Real-time nursing quality monitoring and alarm system

Abstract

The invention relates to the technical field of medical care, in particular to a real-time nursing quality monitoring and alarm system which comprises a data acquisition module, a real-time monitoring module, an intelligent analysis module, an alarm generation module, a decision support module and a visualization module. The real-time monitoring module monitors acquired nursing quality data in real time, the intelligent analysis module processes and analyzes the data and identifies potential problems and trends, the alarm generation module generates alarms and reminds nursing staff to take measures in time, and the decision support module provides suggestions and decision support for optimizing the nursing process. And the visual module provides a user interface, so that nursing personnel can check monitoring data, alarm information and decision suggestions conveniently. Through comprehensive data collection and an intelligent analysis and early warning mechanism, the nursing quality monitoring and management level is improved, potential problems are found and processed in time, and the overall level of nursing service and the patient satisfaction degree are improved.

Description

Technical Field

[0001] The present invention relates to the field of medical care technology, and in particular to a real-time care quality monitoring and alarm system. Background Art

[0002] With the continuous improvement of medical standards and the growing demand for health, the monitoring and management of nursing quality has become particularly important. Nursing quality is directly related to the health status and medical experience of patients, and is an important basis for medical institutions to evaluate and improve services. At present, many hospitals and medical institutions have begun to use information technology to monitor nursing quality, such as recording nursing data through electronic medical record systems and obtaining laboratory test results through laboratory information systems. However, these systems often only passively record the nursing process and lack real-time monitoring and intelligent analysis of nursing quality.

[0003] In the existing technology, the nursing quality monitoring system generally has the following problems: first, the data collection and monitoring methods are single, which makes it difficult to fully and accurately reflect the nursing quality; second, there is a lack of intelligent analysis capabilities, and it is impossible to effectively use big data and machine learning technologies to conduct in-depth analysis and trend prediction of nursing quality data; third, the alarm system is not flexible enough and cannot generate alarms in time according to changes in real-time data and abnormal situations to remind nursing staff to take corresponding measures; fourth, the decision support function is weak, and it is difficult to provide optimized nursing process suggestions based on data analysis to help the nursing team make scientific decisions. Summary of the invention

[0004] Based on the above objectives, the present invention provides a real-time nursing quality monitoring and alarm system.

[0005] The real-time nursing quality monitoring and alarm system includes a data acquisition module, a real-time monitoring module, an intelligent analysis module, an alarm generation module, a decision support module and a visualization module, among which;

[0006] The data collection module is used to collect nursing quality data, including patient satisfaction, nursing accident rate and infection rate;

[0007] The real-time monitoring module is connected to the data acquisition module and is used to monitor the collected nursing quality data in real time to ensure the real-time and accuracy of the data;

[0008] The intelligent analysis module is connected to the real-time monitoring module and is used to process and analyze the monitored data using data analysis and machine learning algorithms to identify potential problems and trends;

[0009] The alarm generation module is connected to the intelligent analysis module, and when the monitoring data is abnormal or exceeds a predetermined threshold, an alarm is automatically issued to remind the nursing staff to take timely measures;

[0010] The decision support module is connected to the intelligent analysis module and the alarm generation module, and is used to provide suggestions and decision support for optimizing the nursing process according to the analysis results;

[0011] The visualization module provides a user interface for nursing staff to view monitoring data, alarm information and decision suggestions.

[0012] Further, the data collection module includes a patient satisfaction data collection submodule, a nursing accident rate data collection submodule and an infection rate data collection submodule, wherein;

[0013] The patient satisfaction data collection submodule specifically includes:

[0014] Electronic questionnaire: When patients are discharged from hospital or during the nursing stage, electronic questionnaires are sent to patients or their families via electronic devices (such as tablets or smartphones) to collect their evaluation of satisfaction with nursing services;

[0015] Telephone survey: Conduct satisfaction surveys with patients or their families through voice interaction, and enter the collected data into the system;

[0016] Online evaluation platform: Through the hospital's official website or a dedicated nursing evaluation app, patients are allowed to fill out satisfaction evaluation online after receiving care;

[0017] The nursing accident rate data collection submodule specifically includes:

[0018] Event reporting system: When a nursing accident (such as medication error, fall, etc.) occurs, the nursing staff will record the accident in detail through the hospital's internal event reporting system, including time, location, participants, and accident description;

[0019] Sensors and monitoring devices: Install monitoring devices in patient rooms to automatically detect and record nursing incidents, such as patient falls or equipment failures;

[0020] Electronic medical record system integration: extract relevant accident data from the hospital's internal electronic medical record system to ensure data consistency and accuracy;

[0021] The infection rate data collection submodule specifically includes:

[0022] Laboratory test data integration: Integrate with the hospital's laboratory information system to automatically collect laboratory test data related to infection, such as blood culture results, urine culture results, etc.;

[0023] Nursing record unit: Nursing staff record the patient's infection symptoms and nursing measures (such as disinfection, anti-infection treatment, etc.) in their daily work, which are collected through the nursing record unit;

[0024] Public health monitoring system: Integrate with the infection monitoring system of the public health department to obtain infection rate data in the region to help hospitals identify and respond to infection risks.

[0025] Furthermore, the real-time monitoring module specifically includes:

[0026] Data reception and caching: Apache Kafka is used as the data stream processing framework to receive nursing quality data from the data acquisition module in real time, and Redis is used as the in-memory database for data caching;

[0027] Data validation and cleaning: Use the Drools rule engine to validate the format and content of the received data. The validation rules include data integrity check, data type matching check, and value range rationality check. The received data is cleaned, including removing duplicate data, processing missing values ​​and outliers, to ensure data quality.

[0028] Real-time data processing: Use Apache Flink for real-time data computing and analysis, including calculating nursing accident rates and infection rates, and generating real-time statistics;

[0029] Data storage and management: Use TimescaleDB as a real-time database to store processed real-time data, and regularly archive real-time data to PostgreSQL;

[0030] Data visualization: Use Grafana to build a real-time dashboard to display the real-time status and trends of nursing quality data, which is convenient for nursing staff and managers to view at any time. It allows users to customize monitoring views and indicators to meet the real-time monitoring requirements of different roles and needs.

[0031] Furthermore, the intelligent analysis module specifically includes:

[0032] Data standardization: receiving the nursing quality data processed by the real-time monitoring module in real time, performing standardization processing, and extracting features from the processed data;

[0033] Machine learning models: Use support vector machine models for classification and regression analysis to predict potential problems and trends, train support vector machine models using training datasets, evaluate model performance through cross-validation, and validate support vector machine models using validation datasets;

[0034] Real-time prediction: Use the trained support vector machine model to predict real-time nursing quality data and identify potential problems and trends;

[0035] Anomaly detection: Real-time detection of anomalies in data, timely discovery and alarm of potential problems;

[0036] Feature importance analysis: Through feature selection and importance analysis, the support vector machine model identifies which features have the greatest impact on the quality of care, so that targeted improvements can be made.

[0037] Furthermore, the intelligent analysis module can customize analysis rules according to different nursing scenarios and needs, and provide personalized nursing quality improvement solutions, including:

[0038] Define rules: Nurses and managers define rules through APIs;

[0039] Rule management: Use the Drools rule engine to manage and execute custom rules, and support adding, modifying, deleting, and versioning rules;

[0040] Real-time data analysis: The support vector machine model predicts the real-time nursing quality data, generates prediction results, inputs the prediction results and real-time nursing quality data into the rule engine, and applies custom rules for analysis;

[0041] Real-time anomaly detection: detect anomalies in data in real time, analyze them through the rule engine, identify potential problems and trigger alerts;

[0042] Generate improvement plans: Generate personalized nursing quality improvement plans based on analysis results and customized rules.

[0043] Furthermore, when the intelligent analysis module detects anomalies or trend changes in the data, it transmits the results to the alarm generation module, which specifically includes:

[0044] Threshold setting: Setting predetermined thresholds based on historical statistics of nursing quality data and expert advice;

[0045] Alert rule management: configure predetermined thresholds and alert trigger conditions;

[0046] Real-time monitoring: Continuously monitor the data results transmitted by the intelligent analysis module. If it is detected that the data exceeds the predetermined threshold or meets abnormal conditions, the alarm generation process is immediately triggered;

[0047] Alarm notification mechanism: Alarm information is sent to relevant caregivers and managers through various means (such as SMS, email, mobile application notification, etc.).

