Neurosurgery nursing management system based on cloud computing

Abstract

The invention relates to the field of nursing management, and discloses a neurosurgical nursing management system based on cloud computing, which is used for solving the problem of data conflict or data synchronization delay when nursing management is carried out according to patient information, and comprises the following steps: monitoring and collecting initial multi-source data; the multi-source data comprises vital sign data, postoperative medication records, nursing observation records and postoperative image data, performing synchronous processing on the initial multi-source data to obtain synchronous multi-source data, performing data conflict processing on the synchronous multi-source data to obtain actual multi-source data, and storing the actual multi-source data into a database; according to the method, the actual multi-source data is subjected to data integration to obtain patient integration information, data analysis is performed according to the patient integration information, health early warning is generated, personalized nursing tasks are designed according to the patient integration information, and the tasks are allocated to related nursing personnel, so that the accuracy of acquiring the patient information is effectively improved, and the nursing quality and the treatment effect are improved.

Description

Technical Field

[0001] The present invention relates to the field of nursing management, and more particularly to a neurosurgery nursing management system based on cloud computing. Background Art

[0002] In the modern medical environment, especially in the field of neurosurgery, nursing work is extremely specialized and complex. Neurosurgery patients often require highly sophisticated nursing management, involving multiple stages before, during, and after surgery.

[0003] Existing neurosurgery care management systems typically obtain multi-source patient data, including operating room records, anesthesia monitoring, postoperative care records, vital signs monitoring, and medication management, integrate the patient's multi-source data, and make care arrangements and resource allocation based on the integrated patient information.

[0004] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0005] In practice, when merging multi-source patient data (such as operating room records, anesthesia records, and vital sign monitoring data), data conflicts or synchronization delays can occur, preventing timely and accurate updates of the patient's latest information to the nursing management system. This prevents caregivers from obtaining real-time patient information, leading to delays in nursing and treatment decisions. Especially during critical stages such as emergency or postoperative care, delayed updates to patient data pose significant safety risks, impacting care quality and treatment outcomes. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a neurosurgery nursing management system based on cloud computing to solve the problems existing in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A neurosurgery nursing management system based on cloud computing comprises: a data acquisition and monitoring module for monitoring and acquiring initial multi-source data, the multi-source data including vital sign data, postoperative medication records, nursing observation records, and postoperative imaging data, each data item including a data ID, a timestamp, a data version number, and a data source, and each data item consisting of a number of fields, and transmitting the initial multi-source data to a data synchronization module; a data synchronization module for performing synchronization processing on the initial multi-source data to obtain synchronized multi-source data, and transmitting the synchronized multi-source data to a data conflict handling module; a data conflict handling module for performing data conflict processing on the synchronized multi-source data to obtain actual multi-source data, storing the actual multi-source data in a database, and transmitting the actual multi-source data to a patient data integration module; a patient data integration module for performing data integration on the actual multi-source data to obtain integrated patient information, and transmitting the integrated patient information to an early warning module and a nursing task assignment module; the early warning module for performing data analysis based on the integrated patient information to generate health warnings; and a nursing task assignment module for designing personalized nursing tasks based on the integrated patient information and assigning the tasks to relevant nursing staff.

[0009] Preferably, the monitoring and collection of initial multi-source data steps are: real-time collection of vital signs data and postoperative medication records, and using the real-time collected vital signs data and postoperative medication records as initial multi-source data; setting an initial update time interval, dynamically adjusting the initial update time interval to obtain an actual update time interval, collecting nursing observation records and postoperative imaging data according to the actual time interval, and using the nursing observation records and postoperative imaging data collected each time as initial multi-source data; if vital signs data, postoperative medication records, nursing observation records and postoperative imaging data are collected at the same time, the collected vital signs data, postoperative medication records, nursing observation records and postoperative imaging data are used as initial multi-source data.

[0010] Preferably, the actual update time interval acquisition step is as follows: setting a monitoring time period, acquiring the number of changes in vital sign data and the number of changes in postoperative medication records within the monitoring time period, and evaluating the data change degree based on the number of changes in vital sign data and the number of changes in postoperative medication records; acquiring system load data in real time, the system load data including CPU usage, memory usage and disk I / O load, and evaluating the system load degree based on the system load data; acquiring network broadband speed in real time, normalizing the data change degree, system load degree and network broadband speed, and evaluating the time adjustment coefficient based on the normalized data change degree, system load degree and network broadband speed. The specific acquisition steps are as follows: Where, Expressed as the time adjustment coefficient, Expressed as the degree of data change, Indicates the degree of system load, It is expressed as the network broadband speed; set the time adjustment threshold, calculate the ratio of the time adjustment threshold and the time adjustment coefficient to obtain the time adjustment factor; multiply the time adjustment factor and the initial update time interval to obtain the actual update time interval.

