Postoperative nursing information management method for neurosurgery department

Abstract

The invention provides a neurosurgery postoperative nursing information management method. The method comprises the steps that physiological data and nursing operation data of a patient are collected and recorded; processing abnormal values and missing values in the data, standardizing the data and dividing the data into an analysis set and a verification set; training an optimized nursing information management system by using the analysis set, wherein the system adopts an improved intelligent optimization algorithm to adjust parameters of a basic nursing information management model; and inputting the verification set into the trained system to realize effective management. According to the invention, efficient and accurate management of postoperative nursing information can be realized, the nursing work efficiency and quality are improved, and the postoperative recovery effect of a patient is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information management, and more specifically, the present invention relates to a method for managing postoperative nursing information in neurosurgery. Background Art

[0002] In the field of postoperative nursing in neurosurgery, patients need to undergo strict physiological monitoring and nursing operations after surgery to ensure the smooth progress of their recovery process. Traditional nursing information management mainly relies on manual records and paper documents. This method has problems such as untimely data recording, difficult information sharing, and difficulty in ensuring data accuracy. With the development of information technology, some electronic nursing information management systems have emerged, but these systems often have relatively simple functions, lack the ability to deeply process and analyze nursing information, and cannot meet the complex needs of postoperative nursing information management in neurosurgery. In addition, existing systems also have deficiencies in data security and privacy protection, and are prone to patient information leakage.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: insufficient data processing ability, unable to effectively process outliers and missing values; low system intelligence, unable to automatically optimize parameters according to actual situations; lack of effective data security and privacy protection measures. Summary of the Invention

[0004] The present invention provides a method for managing postoperative nursing information in neurosurgery, which uses an optimized nursing information management system to achieve efficient management of postoperative nursing information in neurosurgery. The specific steps are as follows:

[0005] Step 1: Collect and record the nursing-related data of patients after neurosurgery, where the nursing-related data includes patient physiological data and nursing operation data;

[0006] Step 2: Process the outliers and missing values in the nursing-related data, and standardize the nursing-related data into a unified format; divide the processed nursing-related data into an analysis set and a validation set;

[0007] Step 3: Use the analysis set to train the optimized nursing information management system. The optimized nursing information management system uses an improved intelligent optimization algorithm to adjust and optimize the parameters of the basic nursing information management model. The parameters include the number of data processing units H, the system operation cycle L, the initial response speed M, and the data accuracy coefficient N. The improved intelligent optimization algorithm sets a data sensitivity factor and an information stability adjustment factor to improve the update frequency;

[0008] Step 4: Input the validation set of the nursing-related data of neurosurgical postoperative patients into the optimized nursing information management system that has been trained to achieve effective management of neurosurgical postoperative nursing information.

[0009] Further, in the said Step 1, the physiological data of the patient includes the patient's postoperative body temperature, blood pressure, and brain nerve function indicators, and the nursing operation data includes the dressing change operation records, rehabilitation training duration records, and pain management measure implementation records carried out by the nursing staff on the patient; the method of collection and recording is to combine and record the patient's physiological data and nursing operation data.

[0010] Further, in the said Step 2, the method of discovering the outlier is: for the i-th data point x of the nursing-related data i , calculate the difference degree between x i and the statistical characteristics of the overall nursing-related data, and calculate the outlier degree A of x i according to the difference degree. The calculation formula of the outlier degree is: i

[0011]

[0012] i i

[0013] p miss,i

[0014]

[0015] i i p miss,i i

[0016]

[0017] ​​​​​​​​​​​​​​​

[0018]

[0019] Among them, f min and f max are respectively the minimum and maximum values of the update frequency, and γ is a parameter for adjusting the steepness of the curve;

[0020] The calculation formula for the data sensitivity factor S is:

[0021]

[0022] Among them, and are respectively the data processing speed values of the i-th individual at the t-th and (t - 1)-th iterations, is the average data processing speed value of the individuals at the t-th iteration;

[0023] The calculation formula for the information stability adjustment factor I is:

[0024]

[0025] Among them, Q is the number of individuals, is the information processing accuracy value of the i-th individual at the t-th iteration, is the mean value of the information processing accuracy of the individuals at the t-th iteration, is the standard deviation of the information processing accuracy of the individuals at the t-th iteration.