[0048] Furthermore, the decision support module specifically includes:

[0049] Integration of analysis results: The decision support module obtains the analysis results and alarm information of nursing quality data from the intelligent analysis module and the alarm generation module;

[0050] Generate optimization recommendations: Based on the integrated analysis results and alarm information, the decision support module uses the rule engine and the configured knowledge base to generate recommendations for optimizing the nursing process;

[0051] Decision support output: Generate specific recommendations for optimizing nursing processes, including improvement measures, expected effects, and implementation steps, and generate detailed decision support reports, including analysis results, alarm information, optimization recommendations, and expected effect evaluation.

[0052] Furthermore, the visualization module specifically includes:

[0053] User interface design: Provide a comprehensive dashboard that displays quality of care indicators, trend analysis, alert information, and decision-making recommendations;

[0054] Data visualization: Use charts and graphs to present monitoring data and analysis results;

[0055] Interactive functions: Provide interactive functions to allow users to screen, filter and drill data to view detailed information;

[0056] Alarm display: displays an overview of current and historical alarms, including alarm type, trigger time, severity, and processing status, and provides detailed alarm information, including anomaly detection results, specific data, and reasons for triggering the alarm;

[0057] Decision support presentation: Presents suggestions for optimizing nursing processes generated by the decision support module, including specific improvement measures and expected results, and provides implementation steps and guidance to help nursing staff and managers implement improvement measures.

[0058] Furthermore, the visualization module further includes a user management unit, which provides different levels of data access and operation permissions according to user roles and permissions, including:

[0059] User role and permission management: define different user roles, such as caregivers, care managers, and system administrators, and assign different data access and operation permissions based on user roles;

[0060] User authentication and access control: Use username / password or multi-factor authentication mechanisms to ensure that only authorized users have access. Perform access control based on user roles and permissions to ensure that users can only access data and functions within their permissions.

[0061] Beneficial effects of the present invention:

[0062] The present invention provides a system including a data acquisition module and a real-time monitoring module, which can comprehensively and accurately collect data related to nursing quality, including patient satisfaction, nursing accident rate and infection rate. The data acquisition module integrates multiple sensors and data input interfaces to ensure that different types of nursing quality data are effectively collected. The real-time monitoring module uses a data cache system to ensure the stability and continuity of data transmission, and monitors the collected data in real time to ensure the real-time and accuracy of the data.

[0063] In the present invention, the intelligent analysis module uses machine learning algorithms to conduct in-depth analysis of nursing quality data to identify potential problems and trends. The intelligent analysis module is connected to the alarm generation module. When the monitoring data is abnormal or exceeds a predetermined threshold, the alarm generation module can automatically issue an alarm to remind nursing staff to take timely measures. The alarm generation module uses preset thresholds and trigger conditions, SMS, email, mobile application notifications and other methods to ensure that the alarm information can be quickly conveyed to relevant personnel, effectively prevent the occurrence of nursing accidents, and improve the response speed and accuracy of nursing quality management.

[0064] The decision support module of the present invention automatically generates suggestions and decision support for optimizing nursing processes based on the analysis results and alarm information provided by the intelligent analysis module, using the rule engine and knowledge base, helping the nursing team to make scientific and reasonable decisions. The visualization module provides a user interface for nursing staff to view monitoring data, alarm information and decision suggestions. Through a variety of visualization tools such as comprehensive dashboards, trend charts, and alarm details, nursing staff can intuitively understand changes in nursing quality and potential problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0066] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0067] Figure 2 Schematic diagram of the intelligent analysis module process of an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0069] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0070] like Figure 1-Figure 2 As shown, the real-time nursing quality monitoring and alarm system includes a data acquisition module, a real-time monitoring module, an intelligent analysis module, an alarm generation module, a decision support module and a visualization module, wherein;

[0071] The data collection module is used to collect nursing quality data, including patient satisfaction, nursing accident rate and infection rate;