[0011] Preferably, the steps of synchronizing the initial multi-source data to obtain synchronized multi-source data are as follows: screening the database according to the data ID, data version number and data source of the initial multi-source data; if there is no corresponding data ID, data version number and data source at the same time, it is determined that the initial multi-source data is stored for the first time, and the initial multi-source data is used as the synchronized multi-source data; if there is a corresponding data ID, data version number and data source at the same time, the timestamp of the initial multi-source data is obtained and recorded as the new timestamp, and the timestamp of the data corresponding to the data ID, data version number and data source is obtained and recorded as the old timestamp; the new timestamp is compared with the old timestamp; if the new timestamp is greater than the old timestamp, the initial multi-source data is used as the synchronized multi-source data; if the new timestamp is less than or equal to the old timestamp, the initial multi-source data is discarded, and the data corresponding to the old timestamp is used as the synchronized multi-source data.

[0012] Preferably, the steps of performing data conflict processing on the synchronized multi-source data to obtain the actual multi-source data are as follows: performing data conflict identification on the synchronized multi-source data; if there is no conflicting data in the synchronized multi-source data, the synchronized multi-source data is recorded as the actual multi-source data; if there is conflicting data in the synchronized multi-source data, the data consistency of the conflicting data is evaluated, and the data consistency is compared with the consistency threshold; if the data consistency is greater than or equal to the consistency threshold, it is judged that the conflicting data has high consistency, and the mean calculation result is used as the final data of the conflicting data, and the final data is merged with the remaining synchronized multi-source data to obtain the actual multi-source data; if the data consistency is less than the consistency threshold, it is judged that the conflicting data has low consistency, and the field information of each conflicting data is obtained, and the data integrity coefficient is calculated according to the field information; the historical data of the data item corresponding to the conflicting data is obtained, and the data trend reliability coefficient is calculated according to the historical data; the data integrity coefficient and the data trend reliability coefficient are normalized, and the data reliability index is obtained according to the data integrity coefficient and the data trend reliability coefficient after normalization. The specific acquisition steps are as follows: Where, Expressed as the data reliability index, Expressed as the data integrity coefficient, Expressed as the data trend reliability coefficient, 、 Expressed as the weight coefficient of the data integrity coefficient and the weight coefficient of the data trend reliability coefficient; obtain the data reliability index of all conflicting data, and select the data with the largest data reliability index as the final data of the conflicting data, merge the final data with the remaining synchronized multi-source data, and obtain the actual multi-source data.

[0013] Preferably, the step of identifying data conflicts for synchronized multi-source data is as follows: if there are identical data items from different data sources in the synchronized multi-source data, a data conflict check is performed on the identical data items from different data sources, and the data conflict check includes a data consistency check, a data format consistency check, and a unit consistency check; if there is an inconsistency in the data conflict check, it is identified that conflicting data exists in the synchronized multi-source data.

[0014] Preferably, the step of evaluating the data consistency of the conflicting data comprises: obtaining the optimal value of each conflicting data value and the data item corresponding to the conflicting data, and calculating the data consistency based on the absolute difference value of each conflicting data value using the root mean square error. The specific obtaining steps are: Where, It is expressed as data consistency, n is the number of conflicting data, It is represented as the value of the i-th conflicting data, and D is the optimal value of the data item corresponding to the conflicting data.

[0015] Preferably, the step of obtaining the data integrity coefficient is: obtaining field information of the conflicting data, the field information including the total number of fields, the number of missing fields and the valid value range of each field; calculating the ratio of the number of missing fields to the total number of fields to obtain the missing field ratio; screening out fields that are not in the valid value range and recording them as invalid fields, calculating the ratio of the number of invalid fields to the total number of fields to obtain the invalid field ratio; and obtaining the data integrity coefficient based on the evaluation of the missing field ratio and the invalid field ratio.