[0026] Furthermore, the steps of adjusting and optimizing the parameters of the basic nursing information management model by using the improved intelligent optimization algorithm include:

[0027] S31. Encode the number H of data processing units, the system operation cycle L, the initial response speed M, and the data accuracy coefficient N of the basic nursing information management model into the spatial vector X = (H, L, M, N). The spatial vector X establishes a position mapping with the individual positions of the improved intelligent optimization algorithm, and the problem dimension of the improved intelligent optimization algorithm is 4;

[0028] S32. Initialize the parameters of the improved intelligent optimization algorithm, including the maximum number of iterations T max , the number of individuals Q, the problem dimension, the upper bound ub and the lower bound lb of the search space, the feedback threshold α, the minimum value f min and the maximum value f max ;

[0029] S33. Randomly initialize the positions of the individuals of the improved intelligent optimization algorithm If the individual position exceeds the boundary [lb, ub], then set the individual position on the boundary;

[0030] S34. If the current iteration number t reaches the maximum iteration number T max , output the individual position corresponding to the global minimum fitness value, and parse it into a spatial vector of the number H of data processing units, the system operation cycle L, the initial response speed M, and the data accuracy coefficient N, as the optimal parameters of the basic nursing information management model; otherwise, execute step S35;

[0031] S35. Calculate the updated frequency f value after the current iteration improvement and the cumulative iteration number Δt of the current iteration number t since the last update. If Δt is greater than , then calculate the feedback result feedback value; otherwise, execute step S37; The calculation formula for the feedback result is:

[0032]

[0033] where std(·) is the standard deviation function, and F (t) is the set of fitness values of the individuals in the t-th iteration;

[0034] S36. If the feedback result feedback is greater than the balance threshold α, perform the local optimization stage of the improved intelligent optimization algorithm to update the new position of the individual; otherwise, perform the global search stage of the improved intelligent optimization algorithm to update the new position of the individual; The calculation formula for the new position of the individual is:

[0035]

[0036] where is the new position of the individual of the improved intelligent optimization algorithm, is the best individual position of the improved intelligent optimization algorithm, and Chaos(·) is the chaos function;

[0037] S37. Calculate the position fitness value of the individual of the improved intelligent optimization algorithm after the current iteration improvement, and record the minimum fitness value in the individuals of the t-th iteration as and compare it with the minimum fitness value in the individuals of the (t - 1)-th iteration, and take the smaller of the two fitness values as the current best fitness value; The calculation formula for the objective function MAE is:

[0038]

[0039] where y j is the true value of the nursing information of the j-th neurosurgical postoperative patient, is the predicted value of the nursing information of the j-th neurosurgical postoperative patient, and s is the number of data related to the nursing of neurosurgical postoperative patients;

[0040] S38. Increase the current iteration number t by 1, and return to step S34.

[0041] Furthermore, the collection and recording in the first step further includes automatically collecting the patient's physiological data through medical devices and the nursing staff's real-time input of nursing operation data to ensure the timeliness and accuracy of the data.

[0042] Furthermore, the standardization process in the second step further includes unit conversion and range normalization of the patient's physiological data, and format unification and coding processing of the nursing operation data for subsequent analysis and management.

[0043] Furthermore, the optimized nursing information management system in the third step further includes data encryption and access control functions to ensure the security and privacy of the patient's nursing information.

[0044] Furthermore, the fourth step further includes visual display of the managed nursing information so that medical staff can quickly understand the patient's postoperative nursing status and adjust the nursing plan in a timely manner according to the display results.

[0045] According to the above embodiments of the present invention, it has at least the following beneficial effects: The method for managing neurosurgical postoperative nursing information of the present invention can efficiently collect and record the patient's physiological data and nursing operation data. Through standardization processing and the processing of outliers and missing values, the accuracy and integrity of the data are ensured. Using the improved intelligent optimization algorithm to adjust and optimize the parameters of the basic nursing information management model can improve the operation efficiency of the system and the accuracy of data processing, thereby realizing the effective management of neurosurgical postoperative nursing information. In addition, this method can also ensure the security and privacy of the patient's nursing information through data encryption and access control functions, preventing information leakage. At the same time, the visual display of the managed nursing information can facilitate medical staff to quickly understand the patient's postoperative nursing status, adjust the nursing plan in a timely manner, improve the nursing quality and the postoperative recovery effect of the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, wherein:

[0047] Figure 1 It is a schematic flowchart of the method for managing neurosurgical postoperative nursing information provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and do not limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to be able to convey the scope of the present invention fully to those skilled in the art.