[0072] The real-time monitoring module is connected to the data acquisition module to monitor the collected nursing quality data in real time to ensure the real-time and accuracy of the data;

[0073] The intelligent analysis module is connected to the real-time monitoring module and is used to process and analyze the monitored data using data analysis and machine learning algorithms to identify potential problems and trends;

[0074] The alarm generation module is connected to the intelligent analysis module. When the monitoring data is abnormal or exceeds the predetermined threshold, an alarm is automatically issued to remind the nursing staff to take timely measures;

[0075] The decision support module is connected with the intelligent analysis module and the alarm generation module to provide suggestions and decision support for optimizing the nursing process based on the analysis results;

[0076] The visualization module provides a user interface for caregivers to view monitoring data, alarm information, and decision suggestions.

[0077] The data collection module includes a patient satisfaction data collection submodule, a nursing accident rate data collection submodule and an infection rate data collection submodule, wherein;

[0078] The patient satisfaction data collection submodule specifically includes:

[0079] Electronic questionnaire: When patients are discharged from hospital or during the nursing stage, electronic questionnaires are sent to patients or their families via electronic devices (such as tablets or smartphones) to collect their evaluation of satisfaction with nursing services;

[0080] Telephone survey: Conduct satisfaction surveys with patients or their families through voice interaction, and enter the collected data into the system;

[0081] Online evaluation platform: Through the hospital's official website or a dedicated nursing evaluation app, patients are allowed to fill out satisfaction evaluation online after receiving care;

[0082] The nursing accident rate data collection submodule specifically includes:

[0083] Event reporting system: When a nursing accident (such as medication error, fall, etc.) occurs, the nursing staff will record the accident in detail through the hospital's internal event reporting system, including time, location, participants, and accident description;

[0084] Sensors and monitoring devices: Install monitoring devices in patient rooms to automatically detect and record nursing incidents, such as patient falls or equipment failures;

[0085] Electronic medical record system integration: extract relevant accident data from the hospital's internal electronic medical record system to ensure data consistency and accuracy;

[0086] The infection rate data collection submodule specifically includes:

[0087] Laboratory test data integration: Integrate with the hospital's laboratory information system to automatically collect laboratory test data related to infection, such as blood culture results, urine culture results, etc.;

[0088] Nursing record unit: Nursing staff record the patient's infection symptoms and nursing measures (such as disinfection, anti-infection treatment, etc.) in their daily work, which are collected through the nursing record unit;

[0089] Public health monitoring system: Integrate with the infection monitoring system of the public health department to obtain infection rate data in the region to help hospitals identify and respond to infection risks.

[0090] The real-time monitoring module specifically includes:

[0091] Data reception and caching: Apache Kafka is used as the data stream processing framework to receive nursing quality data from the data acquisition module in real time, and Redis is used as the in-memory database for data caching to ensure efficient reading and writing of real-time data;

[0092] Data validation and cleaning: Use the Drools rule engine to validate the format and content of the received data to ensure data accuracy. The validation rules include data integrity check, data type matching check, and value range rationality check. The received data is cleaned, including removing duplicate data, processing missing values ​​and outliers, to ensure data quality.

[0093] Real-time data processing: Use Apache Flink for real-time data computing and analysis, including calculating nursing accident rates and infection rates, and generating real-time statistics;

[0094] Data storage and management: Use TimescaleDB as a real-time database to store processed real-time data, ensure efficient query and management of data, and regularly archive real-time data to PostgreSQL for long-term storage and historical data analysis;

[0095] Data visualization: Use Grafana to build a real-time dashboard to display the real-time status and trend of nursing quality data, which is convenient for nursing staff and managers to view at any time. It allows users to customize monitoring views and indicators to meet the real-time monitoring requirements of different roles and needs;

[0096] Through the above design scheme, the real-time monitoring module can efficiently and accurately monitor the nursing quality data in real time, ensure the real-time and accuracy of the data, and provide strong support for improving the quality of nursing.

[0097] The intelligent analysis module specifically includes:

[0098] Data standardization: Receive the nursing quality data processed by the real-time monitoring module in real time, perform standardization, and extract features from the processed data, such as extracting statistical features such as mean, median, and standard deviation from patient satisfaction data;

[0099] Machine learning model: Use support vector machine model for classification and regression analysis to predict potential problems and trends. Use training data set to train the support vector machine model, evaluate model performance through cross-validation, and use validation data set to validate the support vector machine model to ensure the generalization ability and prediction accuracy of the model.