[0016] Preferably, the data trend reliability coefficient acquisition step is as follows: within the monitoring period, historical data of the data item corresponding to the conflict data is acquired from the database; a trend model is fitted based on the historical data by regression analysis, and the data of the current timestamp is predicted by the trend model, which is recorded as the historical trend prediction value; the absolute difference between each conflict data and the historical trend prediction value is calculated as the residual, and the data trend reliability coefficient is calculated based on the residual. The specific acquisition steps are as follows: Where, Expressed as the data trend reliability coefficient, Expressed as residual.

[0017] Preferably, the steps of integrating the actual multi-source data to obtain the patient integrated information are: standardizing the actual multi-source data; associating the data based on the data ID; time-serializing each multi-source data according to the timestamp to obtain a dynamic change curve, and presenting the dynamic change curve of the multi-source data in a visual manner to obtain the patient integrated information.

[0018] Technical effects and advantages of the present invention:

[0019] Monitor and collect initial multi-source data, which includes vital signs data, postoperative medication records, nursing observation records, and postoperative imaging data. Synchronize the initial multi-source data to obtain synchronized multi-source data. Perform data conflict resolution on the synchronized multi-source data to obtain actual multi-source data, and store the actual multi-source data in the database. Perform data integration on the actual multi-source data to obtain patient integrated information. Based on the patient integrated information, perform data analysis and generate health warnings. Based on the patient integrated information, design personalized nursing tasks and assign tasks to relevant nursing staff, effectively improving the accuracy of obtaining patient information, improving nursing quality and treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A structural diagram of a neurosurgery nursing management system based on cloud computing provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. In addition, the forms of the various structures described in the following embodiments are merely examples. The cloud computing-based neurosurgery care management system involved in the present invention is not limited to the various structures described in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0022] The present invention provides a neurosurgery nursing management system based on cloud computing, such as Figure 1 As shown, the following steps are included:

[0023] The data acquisition and monitoring module is used to monitor and collect initial multi-source data. The multi-source data may include vital signs data, postoperative medication records, nursing observation records, and postoperative imaging data. Each piece of data includes a data ID, timestamp, data version number, and data source. Each piece of data consists of several fields. The initial multi-source data is transmitted to the data synchronization module.

[0024] The data ID is used to uniquely identify a data item, representing a certain data item of a certain patient, such as a patient's blood pressure data; the timestamp is the exact time when the data was generated; the data version number is the version number of the data, which increases each time the data is updated; the data source is used to indicate the source of the data, for example, this data comes from the operating room.

[0025] In this embodiment, it should be specifically explained that the steps of monitoring and collecting initial multi-source data are:

[0026] Collect vital signs data and postoperative medication records in real time, and use the real-time collected vital signs data and postoperative medication records as initial multi-source data;

[0027] Set the initial update time interval, dynamically adjust the initial update time interval to obtain the actual update time interval, collect nursing observation records and postoperative imaging data according to the actual time interval, and use the nursing observation records and postoperative imaging data collected each time as the initial multi-source data;

[0028] If vital signs data, postoperative medication records, nursing observation records, and postoperative imaging data are collected at the same time, the collected vital signs data, postoperative medication records, nursing observation records, and postoperative imaging data are used as initial multi-source data.

[0029] Real-time updates of vital signs and post-operative medication records, along with scheduled intervals for updating nursing observation records and post-operative imaging data, ensure that the nursing team always has the latest information on the patient's health status and treatment progress. By updating vital signs and medication records in real time, medical staff can promptly monitor the patient's recovery progress, quickly identify any abnormal changes, and make appropriate adjustments. Setting intervals for updating nursing observation records and post-operative imaging data ensures frequent information updates while avoiding data overload, allowing caregivers to work in an organized manner. This dynamic updating and intelligent management improves nursing efficiency, reduces human error, optimizes the patient care experience, and ensures an efficient and safe treatment process.

[0030] In this embodiment, it should be specifically explained that the steps for obtaining the actual update time interval are:

[0031] Set a monitoring period, obtain the number of changes in vital signs data and the number of changes in postoperative medication records within the monitoring period, and evaluate the degree of data change based on the number of changes in vital signs data and the number of changes in postoperative medication records. The specific acquisition steps are as follows:

[0032] ;

[0033] Where, Expressed as the degree of data change, Expressed as the number of changes in vital signs data, It is expressed as the number of changes in postoperative medication records;

[0034] Obtain system load data in real time. System load data includes CPU usage, memory usage, and disk I / O load. The system load level is evaluated based on the system load data. The specific acquisition steps are as follows:

[0035] ;

[0036] Where, Indicates the degree of system load, Expressed as CPU usage, Expressed as memory usage, Expressed as disk I / O load;

[0037] The network broadband speed is obtained in real time, and the degree of data change, the degree of system load, and the network broadband speed are normalized so that the three parameters with different numerical ranges, namely the degree of data change, the degree of system load, and the network bandwidth speed, are kept within the same scale range (such as 0 to 1), thereby eliminating dimensional differences and avoiding a certain parameter from having too large or too small an impact on the calculation of the time adjustment coefficient. Normalization can improve the comparability of parameters, make calculations more stable, ensure that the influence of the time adjustment coefficient on each parameter is balanced, and avoid a certain parameter from dominating or being ignored. In addition, normalization can also reduce calculation errors, make data adjustments smoother during dynamic changes, optimize the system's adaptability, and improve the stability and data synchronization efficiency of the neurosurgery nursing management system. The time adjustment coefficient is obtained based on the degree of data change, the degree of system load, and the network broadband speed after normalization. The specific acquisition steps are as follows:

[0038] ;

[0039] Where, Expressed as the time adjustment coefficient, Expressed as the degree of data change, Indicates the degree of system load, Expressed as network broadband speed;

[0040] Set a time adjustment threshold, and calculate the ratio of the time adjustment threshold to the time adjustment coefficient to obtain the time adjustment factor;

[0041] The actual update time interval is calculated by multiplying the time adjustment factor by the initial update time interval.

[0042] The benefit of dynamically adjusting the time interval for batch updating of nursing observation records and postoperative imaging data lies in balancing the real-time nature of data synchronization with system resource consumption. This ensures that when data changes frequently or during critical care phases (such as the early stages of postoperative recovery), the time interval can be shortened, increasing the frequency of data updates to promptly reflect patient status and assist in nursing decision-making. When data changes less frequently or the system load is high, the time interval can be extended to reduce unnecessary data transmission and storage pressure, thereby improving system operational efficiency. Furthermore, this dynamic adjustment mechanism optimizes network bandwidth usage, preventing data backlogs or system overloads, thereby improving the stability of the nursing management system and the accuracy of data processing, ensuring that caregivers always have access to the latest patient information.

[0043] A data synchronization module is used to synchronize the initial multi-source data to obtain synchronized multi-source data, and transmit the synchronized multi-source data to the data conflict processing module;

[0044] In this embodiment, it should be specifically explained that the steps of synchronizing the initial multi-source data to obtain synchronized multi-source data are as follows:

[0045] Filter the database based on the data ID, data version number, and data source of the initial multi-source data. If there is no corresponding data ID, data version number, and data source, it is determined that the initial multi-source data is stored for the first time and the initial multi-source data is used as the synchronized multi-source data.

[0046] If there are corresponding data IDs, data version numbers, and data sources, obtain the timestamp of the initial multi-source data and record it as the new timestamp. Obtain the timestamp of the data that corresponds to the data ID, data version number, and data source and record it as the old timestamp.

[0047] Compare the new timestamp with the old timestamp. If the new timestamp is greater than the old timestamp, the initial multi-source data is used as the synchronized multi-source data. If the new timestamp is less than or equal to the old timestamp, the initial multi-source data is discarded and the data corresponding to the old timestamp is used as the synchronized multi-source data.

[0048] After synchronizing multi-source data, data conflicts may arise. This is because different data sources may record or update the same data items for the same patient differently, resulting in inconsistent data. For example, multiple systems may record information such as vital signs and medication use for the same time period, but the data may differ due to measurement methods, timing differences, or device issues. Additionally, data with similar or identical timestamps, inconsistent data formats, and missing data may also cause conflicts.

[0049] The data conflict handling module is used to handle data conflicts on synchronized multi-source data, obtain actual multi-source data, and store the actual multi-source data in the database for easy subsequent calls and queries. For example, the data of body temperature 37°C includes the numerical field: 37 and the unit field: ℃. The actual multi-source data is transmitted to the patient data integration module;

[0050] In this embodiment, it should be specifically explained that the steps for performing data conflict processing on synchronized multi-source data to obtain actual multi-source data are as follows:

[0051] Perform data conflict identification on the synchronized multi-source data. If there is no conflicting data in the synchronized multi-source data, the synchronized multi-source data will be recorded as the actual multi-source data.