[0049] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, equipment, method, or computer program product. Therefore, the present invention can be specifically implemented in the following forms: completely hardware, completely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0050] It should be noted that the number of any element in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0051] The following refers to Figure 1 , Figure 1 which is a schematic flowchart of a method for managing neurosurgical postoperative care information provided for an embodiment of the present invention. As Figure 1 shown, a method 100 for managing neurosurgical postoperative care information includes:

[0052] Utilize an optimized nursing information management system to achieve efficient management of neurosurgical postoperative care information. The specific steps are as follows:

[0053] Step 1: Collect and record the care-related data of neurosurgical postoperative patients. The care-related data includes patient physiological data and nursing operation data;

[0054] Step 2: Process the outliers and missing values in the care-related data, and standardize the care-related data into a unified format; divide the processed care-related data into an analysis set and a validation set;

[0055] Step 3: Use the analysis set to train the optimized nursing information management system. The optimized nursing information management system adjusts and optimizes the parameters of the basic nursing information management model by using an improved intelligent optimization algorithm. The parameters include the number of data processing units H, the system operation cycle L, the initial response speed M, and the data accuracy coefficient N. The improved intelligent optimization algorithm sets a data sensitivity factor and an information stability adjustment factor to improve the update frequency;

[0056] Step 4: Input the validation set of the care-related data of neurosurgical postoperative patients into the trained optimized nursing information management system to achieve effective management of neurosurgical postoperative care information.

[0057] First, the present invention proposes a method for managing neurosurgical postoperative care information. The core of this method lies in using an optimized nursing information management system to achieve efficient management of neurosurgical postoperative care information. Here, the optimized nursing information management system refers to a software system that has been specially designed and optimized and can process and analyze a large amount of postoperative care data. The specific steps include collecting and recording the nursing-related data of neurosurgical postoperative patients. These data cover the physiological indicators of patients and nursing operation records, such as physiological data like postoperative body temperature and blood pressure, as well as nursing operation data such as dressing changes and rehabilitation training. The collection and recording of these data are the basis for subsequent data processing and system optimization.

[0058] Specifically, the nursing-related data collected and recorded not only include the physiological data of patients, such as body temperature, blood pressure, and brain nerve function indicators, but also the nursing operation data of nursing staff on patients, such as dressing change operation records, rehabilitation training duration records, and pain management measure implementation records. The collection method of these data can be to combine and record the patient's physiological data and nursing operation data to ensure the integrity and accuracy of the information. When processing the data, it is necessary to identify and process the outliers and missing values in the data and standardize the data into a unified format. For example, for the identification of outliers, it can be determined by calculating the difference degree between the data points and the statistical characteristics of the overall data. If the difference degree exceeds a certain threshold, it is determined as an outlier. For missing values, it can be determined by cluster analysis and calculating the missing probability. If the missing probability is higher than the set value, it is determined as a missing value.

[0059] Preferably, during the implementation process, automated medical devices can be used to collect the physiological data of patients to improve the efficiency and accuracy of data collection. At the same time, nursing staff can enter the nursing operation data in real time through a dedicated input interface to ensure the timely update of the data. In the data processing stage, the processing methods for outliers and missing values can be further refined. For example, for outliers, in addition to calculating the difference degree, clinical experience and expert knowledge can be combined for comprehensive judgment; for missing values, interpolation methods or prediction methods based on data of similar patients can be used to fill in the missing values. In addition, in terms of system optimization, the performance of the optimization algorithm can be adjusted by setting different parameters, such as the number of data processing units and the system operation cycle, to adapt to different nursing scenarios and requirements.

[0060] In some embodiments, in step one, the patient's physiological data includes the patient's postoperative body temperature, blood pressure, and brain nerve function indicators, and the nursing operation data includes the dressing change operation records, rehabilitation training duration records, and pain management measure implementation records of the nursing staff on the patient; the collection and recording method is to combine and record the patient's physiological data and nursing operation data.