[0100] Real-time prediction: Use the trained support vector machine model to predict real-time nursing quality data and identify potential problems and trends. For example, it can predict whether nursing satisfaction will decrease in a certain period of time in the future, so as to take measures to improve it in advance.

[0101] Anomaly detection: Real-time detection of anomalies in data, timely discovery and alarm of potential problems. The support vector machine model can identify anomalies in data through prediction error and outlier detection. If the actual data is far from the predicted value, there may be potential problems. For example, if the actual nursing accident rate is much higher than the model prediction value, further investigation is needed to find the cause.

[0102] Feature importance analysis: Through feature selection and importance analysis, the support vector machine model identifies which features (such as nursing staff’s work experience, patient’s condition severity, etc.) have the greatest impact on nursing quality, so as to make targeted improvements;

[0103] The calculation formula is as follows:

[0104] Support vector machine classification model: The objective function is expressed as: ξ i , where w is the weight vector, b is the bias, ξ i is the loose ground variable, C is the penalty parameter;

[0105] Constraints: y i (w·x i +b)≥1-ξ i ,ξ i ≥0,i=1,…,n, where x i is the input sample, y i is the corresponding label;

[0106] Support vector regression model: The objective function is expressed as: Among them, ξ i and is the slack variable;

[0107] Constraints: Among them, ∈ is a tolerance parameter;

[0108] Through the support vector machine model, the intelligent analysis module can effectively identify potential problems and trends in nursing quality, helping the nursing team to take timely measures to improve nursing quality.

[0109] The intelligent analysis module can customize analysis rules according to different nursing scenarios and needs, and provide personalized nursing quality improvement solutions, including:

[0110] Define rules: Nurses and managers define rules through the API. For example, set an alarm to be triggered when the patient satisfaction rate is lower than 3.0 and the nursing accident rate is higher than 0.05.

[0111] Rule management: Use the Drools rule engine to manage and execute custom rules, ensure flexibility and scalability, support the addition, modification, deletion and version control of rules, and ensure the accuracy and timeliness of rules;

[0112] Real-time data analysis: The support vector machine model predicts the real-time nursing quality data and generates prediction results. The prediction results and real-time nursing quality data are input into the rule engine, and the custom rules are applied for analysis. If the rule conditions are met, the corresponding alarm is generated or other actions are taken;

[0113] Real-time anomaly detection: detect anomalies in data in real time, analyze them through the rule engine, identify potential problems and trigger alerts;

[0114] Generate improvement plans: Generate personalized nursing quality improvement plans based on analysis results and custom rules, such as:

[0115] Improve training: If the model prediction results and custom rules show that the nursing staff's lack of skills leads to low patient satisfaction, it is recommended to increase the professional skills training of the nursing staff;

[0116] Adjust workflow: If the analysis results show that certain workflows have bottlenecks, we can recommend ways to optimize these processes and reduce the occurrence of nursing accidents;

[0117] Increase human resources: If the nursing accident rate is high and the nursing staff's workload is too heavy, it is recommended to increase the number of nursing staff to share the workload and improve the quality of nursing;

[0118] Customized analysis rules can flexibly respond to different nursing scenarios and needs, provide personalized nursing quality improvement plans, and improve overall nursing quality.

[0119] When the intelligent analysis module detects anomalies or trend changes in the data (such as a sudden drop in patient satisfaction or an increase in the rate of nursing accidents), it passes the results to the alarm generation module, which specifically includes:

[0120] Threshold setting: Setting predetermined thresholds based on historical statistics of nursing quality data and expert advice;

[0121] Alarm rule management: configure predetermined thresholds and alarm trigger conditions, for example, set an alarm to be triggered when patient satisfaction is lower than a certain value or the nursing accident rate is higher than a certain threshold;

[0122] Real-time monitoring: Continuously monitor the data results transmitted by the intelligent analysis module. If it is detected that the data exceeds the predetermined threshold or meets abnormal conditions, the alarm generation process is immediately triggered;

[0123] Alarm notification mechanism: Alarm information is sent to relevant caregivers and managers through various means (such as SMS, email, mobile application notification, etc.).