[0052] If there is conflicting data in the synchronized multi-source data, the data consistency of the conflicting data is evaluated and compared with the consistency threshold. If the data consistency is greater than or equal to the consistency threshold, the conflicting data is judged to have high consistency. The conflicting data is then averaged and the average calculation result is used as the final data of the conflicting data. The final data is merged with the remaining synchronized multi-source data to obtain the actual multi-source data. The conflicting data is specifically the value of the same data item provided by different data sources.

[0053] If the data consistency is less than the consistency threshold, the conflicting data is judged to have low consistency, the field information of each conflicting data is obtained, and the data integrity coefficient is calculated based on the field information;

[0054] Obtain historical data of the data items corresponding to the conflicting data, and calculate the data trend reliability coefficient based on the historical data;

[0055] The data integrity coefficient and the data trend reliability coefficient are normalized, and the data reliability index is obtained based on the normalized data integrity coefficient and the data trend reliability coefficient. The specific acquisition steps are as follows:

[0056] ;

[0057] Where, Expressed as the data reliability index, Expressed as the data integrity coefficient, when data has high integrity, it means that the data contains all necessary and valid information, with fewer or no missing values, which makes the data more credible in subsequent analysis and decision-making. Specifically, the data integrity coefficient measures the proportion of actual valid content in the data. For example, in vital signs data, if all key indicators are fully recorded and there are fewer missing items, then the data integrity coefficient is higher. The higher the data integrity, the more valid information the data contains, resulting in an increase in the final data reliability index, thereby enhancing the role of data in the decision-making and analysis process. Expressed as the data trend reliability coefficient, the data trend reliability coefficient measures the rationality and consistency of data changes over time. Since the rationality of data trends is one of the important signs of reliable data, the trend reliability coefficient directly affects the level of the data reliability index. Specifically, the higher the data trend reliability coefficient, the more stable and in-line with expectations the data change trend is, making the data more credible, thereby improving its reliability index in the overall assessment. In contrast, if the trend change of the data is unstable or there are abnormal fluctuations, it means that the data may have measurement errors or sensor failures, thereby reducing the reliability of the data. Therefore, the trend reliability coefficient is proportional to the data reliability index, which means that data with more stable trends tend to be more reliable and can provide higher-quality support for subsequent analysis and decision-making. 、 It is expressed as the weight coefficient of the data integrity coefficient and the weight coefficient of the data trend reliability coefficient, and , 、 Obtained through AHP, e.g. 、 It can be 0.4, 0.6;

[0058] The Analytic Hierarchy Process (AHP) is a method for multi-criteria decision analysis. It aims to help decision makers evaluate and select based on different criteria and factors by constructing a hierarchical model. This method breaks down complex decision problems into multiple levels, typically including the objective level, the criteria level, and the alternative level. The AHP assesses the relative importance of each factor through pairwise comparisons, assigning each factor a weighting coefficient. Decision makers compare the relative importance of different factors and use a mathematical model to calculate the weight of each factor. The weighted sum of these factors is then used to arrive at a comprehensive score or decision outcome.

[0059] The data reliability index of all conflicting data is obtained, and the data with the largest data reliability index is selected as the final data of the conflicting data. The final data is merged with the remaining synchronized multi-source data to obtain the actual multi-source data.

[0060] In this embodiment, it should be specifically explained that the steps for identifying data conflicts for synchronized multi-source data are:

[0061] When the timestamps are consistent, if the same data items from different data sources exist in the synchronized multi-source data, a data conflict check is performed on the same data items from different data sources. The data conflict check includes a data consistency check, a data format consistency check, and a unit consistency check. If there is an inconsistency in the data conflict check, it is identified that conflicting data exists in the synchronized multi-source data.

[0062] In this embodiment, it should be specifically explained that the steps for evaluating the data consistency of conflicting data are:

[0063] Obtain the optimal value of each conflicting data value and the corresponding data item of the conflicting data. For example, the optimal data value of body temperature is 36.5. Use the root mean square error to calculate the data consistency based on the absolute difference value of each conflicting data value. The specific steps are as follows:

[0064] ;

[0065] Where, It is expressed as data consistency, n is the number of conflicting data, Denoted as the value of the i-th conflicting data item, D is the optimal value of the corresponding data item. The root mean square error (RMS) effectively quantifies the difference between the values ​​of different data sources and restores the error to the units of the original data by taking the square root, making it easier to understand. The RMS error has the same dimensions as the original data, making the results more interpretable. Furthermore, the RMS error is more sensitive to larger differences and can highlight larger errors in the data, making it very effective in detecting data conflicts or anomalies.