[0061] It should be noted that the patient's physiological data and nursing operation data mentioned in the present invention are important components of the postoperative nursing information management in neurosurgery. The patient's physiological data mainly includes postoperative body temperature, blood pressure, and brain nerve function indicators, etc. These data can reflect the patient's physiological state and recovery situation after surgery. The nursing operation data includes records of dressing change operations, rehabilitation training duration records, and pain management measure implementation records carried out by nursing staff on patients, etc. These data record the nursing behaviors and measures of nursing staff on patients. Combining and recording these data can provide comprehensive information support for subsequent data analysis and nursing decision-making.

[0062] Specifically, the collection of the patient's physiological data can be automatically carried out through medical devices. For example, devices such as thermometers and sphygmomanometers are used to regularly monitor the patient's body temperature and blood pressure, and the data is automatically transmitted to the nursing information management system. The measurement of brain nerve function indicators may require professional medical devices and professionals for evaluation, such as obtaining through means like neuroimaging examinations and nerve function tests. The recording of nursing operation data requires nursing staff to enter relevant information in real time through an electronic recording system when performing nursing operations, such as the time, frequency, and operation details of dressing change, the duration and content of rehabilitation training, and the specific implementation situation of pain management measures, etc. The recording of these data needs to follow certain formats and standards to facilitate subsequent data processing and analysis.

[0063] Preferably, in the process of data collection and recording, a combination of multiple data collection methods can be adopted to improve the accuracy and integrity of the data. For example, in addition to the automatically collected physiological data, some data that cannot be automatically collected by devices can be supplemented through the observation and evaluation of nursing staff, such as the patient's subjective feelings and behavioral manifestations, etc. In addition, in order to ensure the real-time and consistency of the data, the time interval and frequency of data collection and recording can be set, such as automatically collecting physiological data every certain period of time, and requiring nursing staff to enter relevant records in a timely manner after performing nursing operations. In terms of data recording, technical means such as electronic signatures and time stamps can also be adopted to ensure the authenticity and traceability of the data.

[0064] In some embodiments, in step two, the method for finding the outlier is: for the i-th data point x of the nursing-related data i , calculate the difference degree between x i and the statistical characteristics of the overall nursing-related data, and calculate the outlier degree A i of x i . The calculation formula for the outlier degree is:

[0065]

[0066] Among them, μ is the mean of the overall nursing-related data, and σ is the standard deviation of the overall nursing-related data; if the abnormality degree A i is greater than 2, then it is determined that x i is an outlier.

[0067] It should be noted that the outlier detection method mentioned in the present invention is based on statistical principles to identify outlier data points in nursing-related data. Here, the abnormality degree is an index to measure the deviation degree of a data point from the overall data set, and its calculation formula is

[0068]

[0069] Among them, x i represents the i-th data point, μ is the mean of the data set, and σ is the standard deviation of the data set. This method determines whether a data point is an outlier by calculating the difference degree of the statistical characteristics between each data point and the overall data set. If the abnormality degree is greater than 2, then the data point is considered an outlier, because according to the properties of the normal distribution, approximately 95% of the data points will fall within the range of the mean plus or minus 2 times the standard deviation.

[0070] Specifically, the detection of outliers involves the statistical analysis of the nursing-related data set. In practical applications, first, a certain amount of nursing-related data needs to be collected, and then the mean and standard deviation of these data are calculated. The mean μ is the average of all data points, and the standard deviation σ reflects the degree of dispersion of the data points. For each data point x i , calculate the absolute value of the difference between it and the mean, and then divide by the standard deviation to obtain the abnormality degree of this data point. This process can be automatically implemented in data processing software or systems to quickly identify possible outlier data points. The identification of outliers is crucial for data quality control because outliers may mislead subsequent data analysis and model training.

[0071] Preferably, when implementing outlier detection, the detection process can be further refined. For example, in addition to using the above-mentioned abnormality degree calculation method, the business background and clinical significance of the data can also be combined to set different outlier determination thresholds. For some key physiological indicators, such as blood pressure or brain nerve function indicators, more strict outlier determination criteria may be required because the abnormality of these indicators may have a significant impact on the patient's health status. In addition, for the detected outliers, different processing strategies can be adopted, such as data correction, deletion, or further investigation and verification. In terms of data correction, the data of adjacent time points or the data of patients of the same type can be referred to for reasonable estimation and adjustment. At the same time, in order to improve the accuracy and reliability of outlier detection, the detection algorithm and threshold can be evaluated and optimized regularly to adapt to the changes in data and new clinical needs.