[0124] The decision support module specifically includes:

[0125] Integration of analysis results: The decision support module obtains the analysis results and alarm information of nursing quality data from the intelligent analysis module and the alarm generation module. The intelligent analysis module provides the long-term trend, potential problems and abnormal conditions of the data, and the alarm generation module issues an alarm when the data is abnormal or exceeds the predetermined threshold;

[0126] Generate optimization suggestions: Based on the integrated analysis results and alarm information, the decision support module uses the rule engine and the configured knowledge base to generate suggestions for optimizing the nursing process. The configured knowledge base contains nursing process optimization solutions, best practices, and historical cases. As the basis for decision support, the rule engine can generate corresponding optimization suggestions based on pre-set rules (such as thresholds of nursing quality indicators, anomaly detection criteria, etc.), for example:

[0127] If patient satisfaction falls below a certain threshold, additional nursing staff training is recommended;

[0128] If the nursing accident rate is above a certain threshold, it is recommended to optimize the nursing process and increase safety measures;

[0129] Decision support output: Generate specific suggestions for optimizing nursing processes, including improvement measures, expected effects and implementation steps, and generate detailed decision support reports, including analysis results, alarm information, optimization suggestions and expected effect evaluation;

[0130] Example scenario

[0131] Data reception and integration: The intelligent analysis module detects a decrease in patient satisfaction over a period of time and predicts that more nursing incidents may occur in the future. The alarm generation module generates an alarm indicating that the nursing incident rate exceeds a predetermined threshold and recommends immediate action.

[0132] Rule matching and optimization suggestion generation: The decision support module receives analysis results and alarm information, matches decision rules through the rule engine, and finds the need to optimize nursing staff training and adjust nursing processes;

[0133] The decision support module generates the following specific recommendations:

[0134] Nursing staff training: Organize special training to improve the professional skills of nursing staff and their ability to respond to emergencies;

[0135] Adjust the nursing staff ratio: increase the number of nursing staff during peak hours to ensure that patients receive timely and high-quality care;

[0136] Optimize nursing process: re-evaluate and optimize nursing workflow, reduce unnecessary links and improve work efficiency;

[0137] Generate decision support reports detailing analysis results, alarm information, optimization suggestions, and expected effect evaluation;

[0138] Output optimization suggestions and reports: The decision support module sends suggestions and decision support reports for optimizing nursing processes to nursing teams and managers;

[0139] Through the above workflow, the decision support module can generate specific and actionable suggestions for optimizing the nursing process based on the analysis results and alarm information provided by the intelligent analysis module and the alarm generation module, helping the nursing team to improve the quality of care and patient satisfaction in a timely and effective manner. The core of the decision support module lies in the management of the rule engine and knowledge base, as well as the seamless integration with the intelligent analysis and alarm generation modules.

[0140] The visualization module specifically includes:

[0141] User interface design: Provide a comprehensive dashboard that displays quality of care indicators, trend analysis, alert information, and decision-making recommendations;

[0142] Data visualization: Use charts and graphs to present monitoring data and analysis results;

[0143] Interactive functions: Provide interactive functions to allow users to screen, filter and drill data to view detailed information;

[0144] Alarm display: displays an overview of current and historical alarms, including alarm type, trigger time, severity, and processing status, and provides detailed alarm information, including anomaly detection results, specific data, and reasons for triggering the alarm;

[0145] Decision support presentation: Presents suggestions for optimizing nursing processes generated by the decision support module, including specific improvement measures and expected results, and provides implementation steps and guidance to help nursing staff and managers implement improvement measures.

[0146] The visualization module further includes a user management unit, which provides different levels of data access and operation permissions based on user roles and permissions, including:

[0147] User role and permission management: define different user roles, such as caregivers, care managers, and system administrators, and assign different data access and operation permissions based on user roles to ensure data security and privacy protection;

[0148] User authentication and access control: Use username / password or multi-factor authentication mechanisms to ensure that only authorized users have access. Perform access control based on user roles and permissions to ensure that users can only access data and functions within their permissions.