[0066] In this embodiment, it should be specifically explained that the steps for obtaining the data integrity coefficient are:

[0067] Get the field information of the conflicting data, including the total number of fields, the number of missing fields, and the valid value range of each field;

[0068] Calculate the ratio of the number of missing fields to the total number of fields to obtain the missing field ratio;

[0069] Filter out the fields that are not in the valid value range and record them as invalid fields. For example, if the body temperature data is 50℃, the value field: 50 is an invalid field. Calculate the ratio of the number of invalid fields to the total number of fields to get the invalid field ratio.

[0070] The data integrity coefficient is obtained by evaluating the ratio of missing fields and invalid fields. The specific steps to obtain it are:

[0071] ;

[0072] Where, Expressed as the data integrity coefficient, Expressed as the proportion of missing fields, Indicates an invalid field scale.

[0073] In this embodiment, it should be specifically explained that the steps for obtaining the data trend reliability coefficient are:

[0074] During the monitoring period, historical data of the data items corresponding to the conflicting data are obtained from the database. The monitoring period can be changed according to the actual situation. For example, the monitoring period can be one week or half a month.

[0075] Based on historical data, a trend model is fitted through regression analysis, and the data of the current timestamp is predicted by the trend model, which is recorded as the historical trend forecast value. Regression analysis is a statistical method used to study the relationship between variables and predict or explain trends and patterns in the data by fitting a model. Regression analysis establishes a mathematical model by finding the mathematical relationship between independent variables and dependent variables. The most common regression analysis method is linear regression, which assumes a linear relationship between independent variables and dependent variables, that is, a straight line is used to represent the trend of the data. Regression analysis can not only be used to predict future data, but also help evaluate the strength and direction of the association between variables;

[0076] Calculate the absolute difference between each conflict data and the historical trend forecast value, record it as the residual, and calculate the data trend reliability coefficient based on the residual. The specific steps to obtain it are:

[0077] ;

[0078] Where, Expressed as the data trend reliability coefficient, Expressed as residuals, the exponential function responds more sensitively to increases in residuals. When the data deviates slightly from the historical trend (small residuals), the trend reliability coefficient changes little and remains high. However, when the residuals increase (i.e., the data deviates significantly from the trend), the trend reliability coefficient decreases rapidly, effectively distinguishing between data that conform to the trend and those that do not. This method makes the changes in the trend reliability coefficient smoother and more sensitive, helping to accurately assess data reliability.

[0079] The patient data integration module is used to integrate the actual multi-source data to obtain patient integrated information, and transmit the patient integrated information to the early warning module and the nursing task allocation module;

[0080] In this embodiment, it should be specifically explained that the steps for integrating actual multi-source data to obtain integrated patient information are as follows:

[0081] Standardize actual multi-source data for integrated analysis;

[0082] Data association is performed based on data ID to ensure that all associated data belong to the same patient;

[0083] Each multi-source data point is time-serialized according to its timestamp to generate a dynamic change curve. This dynamic change curve of the multi-source data is then visualized to obtain integrated patient information. Time serialization is the process of arranging and organizing multi-source data in the order of its timestamps. Through time serialization, the system can align time data from different sources and frequencies, so that all data points are arranged in order on the timeline to form a continuous time series. This processing method ensures that various types of data can be dynamically displayed and analyzed based on the patient's actual changes, thereby providing caregivers with a comprehensive, time-related curve of changes in the patient's health status, supporting real-time monitoring and prediction.

[0084] The early warning module is used to integrate patient information, perform data analysis, and generate health warnings. If abnormal vital signs are detected (such as low blood pressure or abnormal body temperature), the system will automatically generate an early warning notification to remind nursing staff to intervene in time and transmit the early warning notification to the nursing task allocation module;

[0085] Data analysis based on integrated patient information generates health alerts, enabling monitoring of patient health and timely identification of potential anomalies or danger signals. By comprehensively analyzing multi-source data, the system can predict and warn of patient health risks in advance, enabling healthcare professionals to intervene at an early stage, reducing the risk of sudden illnesses and improving the quality and safety of patient care. This early warning mechanism not only improves diagnosis and treatment efficiency but also optimizes resource allocation and reduces the damage caused by emergencies.

