiveness of state identification.

[0046] Furthermore, the evidence-based unit 12 is also used to perform the following steps: the wearable device has a built-in sensor array; receiving sampled data of the wearable device as one-dimensional sensor data with synchronization timestamp constraints; introducing environmental factors and sampling to determine two-dimensional sensor data; and determining multi-source sensor data based on the one-dimensional sensor data and the two-dimensional sensor data.

[0047] In the embodiment of the present application, the sampled data of the wearable device is first received as one-dimensional sensor data with a synchronization timestamp constraint. The wearable device is internally integrated with a variety of physiological parameter sensors, which can continuously collect the user's vital signs information, including but not limited to heart rate, skin galvanic response, body temperature, blood oxygen level, etc. In order to ensure the data correlation and timeliness between different parameters, the system synchronizes and marks each sampled data based on a unified timestamp mechanism. That is, after each set of data is collected, a unified sampling timestamp is added to form one-dimensional sensor data in the form of a time series. Among them, the one-dimensional attribute of the one-dimensional sensor data is mainly reflected in the fact that it is based on the individual physiological state of the user as the only source, representing the basic health change curve of the user himself.

[0048] Next, environmental factors are introduced to sample and determine two-dimensional sensor data. These environmental factors include external interference factors in the user's environment, such as noise intensity, illumination level, air temperature and humidity, and air pressure changes. These parameters are typically acquired through external sensors or environmental sensing units in wearable devices. During the sampling process, environmental sensor data is collected synchronously with physiological data and assigned the same timestamp to ensure that the two types of data have a consistent temporal structure. Based on the one-dimensional and two-dimensional sensor data (i.e., composed of the two dimensions of user individual data and environmental intervention data), a correlated spatiotemporal health profile is constructed. This multi-source sensor data is the multidimensional feature set formed by fusing these two types of sensor information along a time axis. It contains a joint expression of the user's internal physiological state and external environmental conditions and can be used to comprehensively analyze the triggering factors and state evolution of migraines. For example, if a multi-source data pattern of a mild increase in blood pressure, a dramatic change in light intensity, and an increase in noise intensity is detected within a certain time period, it can be identified as a complex stimulus situation that may trigger a migraine, providing key input for subsequent state assessment and intervention strategies.

[0049] Furthermore, the data determination unit is further configured to perform the following steps: Determining multi-source sensor data according to the one-dimensional sensor data and the two-dimensional sensor data includes: According to the two-dimensional sensing data, a feature impact analysis based on the migraine state is performed to measure the environmental impact coefficient; according to the environmental impact coefficient, the one-dimensional sensing data is marked as the multi-source sensing data.

[0050] In an embodiment of the present application, a feature impact analysis based on the migraine state is first performed based on the two-dimensional sensor data. The two-dimensional sensor data is a joint time-series data set that integrates the user's physiological parameters and environmental variables, and has the ability to describe the migraine-inducing context and individual state responses. In one feasible embodiment, a migraine state feature library is introduced. The feature library stores a variety of typical environmental triggers and corresponding physiological response patterns before, during, and during migraine remission. For example, continuous high noise can lead to an increase in heart rate and skin conductance, corresponding to the prodromal phase of migraine. The environmental impact coefficient is obtained by identifying the statistical significance and correlation strength of current environmental parameters such as noise, light, temperature, and humidity on changes in user physiological indicators.

[0051] The environmental impact coefficient is a numerical expression that quantifies the degree to which external environmental factors interfere with an individual's migraine state. It is expressed as a weighted impact score or association strength score, and its value range can be normalized to the [0, 1] interval. For example, if an increase in noise intensity leads to a significant increase in heart rate, and this combination frequently co-occurs in historical migraine attacks, a high impact coefficient, such as 0.85, may be generated, indicating that the current environment has a strong interference effect on the potential attack state.

[0052] Furthermore, the one-dimensional sensor data is labeled based on the environmental impact coefficient. This means that an environmental tag is embedded in the one-dimensional data stream consisting of the user's pure physiological parameters to indicate the degree to which it is modulated by external factors. In one feasible embodiment, this tagging process can use multi-channel encoding, for example, by appending the label "noise modulation: strong" to the heart rate data sequence, or by recording the influence weight of the current environmental variable in the form of metadata.

[0053] Finally, the identified one-dimensional sensor data is used as the multi-source sensor data. That is, the constructed multi-source sensor data not only contains synchronized physiological and environmental data, but also embeds the weight identification of the environment-physiological interaction relationship, thereby improving the system's sensitivity and explanatory power to individual state perception under complex inducing conditions, and providing more accurate and traceable data support for early identification of migraine and intelligent nursing decisions.

[0054] Furthermore, the decision unit 13 is further configured to perform the following steps: Before performing user status assessment and care decisions, including: A temporary database is added to the nursing management platform, wherein the temporary database stores user nursing data for a preset number of times, and the nursing assessment module, the temporary database and the user end interact with each other; as the nursing data on the user end is updated, the temporary database is updated synchronously, and the temporary database is the data pool for the decision-making of the nursing assessment module.