[0149] Example scenario:

[0150] Define three roles: caregiver, care manager, and system administrator;

[0151] Nursing staff can only view patient satisfaction data and alarm information;

[0152] Care managers can view all care quality data and alert information and generate decision support reports;

[0153] System administrators can manage user roles and assign permissions;

[0154] User authentication and access control:

[0155] When users log in, they authenticate their identity using username / password and SMS verification code;

[0156] The system controls the user's access scope based on the user's role and permissions, ensuring that the user can only view and operate the data within the scope of his or her permissions.

[0157] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0158] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Real-time nursing quality monitoring and alarm system, characterized by: It includes data acquisition module, real-time monitoring module, intelligent analysis module, alarm generation module, decision support module and visualization module, among which; The data collection module is used to collect nursing quality data, including patient satisfaction, nursing accident rate and infection rate; The real-time monitoring module is connected to the data acquisition module and is used to monitor the collected nursing quality data in real time to ensure the real-time and accuracy of the data; The intelligent analysis module is connected to the real-time monitoring module and is used to process and analyze the monitored data using data analysis and machine learning algorithms to identify potential problems and trends; The alarm generation module is connected to the intelligent analysis module, and when the monitoring data is abnormal or exceeds a predetermined threshold, an alarm is automatically issued to remind the nursing staff to take timely measures; The decision support module is connected to the intelligent analysis module and the alarm generation module, and is used to provide suggestions and decision support for optimizing the nursing process according to the analysis results; The visualization module provides a user interface for nursing staff to view monitoring data, alarm information and decision suggestions.

2. The real-time nursing quality monitoring and alarm system according to claim 1, characterized in that: The data collection module includes a patient satisfaction data collection submodule, a nursing accident rate data collection submodule and an infection rate data collection submodule, wherein; The patient satisfaction data collection submodule specifically includes: Electronic questionnaire: When patients are discharged from hospital or during the nursing stage, electronic questionnaires are sent to patients or their families through electronic devices to collect their evaluation of satisfaction with nursing services; Telephone survey: Conduct satisfaction surveys with patients or their families through voice interaction, and enter the collected data into the system; Online evaluation platform: Through the hospital's official website or a dedicated nursing evaluation app, patients are allowed to fill out satisfaction evaluation online after receiving care; The nursing accident rate data collection submodule specifically includes: Incident reporting system: When a nursing accident occurs, the nursing staff will record the accident in detail through the hospital's internal incident reporting system, including time, location, participants, and accident description; Sensors and monitoring equipment: Install monitoring equipment in patient wards to automatically detect and record nursing incidents; Electronic medical record system integration: extract relevant accident data from the hospital's internal electronic medical record system to ensure data consistency and accuracy; The infection rate data collection submodule specifically includes: Laboratory test data integration: Integrate with the hospital's laboratory information system to automatically collect laboratory test data related to infection; Nursing record unit: Nursing staff record patients’ infection symptoms and nursing measures in their daily work, which are collected through the nursing record unit; Public health monitoring system: Integrate with the infection monitoring system of the public health department to obtain infection rate data in the region to help hospitals identify and respond to infection risks.

3. The real-time nursing quality monitoring and alarm system according to claim 2, characterized in that: The real-time monitoring module specifically includes: Data reception and caching: Apache Kafka is used as the data stream processing framework to receive nursing quality data from the data acquisition module in real time, and Redis is used as the in-memory database for data caching; Data validation and cleaning: Use the Drools rule engine to validate the format and content of the received data. The validation rules include data integrity check, data type matching check, and value range rationality check. The received data is cleaned, including removing duplicate data, processing missing values ​​and outliers, to ensure data quality. Real-time data processing: Use Apache Flink for real-time data computing and analysis, including calculating nursing accident rates and infection rates, and generating real-time statistics; Data storage and management: Use TimescaleDB as a real-time database to store processed real-time data, and regularly archive real-time data to PostgreSQL; Data visualization: Use Grafana to build a real-time dashboard to display the real-time status and trends of nursing quality data, which is convenient for nursing staff and managers to view at any time. It allows users to customize monitoring views and indicators to meet the real-time monitoring requirements of different roles and needs.