[0072] In some embodiments, in the second step, the method for finding the missing value is as follows: perform a clustering analysis on the nursing-related data set, divide it into P clusters, and the p-th cluster C p contains a set of nursing-related data points, and calculate the missing probability P miss,i of the i-th data point of the nursing-related data. The calculation formula for the missing probability is:

[0073]

[0074] where count(x i ) is the number of data points of the same category as x i in the p-th cluster, and n p is the total number of data points in the p-th cluster; if the missing probability P miss,i is higher than 0.7, then it is determined that x i is a missing value.

[0075] It should be noted that the missing value detection method mentioned in the present invention is based on clustering analysis to identify the missing data points in the nursing-related data. Here, the missing probability refers to the possibility that a certain data point is missing in a specific cluster, and its calculation formula is

[0076]

[0077] where N same,i is the number of data points of the same category as the data point x i in the i-th cluster, and N cluster,i is the total number of data points in the i-th cluster. If the missing probability is higher than 0.7, then it is determined that the data point is a missing value. This method divides the data set into different clusters through clustering analysis and calculates the missing probability of each data point in the cluster, so as to identify the possible missing data points.

[0078] Specifically, the detection of missing values involves the clustering analysis of the nursing-related data set. In practical applications, first, a certain amount of nursing-related data needs to be collected, and then the data set is divided into several clusters using a clustering algorithm. The clustering algorithm can be common algorithms such as K-means and hierarchical clustering, and the number of clusters can be determined according to the characteristics and requirements of the data. For each data point in the cluster, calculate its similarity with other data points in the cluster and count the number of data points of the same category. Then, according to the calculation formula of the missing probability, calculate the missing probability of each data point. This process can be automatically implemented in data processing software or systems to quickly identify the possible missing data points. The identification of missing values is crucial for the integrity and accuracy of the data, because missing values may affect the results of subsequent data analysis and model training.

[0079] Preferably, when performing missing value detection, the detection process can be further refined. For example, in addition to using the above-mentioned missing probability calculation method, different missing value determination thresholds can also be set in combination with the business background and clinical significance of the data. For some key nursing operation data, such as dressing change operation records or rehabilitation training duration records, stricter missing value determination criteria may be required because the absence of these data may have a significant impact on the nursing quality and recovery effect of patients.

[0080] Furthermore, for the detected missing values, different processing strategies can be adopted, such as data interpolation, deletion, or further investigation and verification. In terms of data interpolation, linear interpolation, polynomial interpolation, or prediction methods based on similar patient data can be used for reasonable estimation and filling. At the same time, to improve the accuracy and reliability of missing value detection, the detection algorithm and threshold can be evaluated and optimized regularly to adapt to data changes and new clinical needs.

[0081] In some embodiments, in the improved intelligent optimization algorithm, the improved method for the update frequency f is as follows:

[0082] Set the data sensitivity factor S and the information stability adjustment factor I, and the calculation formula for the update frequency is:

[0083]

[0084] where f min and f max are respectively the minimum and maximum values of the update frequency, and γ is a parameter for adjusting the steepness of the curve;

[0085] The calculation formula for the data sensitivity factor S is:

[0086]

[0087] where and are respectively the data processing speed values of individual i at the t-th and t - 1-th iterations, is the average data processing speed value of individuals at the t-th iteration;

[0088] The calculation formula for the information stability adjustment factor I is:

[0089]

[0090] where Q is the number of individuals, is the information processing accuracy value of the i-th individual at the t-th iteration, is the mean value of the information processing accuracy of individuals at the t-th iteration, is the standard deviation of the information processing accuracy of individuals at the t-th iteration.