[0055] In this application's embodiment, a temporary database is first added to the care management platform. This temporary database is a lightweight dynamic data cache module, distinct from the long-term historical data warehouse, primarily used to store recent user care data to support short-term reasoning and decision optimization of the evaluation model. This database is deployed locally or on an edge computing unit within the care management platform via an efficient memory mapping mechanism. It features low latency and fast read and write speeds, making it suitable for the rapid response requirements of real-time care scenarios.

[0056] Furthermore, the temporary database is used to store a preset number of user care data. Specifically, for each user, only the most recent five or ten key care events and status records are retained. This care data includes network snapshots of pre- and post-care status, care interventions, user feedback, and autonomous health behavior records. It is both structured and serialized, facilitating rapid retrieval and trend analysis. By limiting the number of records, the database size can be effectively controlled, access efficiency can be improved, and the platform's real-time performance and stability can be ensured even with multiple users running concurrently.

[0057] In terms of data interaction, the nursing assessment module, temporary database, and user end interact with each other. The nursing assessment module uses data from the temporary database as a decision input basis to dynamically assess the user's current status and historical evolution trajectory. The user end interacts with the platform through a visual interface, uploading the latest nursing records, such as medication usage, symptom scores, and behavioral feedback, while also receiving strategic recommendations from the platform. Exemplary interaction methods may include HTTP / HTTPS communication, MQTT message push, or WebSocket real-time connection to ensure data synchronization and consistency across multiple terminals.

[0058] As the nursing process progresses, the user's nursing data is continuously updated, and the temporary database is updated synchronously. This means that the oldest record is immediately replaced as new nursing data is generated, implementing a cyclical overwriting data maintenance process to avoid data redundancy and historical accumulation. This synchronous update mechanism ensures that the information retained in the database is highly timely and can accurately reflect the user's current dynamic status characteristics.

[0059] Ultimately, the temporary database serves as a data pool for the decision-making of the nursing assessment module. That is, when the module generates nursing strategies, predicts the risk of attacks, or pushes intervention recommendations, it uses the data in the temporary database as a benchmark to ensure that it is consistent with the user's current nursing status, thereby improving the adaptability, sensitivity, and individualization of nursing decisions. It is particularly suitable for chronic disease nursing scenarios such as migraines where the status fluctuates significantly and the timeliness of intervention is high.

[0060] Furthermore, after determining the nursing management strategy, the system is further configured to perform the following steps: According to the care management strategy, the regulatory requirements of the strategy stage are determined; and the monitoring sampling of the wearable device is managed and controlled based on the regulatory requirements.

[0061] In an embodiment of the present application, the regulatory requirements of the strategy stage are first determined based on the nursing management strategy. The nursing management strategy is an individualized intervention plan generated by the nursing assessment module based on state network analysis and historical data reasoning, and usually includes a multi-stage implementation path, such as an early warning stage, an intervention execution stage, and a recovery tracking stage.

[0062] The system automatically identifies regulatory requirements for different phases, specifically the granularity, frequency, and types of key indicators required for monitoring a user's health status. For example, during the prodromal phase of a migraine attack, it can determine that heart rate variability, skin conductance fluctuations, and noise exposure intensity require special attention, with the sampling frequency increased to once every five seconds. During the recovery phase, the sampling frequency can be reduced, retaining only indicators such as sleep quality and subjective feedback, to avoid wasted resources and excessive user interference.

[0063] Subsequently, the wearable device's monitoring and sampling is managed based on these regulatory requirements. This involves sending the generated phased sampling strategy to the wearable device, controlling the sensor module's start / stop logic, sampling cycle, and types of collected metrics. For example, wireless commands can be used to activate high-frequency ECG monitoring, pause temperature sensing, or adjust the blood oxygen sampling cycle. This enables automatic synchronization, dynamic configuration, and personalized customization.

[0064] Through the above steps, the device monitoring behavior can be dynamically adapted according to the nursing strategy to achieve optimal resource allocation, improve the real-time recognition of key states and the accuracy of nursing responses, ensure that the entire nursing process runs in a closed loop with data support, and improve the intelligence and safety management level of migraine care.

[0065] This application provides an evidence-based migraine care quality management system with the following technical effects: 1. Collect an evidence-based database, including conceptual and empirical evidence-based sub-databases. Decompose evidence-based elements into their smallest units. Reconstruct trend chains within these decomposed elements across the entire nursing cycle. Reconstruct the evidence-based database using evidence chains as entities and element relevance as relationships. Construct an evidence-based network and integrate it into the nursing management platform, adding evidence-based nodes. This constructed evidence-based network comprehensively and systematically integrates various evidence-based elements related to migraine care, providing a rich and accurate knowledge base for subsequent nursing decisions and helping to improve the scientific nature and accuracy of nursing decisions.