[0086] The Nursing Task Assignment module integrates patient information, designs personalized nursing tasks, and assigns them to relevant caregivers. The system dynamically adjusts nursing plans based on factors such as the patient's recovery and medication use, ensuring each patient receives the most appropriate care.

[0087] By designing personalized nursing tasks based on integrated patient information and assigning them to relevant caregivers, each patient receives tailored care. By comprehensively analyzing the patient's health status, treatment needs, and postoperative recovery progress, the system can develop the most appropriate care plan for each patient, thereby improving care efficiency and quality. Furthermore, by intelligently assigning tasks to caregivers with the appropriate skills and experience, it effectively avoids waste of nursing resources, optimizes human resource allocation, reduces the workload of caregivers, and improves the overall responsiveness of nursing services and patient satisfaction.

[0088] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0089] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A neurosurgery nursing management system based on cloud computing, characterized in that: The system comprises: The data acquisition and monitoring module is used to monitor and collect initial multi-source data. The multi-source data includes vital signs data, postoperative medication records, nursing observation records, and postoperative imaging data. Each data item includes a data ID, timestamp, data version number, and data source. Each data item consists of several fields. The initial multi-source data is then transmitted to the data synchronization module. A data synchronization module is used to synchronize the initial multi-source data to obtain synchronized multi-source data, and transmit the synchronized multi-source data to the data conflict processing module; A data conflict processing module is used to process data conflicts on the synchronized multi-source data, obtain actual multi-source data, store the actual multi-source data in a database, and transmit the actual multi-source data to the patient data integration module; The patient data integration module is used to integrate the actual multi-source data to obtain patient integrated information, and transmit the patient integrated information to the early warning module and the nursing task allocation module; The early warning module is used to integrate patient information, perform data analysis, and generate health warnings; The nursing task assignment module is used to integrate patient information, design personalized nursing tasks, and assign tasks to relevant nursing staff.

2. A neurosurgery nursing management system based on cloud computing according to claim 1, characterized in that: The steps of monitoring and collecting initial multi-source data are as follows: Collect vital signs data and postoperative medication records in real time, and use the real-time collected vital signs data and postoperative medication records as initial multi-source data; Set the initial update time interval, dynamically adjust the initial update time interval to obtain the actual update time interval, collect nursing observation records and postoperative imaging data according to the actual time interval, and use the nursing observation records and postoperative imaging data collected each time as the initial multi-source data; If vital signs data, postoperative medication records, nursing observation records, and postoperative imaging data are collected at the same time, the collected vital signs data, postoperative medication records, nursing observation records, and postoperative imaging data are used as initial multi-source data.

3. A neurosurgery nursing management system based on cloud computing according to claim 2, characterized in that: The actual update time interval acquisition step is: Set a monitoring time period, obtain the number of changes in vital sign data and the number of changes in postoperative medication records within the monitoring period, and evaluate the degree of data change based on the number of changes in vital sign data and the number of changes in postoperative medication records; Obtain system load data in real time, including CPU usage, memory usage, and disk I / O load. Evaluate the system load level based on the system load data. Obtain network broadband speed in real time, normalize the data change degree, system load degree, and network broadband speed, and evaluate the time adjustment coefficient based on the normalized data change degree, system load degree, and network broadband speed. The specific acquisition steps are as follows: ； Where, Expressed as the time adjustment coefficient, Expressed as the degree of data change, Indicates the degree of system load, Expressed as network broadband speed; Set a time adjustment threshold, and calculate the ratio of the time adjustment threshold to the time adjustment coefficient to obtain the time adjustment factor; The actual update time interval is calculated by multiplying the time adjustment factor by the initial update time interval.

4. The neurosurgery nursing management system based on cloud computing according to claim 1, characterized in that: The steps of synchronizing the initial multi-source data to obtain synchronized multi-source data are as follows: Filter the database based on the data ID, data version number, and data source of the initial multi-source data. If there is no corresponding data ID, data version number, and data source, it is determined that the initial multi-source data is stored for the first time and the initial multi-source data is used as the synchronized multi-source data. If there are corresponding data IDs, data version numbers, and data sources, obtain the timestamp of the initial multi-source data and record it as the new timestamp. Obtain the timestamp of the data that corresponds to the data ID, data version number, and data source and record it as the old timestamp. Compare the new timestamp with the old timestamp. If the new timestamp is greater than the old timestamp, the initial multi-source data is used as the synchronized multi-source data. If the new timestamp is less than or equal to the old timestamp, the initial multi-source data is discarded and the data corresponding to the old timestamp is used as the synchronized multi-source data.