[0091] It should be noted that the improved intelligent optimization algorithm mentioned in the present invention is used to adjust and optimize the parameters of the basic nursing information management model to improve the performance and adaptability of the system. The data sensitivity factor here is used to measure the impact of data processing speed on the update frequency, and its calculation formula is

[0092]

[0093] where and are the data processing speed values of individual i in the i-th and (i - 1)-th iterations respectively, and is the average data processing speed value of the individual in the t-th iteration. The information stability adjustment factor is used to measure the impact of information processing accuracy on the update frequency, and its calculation formula is

[0094]

[0095] where n is the number of individuals, is the information processing accuracy value of the i-th individual in the t-th iteration, is the mean value of the information processing accuracy of the individual in the t-th iteration, and is the standard deviation of the information processing accuracy of the individual in the t-th iteration. By setting these two factors, the update frequency can be dynamically adjusted to adapt to different data processing requirements and information stability requirements.

[0096] Specifically, when implementing the improved intelligent optimization algorithm, it is first necessary to determine the minimum and maximum values of the update frequency, as well as the parameter for adjusting the steepness of the adjustment curve. The minimum and maximum values of the update frequency can be set according to the actual operation of the system and data processing requirements. For example, the minimum value can be set to update once per second, and the maximum value can be set to update once per minute. The parameter for adjusting the steepness of the adjustment curve can be adjusted according to the response speed and stability requirements of the system.

[0097] More specifically, in each iteration process, calculate the data processing speed and information processing accuracy of the current iteration individual, and then calculate the data sensitivity factor and information stability adjustment factor according to the above formulas. Then, according to the values of these two factors, dynamically adjust the update frequency to optimize the performance and adaptability of the system. For example, when the data sensitivity factor is large, it indicates that the data processing speed is fast, and the update frequency can be appropriately increased; while when the information stability adjustment factor is large, it indicates that the information processing accuracy is low, and the update frequency can be appropriately reduced to improve the stability of the system.

[0098] Preferably, when implementing the improved intelligent optimization algorithm, the parameter settings and update strategies of the algorithm can be further refined and optimized. For example, according to the actual operating conditions of the system and the data processing requirements, the minimum and maximum values of the update frequency, as well as the parameters for adjusting the curve steepness, can be dynamically adjusted to adapt to different operating environments and data characteristics. In addition, other optimization algorithms and strategies, such as genetic algorithms and particle swarm optimization, can be combined to further improve the optimization effect and performance of the system.

[0099] Furthermore, in terms of the update strategy, an adaptive update strategy can be adopted to automatically adjust the update frequency and optimization parameters according to the real-time performance of the system and data characteristics, so as to achieve the optimal operating state of the system. At the same time, to improve the stability and reliability of the algorithm, the algorithm can be evaluated and optimized regularly to adapt to data changes and new system requirements.

[0100] In some embodiments, the steps of adjusting and optimizing the parameters of the basic nursing information management model by using the improved intelligent optimization algorithm include:

[0101] S31. Encode the number of data processing units H, the system operation cycle L, the initial response speed M, and the data accuracy coefficient N of the basic nursing information management model into the spatial vector X = (H, L, M, N). The spatial vector X establishes a position mapping with the individual positions of the improved intelligent optimization algorithm, and the problem dimension of the improved intelligent optimization algorithm is 4;

[0102] S32. Initialize the parameters of the improved intelligent optimization algorithm, including the maximum number of iterations T max , the number of individuals Q, the problem dimension, the upper bound ub of the search space and the lower bound lb of the search space, the feedback threshold α, the minimum value f of the update frequency min and the maximum value f max ;

[0103] S33. Randomly initialize the positions of the individuals of the improved intelligent optimization algorithm If the individual position exceeds the boundary [lb, ub], then set the individual position on the boundary;

[0104] S34. If the current iteration number t reaches the maximum number of iterations T max , then output the individual position corresponding to the global minimum fitness value and parse it into the spatial vector of the number of data processing units H, the system operation cycle L, the initial response speed M, and the data accuracy coefficient N as the best parameters of the basic nursing information management model; otherwise, execute step S35;

[0105] S35. Calculate the updated frequency f value after the current iteration improvement and the cumulative iteration number Δt of the current iteration number t since the last update. If Δt is greater than Then calculate the feedback result feedback value; otherwise, execute step S37; the calculation formula for the feedback result is:

[0106]

[0107] where std(·) is the standard deviation function, and F (t) is the set of fitness values of the individual at the t-th iteration;