[0066] 2. Establish a wireless connection between the wearable device and the nursing management platform. Determine the sensor vector through sampling and integration. First-order matching based on the evidence chain and inter-chain relationships, and second-order matching based on chain nodes, are performed to determine the state network. Label values are generated based on the direction of sensor data change to identify the state network. Using the constructed evidence network as a benchmark, two-order matching is performed to quickly and accurately determine the patient's migraine status, providing a basis for personalized nursing decisions. Furthermore, the identification of the state network facilitates rapid location and analysis of patient status changes.

[0067] 3. Add a temporary database to the nursing management platform to store a preset number of user nursing data. The temporary database is updated synchronously with the user-side nursing data, providing a data pool for the nursing assessment module to make decisions. The use of evidence-based networks and multi-source sensor data for nursing decisions, combined with the historical nursing data stored in the temporary database, can improve the accuracy of nursing assessments and the pertinence of nursing decisions, provide medical staff with appropriate nursing strategy recommendations in a timely manner, and improve the quality of patient care.

[0068] Through the above detailed description of an evidence-based migraine care quality management system in this specification, those skilled in the art can clearly understand the evidence-based migraine care quality management system in this embodiment. For the device disclosed in the embodiment, since it corresponds to the system disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the system part description.

[0069] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one 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 present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An evidence-based migraine care quality management system, characterized by: The system comprises: A construction unit is used to collect evidence-based databases, decompose and cascade evidence-based elements with the smallest evidence-based units, build an evidence-based network, embed the evidence-based network into the nursing management platform, and add evidence-based nodes; An evidence-based unit, configured to establish a wireless connection between the wearable device and the nursing management platform, perform multi-source sensor upload, trigger the evidence-based node to perform two-order matching based on the evidence-based network, and determine the state network, wherein the two-order matching is a first-order matching based on the evidence chain and the relationship between the chains, and a second-order matching based on the chain nodes; The decision-making unit is used to import the status network into the nursing assessment module embedded in the nursing management platform, perform user status assessment and nursing decision-making, determine the nursing management strategy, and display it in a pop-up window on the platform interface.

2. An evidence-based migraine care quality management system according to claim 1, characterized in that: The building block comprises: The evidence-based database includes a concept-based evidence sub-library and an experience-based evidence sub-library; an element determination unit, configured to determine a first evidence-based element, wherein the first evidence-based element is any evidence-based element in the evidence-based database; An element decomposition unit, configured to decompose the first evidence-based element into minimum element units to determine a plurality of decomposition elements; The element reconstruction unit is used to reconstruct the trend chain of the multiple decomposition elements for the entire nursing cycle and add them into the evidence-based chain set.

3. The evidence-based migraine care quality management system according to claim 2, characterized in that: The element reconstruction unit includes: a correlation determination unit, configured to determine element correlations of decomposed elements, wherein the element correlations include physiological state correlations and nursing correlations; The network reconstruction unit is used to combine the evidence-based chain set, reconstruct the evidence-based database with the evidence-based chain as the entity and the element correlation as the relationship, and determine the evidence-based network.

4. The evidence-based migraine care quality management system according to claim 1, characterized in that: The evidence-based unit includes: a vector determination unit, configured to identify multi-source sensor data and determine a sensor vector, wherein the sensor vector is a vector value and a transition direction of each sensor data; a first matching unit, configured to perform a first-order matching based on the evidence chain and the relationship between the chains according to the sensing vector and the evidence element, and determine a first matching result; A second matching unit is configured to perform node matching within the evidence chain according to the vector value and determine a second matching result; A network determining unit is configured to determine the state network according to the first matching result and the second matching result.

5. The evidence-based migraine care quality management system according to claim 4, characterized in that: A label value is generated according to the changing direction, and the state network is identified according to the label value.

6. The evidence-based migraine care quality management system according to claim 1, characterized in that: The wearable device has a built-in sensor array, and the evidence-based unit includes: a one-dimensional acquisition unit, configured to receive sampled data from the wearable device as one-dimensional sensing data under synchronization timestamp constraints; A two-dimensional acquisition unit is used to introduce environmental factors and sample and determine two-dimensional sensing data; The data determining unit is configured to determine multi-source sensing data based on the one-dimensional sensing data and the two-dimensional sensing data.

7. The evidence-based migraine care quality management system according to claim 6, characterized in that: The data determination unit includes: an impact measurement unit, configured to perform a feature impact analysis based on the migraine state according to the two-dimensional sensing data and measure an environmental impact coefficient; A data identification unit is used to identify the one-dimensional sensing data as the multi-source sensing data according to the environmental impact coefficient.

8. The evidence-based migraine care quality management system according to claim 1, characterized in that: The decision-making unit includes: A database adding unit is used to add a temporary database to the nursing management platform, wherein the temporary database stores a preset number of user nursing data, and the nursing assessment module, the temporary database and the user terminal interact; The database updating unit is used to update the temporary database synchronously with the update of the nursing data on the user side. The temporary database is the data pool for the decision of the nursing assessment module.

9. The evidence-based migraine care quality management system according to claim 1, characterized in that: The system further comprises: a demand determination unit, configured to determine regulatory requirements at a strategy stage based on the nursing management strategy; The sampling control unit is used to control the monitoring sampling of the wearable device based on the regulatory requirements.

Images