5. The cloud computing-based neurosurgery nursing management system according to claim 1, characterized in that: The steps of processing data conflicts on synchronized multi-source data to obtain actual multi-source data are as follows: Perform data conflict identification on the synchronized multi-source data. If there is no conflicting data in the synchronized multi-source data, the synchronized multi-source data will be recorded as the actual multi-source data. If there is conflicting data in the synchronized multi-source data, the data consistency of the conflicting data is evaluated and compared with the consistency threshold. If the data consistency is greater than or equal to the consistency threshold, the conflicting data is judged to have high consistency. The conflicting data is averaged and the average calculation result is used as the final data of the conflicting data. The final data is merged with the remaining synchronized multi-source data to obtain the actual multi-source data. If the data consistency is less than the consistency threshold, the conflicting data is judged to have low consistency, the field information of each conflicting data is obtained, and the data integrity coefficient is calculated based on the field information; Obtain historical data of the data items corresponding to the conflicting data, and calculate the data trend reliability coefficient based on the historical data; The data integrity coefficient and the data trend reliability coefficient are normalized, and the data reliability index is obtained based on the normalized data integrity coefficient and the data trend reliability coefficient. The specific acquisition steps are as follows: ； Where, Expressed as the data reliability index, Expressed as the data integrity coefficient, Expressed as the data trend reliability coefficient, 、 Expressed as the weight coefficient of the data integrity coefficient and the weight coefficient of the data trend reliability coefficient; The data reliability index of all conflicting data is obtained, and the data with the largest data reliability index is selected as the final data of the conflicting data. The final data is merged with the remaining synchronized multi-source data to obtain the actual multi-source data.

6. The cloud computing-based neurosurgery nursing management system according to claim 5, characterized in that: The steps of identifying data conflicts for synchronized multi-source data are as follows: If there are identical data items from different data sources in the synchronized multi-source data, a data conflict check is performed on the identical data items from different data sources. The data conflict check includes a data consistency check, a data format consistency check, and a unit consistency check. If there is an inconsistency in the data conflict check, it is identified that conflicting data exists in the synchronized multi-source data.

7. The cloud computing-based neurosurgery nursing management system according to claim 5, characterized in that: The steps for evaluating the data consistency of conflicting data are: Obtain the optimal value of each conflicting data value and the corresponding data item of the conflicting data, and use the root mean square error to calculate the data consistency based on the absolute difference value of each conflicting data value. The specific acquisition steps are as follows: ； Where, It is expressed as data consistency, n is the number of conflicting data, It is represented as the value of the i-th conflicting data, and D is the optimal value of the data item corresponding to the conflicting data.

8. The cloud computing-based neurosurgery nursing management system according to claim 5, characterized in that: The steps for obtaining the data integrity coefficient are: Get the field information of the conflicting data, including the total number of fields, the number of missing fields, and the valid value range of each field; Calculate the ratio of the number of missing fields to the total number of fields to obtain the missing field ratio; Filter out the fields that are not in the valid value range and record them as invalid fields. Ratio the number of invalid fields to the total number of fields to get the invalid field ratio. The data integrity coefficient was obtained by evaluating the proportion of missing fields and the proportion of invalid fields.

9. The neurosurgery nursing management system based on cloud computing according to claim 5, characterized in that: The steps for obtaining the data trend reliability coefficient are: During the monitoring period, historical data of the data items corresponding to the conflicting data are obtained from the database; A trend model is obtained by fitting historical data through regression analysis, and the data of the current timestamp is predicted by the trend model, which is recorded as the historical trend prediction value; Calculate the absolute difference between each conflict data and the historical trend forecast value, record it as the residual, and calculate the data trend reliability coefficient based on the residual. The specific steps to obtain it are: ； Where, Expressed as the data trend reliability coefficient, Expressed as residual.

10. The neurosurgery nursing management system based on cloud computing according to claim 1, characterized in that: The steps of integrating actual multi-source data to obtain integrated patient information are as follows: Standardize actual multi-source data; Data association based on data ID; Each multi-source data is time-serialized according to the timestamp to obtain a dynamic change curve, and the dynamic change curve of the multi-source data is presented in a visual way to obtain patient integrated information.

Images