[0108] S36. If the feedback result feedback is greater than the balance threshold α, then perform the local optimization stage of the improved intelligent optimization algorithm to update the new position of the individual; otherwise, perform the global search stage of the improved intelligent optimization algorithm to update the new position of the individual; the calculation formula for the new position of the individual is:

[0109]

[0110] where, is the new position of the individual of the improved intelligent optimization algorithm, is the best individual position of the improved intelligent optimization algorithm, and Chaos(·) is the chaos function;

[0111] S37. Calculate the position fitness value of the individual of the improved intelligent optimization algorithm at the current iteration using the objective function, and record the minimum fitness value among the individuals at the t-th iteration as and compare it with the minimum fitness value among the individuals at the (t - 1)-th iteration, and take the smaller of the two fitness values as the current best fitness value; the calculation formula for the objective function MAE is:

[0112]

[0113] where y j is the true value of the nursing information of the j-th neurosurgical postoperative patient, is the predicted value of the nursing information of the j-th neurosurgical postoperative patient, and s is the number of data related to the nursing of neurosurgical postoperative patients;

[0114] S38. Increase the current iteration number t by 1, and return to step S34.

[0115] It should be noted that in the present invention, the process of adjusting and optimizing the parameters of the basic nursing information management model by using an improved intelligent optimization algorithm involves encoding the model parameters into a spatial vector and establishing a mapping relationship between the vector and the individual position of the algorithm. Here, the spatial vector refers to a vector containing multiple parameters, which is used to represent the configuration state of the model. The specific parameters include the number of data processing units, the system operation cycle, the initial response speed, and the data accuracy coefficient. These parameters jointly determine the performance and efficiency of the model. The improved intelligent optimization algorithm adjusts these parameters to make the model better adapt to the needs of neurosurgical postoperative nursing information management.

[0116] Specifically, when implementing the improved intelligent optimization algorithm, first, the parameters of the basic nursing information management model need to be encoded to form a four-dimensional spatial vector X = (x 1 , x 2 , x 3 , x 4 ), where x 1 represents the number of data processing units, x 2 represents the system operation cycle, x 3 represents the initial response speed, and x 4 represents the data accuracy coefficient. The specific settings of these parameters can be determined according to the actual system requirements and data characteristics. For example, the number of data processing units can be set according to the processing capacity and data volume of the system, the system operation cycle can be adjusted according to the frequency and urgency of nursing operations, the initial response speed can be set according to the user's expectation of the system response time, and the data accuracy coefficient can be determined according to the quality requirements of the data. When initializing the algorithm parameters, the maximum number of iterations, the number of individuals, the upper and lower bounds of the search space, etc. need to be set. The settings of these parameters will affect the search efficiency and optimization effect of the algorithm.

[0117] Preferably, when implementing the improved intelligent optimization algorithm, the parameter settings and optimization process can be further refined. For example, for the number of data processing units, its value can be dynamically adjusted according to the actual load and data processing requirements of the system to achieve the optimal allocation of resources. The system operation cycle can be flexibly set in combination with the time arrangement of nursing operations and the specific situation of patients to ensure that the system can respond in a timely manner at critical moments. The initial response speed can be improved by optimizing the system architecture and algorithm to reduce unnecessary calculations and waiting times and enhance the user experience. The data accuracy coefficient can ensure the accuracy and reliability of the data by introducing a data verification mechanism and a feedback adjustment strategy. In the optimization process, a combination of multiple optimization strategies, such as the combination of global search and local optimization, can be adopted to improve the search ability and convergence speed of the algorithm. In addition, the algorithm parameters and strategies can be dynamically adjusted according to the real-time performance feedback of the system to adapt to the changing operating environment and data characteristics.

[0118] In some embodiments, the collection and recording in the first step further includes automatically collecting the physiological data of the patient by medical devices and the nursing staff entering the nursing operation data in real time to ensure the timeliness and accuracy of the data.