4. The real-time nursing quality monitoring and alarm system according to claim 3, characterized in that: The intelligent analysis module specifically includes: Data standardization: receiving the nursing quality data processed by the real-time monitoring module in real time, performing standardization processing, and extracting features from the processed data; Machine learning models: Use support vector machine models for classification and regression analysis to predict potential problems and trends, train support vector machine models using training datasets, evaluate model performance through cross-validation, and validate support vector machine models using validation datasets; Real-time prediction: Use the trained support vector machine model to predict real-time nursing quality data and identify potential problems and trends; Anomaly detection: Real-time detection of anomalies in data, timely discovery and alarm of potential problems; Feature importance analysis: Through feature selection and importance analysis, the support vector machine model identifies which features have the greatest impact on the quality of care, so that targeted improvements can be made.

5. The real-time nursing quality monitoring and alarm system according to claim 4, characterized in that: The intelligent analysis module can customize analysis rules according to different nursing scenarios and needs, and provide personalized nursing quality improvement solutions, including: Define rules: Nurses and managers define rules through the API interface; Rule management: Use the Drools rule engine to manage and execute custom rules, and support adding, modifying, deleting, and versioning rules; Real-time data analysis: The support vector machine model predicts the real-time nursing quality data, generates prediction results, inputs the prediction results and real-time nursing quality data into the rule engine, and applies custom rules for analysis; Real-time anomaly detection: detect anomalies in data in real time, analyze them through the rule engine, identify potential problems and trigger alerts; Generate improvement plans: Generate personalized nursing quality improvement plans based on analysis results and customized rules.

6. The real-time nursing quality monitoring and alarm system according to claim 4, characterized in that: When the intelligent analysis module detects anomalies or trend changes in the data, it transmits the results to the alarm generation module, which specifically includes: Threshold setting: Setting predetermined thresholds based on historical statistics of nursing quality data and expert advice; Alert rule management: configure predetermined thresholds and alert trigger conditions; Real-time monitoring: Continuously monitor the data results transmitted by the intelligent analysis module. If it is detected that the data exceeds the predetermined threshold or meets abnormal conditions, the alarm generation process is immediately triggered; Alarm notification mechanism: Alarm information is sent to relevant caregivers and managers through a variety of methods.

7. The real-time nursing quality monitoring and alarm system according to claim 6, characterized in that: The decision support module specifically includes: Integration of analysis results: The decision support module obtains the analysis results and alarm information of nursing quality data from the intelligent analysis module and the alarm generation module; Generate optimization recommendations: Based on the integrated analysis results and alarm information, the decision support module uses the rule engine and the configured knowledge base to generate recommendations for optimizing the nursing process; Decision support output: Generate specific recommendations for optimizing nursing processes, including improvement measures, expected effects, and implementation steps, and generate detailed decision support reports, including analysis results, alarm information, optimization recommendations, and expected effect evaluation.

8. The real-time nursing quality monitoring and alarm system according to claim 1, characterized in that: The visualization module specifically includes: User interface design: Provide a comprehensive dashboard that displays care quality indicators, trend analysis, alert information, and decision-making recommendations; Data visualization: Use charts and graphs to present monitoring data and analysis results; Interactive functions: Provide interactive functions to allow users to screen, filter and drill data to view detailed information; Alarm display: displays an overview of current and historical alarms, including alarm type, trigger time, severity, and processing status, and provides detailed alarm information, including anomaly detection results, specific data, and reasons for triggering the alarm; Decision support presentation: Presents suggestions for optimizing nursing processes generated by the decision support module, including specific improvement measures and expected results, and provides implementation steps and guidance to help nursing staff and managers implement improvement measures.

9. The real-time nursing quality monitoring and alarm system according to claim 8, characterized in that: The visualization module further includes a user management unit, which provides different levels of data access and operation permissions according to user roles and permissions, including: User role and permission management: define different user roles and assign different data access and operation permissions according to user roles; User authentication and access control: Use username / password or multi-factor authentication mechanisms to ensure that only authorized users have access. Perform access control based on user roles and permissions to ensure that users can only access data and functions within their permissions.

Images