[0119] It should be noted that the collection and recording of the nursing-related data of the neurosurgical postoperative patients mentioned in the present invention not only includes the physiological data of the patient automatically collected by medical devices, but also covers the nursing operation data entered in real time by the nursing staff. This data collection method ensures the timeliness and accuracy of the data and provides a reliable basis for subsequent data processing and analysis. The physiological data of the patient refers to the data of various physical indicators of the patient monitored by medical devices, such as body temperature, blood pressure, etc.; the nursing operation data is the data recorded by the nursing staff during the nursing operation of the patient, such as the detailed information of operations such as dressing change and rehabilitation training.

[0120] Specifically, the automatic collection of the physiological data of the patient by medical devices means using various medical monitoring devices, such as electronic thermometers, sphygmomanometers, electrocardiogram monitors, etc., to monitor the physiological indicators of the patient in real time and automatically transmit these data to the nursing information management system. These devices usually have data interfaces and can be seamlessly docked with the hospital's information system. The nursing staff entering the nursing operation data in real time means that when the nursing staff performs the nursing operation, they timely record information such as the time, content, and result of the operation through a mobile terminal or the electronic recording system of the nursing workstation. The entry of these data needs to follow certain formats and standards to ensure the consistency and analyzability of the data. For example, the dressing change operation record should include the time of dressing change, the drugs used, the wound condition after dressing change, etc.; the rehabilitation training record should include the start and end times of the training, the training content, the patient's reaction, etc.

[0121] Preferably, during the data collection process, the data collection process and standards can be further refined. For example, for the physiological data collected by medical devices, the data collection frequency and accuracy requirements can be set to ensure that the data can accurately reflect the physiological state of the patient. For the nursing operation data, a standardized entry template can be developed to guide the nursing staff to enter the data in accordance with the specified format and reduce human errors.

[0122] Furthermore, a data quality monitoring mechanism can be introduced to perform real-time verification and auditing on the collected data, and promptly discover and correct the anomalies or errors in the data. At the same time, to improve the security and privacy of the data, the collected data can be encrypted and access permissions can be set, and only authorized medical staff can view and use these data.

[0123] In some embodiments, the standardization process in the second step further includes unit conversion and range normalization of the patient's physiological data, and format unification and coding processing of the nursing operation data, so as to facilitate subsequent analysis and management.

[0124] It should be noted that the standardization process mentioned in the present invention is to preprocess the collected patient physiological data and nursing operation data to facilitate subsequent analysis and management. Here, unit conversion refers to converting data in different units into a unified unit. For example, converting body temperature from Fahrenheit to Celsius; range normalization refers to scaling the data to a specific range, such as between 0 and 1, for easy comparison and analysis. For nursing operation data, format unification means organizing the data into a consistent format, and coding processing is to convert non-numerical data into numerical data for computer processing.

[0125] Specifically, unit conversion and range normalization are common steps in data preprocessing. For example, for the patient's blood pressure data, if the original unit of the data is millimeters of mercury (mmHg) and the unit required by the system is kilopascals (kPa), unit conversion is needed. Range normalization can be achieved through linear transformation. For example, if the original range of the data is [a, b] and the target range is [0, 1], the formula

[0126]

[0127] can be used for normalization. For nursing operation data, format unification may include unifying the date and time format into the ISO standard format, and coding processing may involve converting text-described nursing operations (such as dressing change, rehabilitation training) into numerical codes (such as 1, 2).

[0128] Preferably, when implementing the standardization process, these steps can be further refined and optimized. For example, for unit conversion, an automated conversion tool can be developed to automatically select the appropriate conversion formula according to the metadata of the data (such as unit information). In terms of range normalization, the distribution characteristics of the data can be considered, and an appropriate normalization method can be selected, such as Z-score standardization or Min-Max standardization. For the coding processing of nursing operation data, a detailed coding dictionary can be established to ensure that each nursing operation has a unique numerical code and these codes are consistent in the system. In addition, a data cleaning step can be introduced to remove duplicate data and correct incorrect data to further improve the data quality.

[0129] In some embodiments, the optimized nursing information management system in the third step further includes data encryption and access control functions to ensure the security and privacy of patient care information.

[0130] It should be noted that the optimized nursing information management system mentioned in the present invention has data encryption and access control functions, aiming to ensure the security and privacy of patient care information. Data encryption refers to converting data into a format that cannot be understood by unauthorized users through an encryption algorithm, and only users with the correct key can decrypt and access the data. Access control refers to restricting access rights to data to ensure that only authorized users and systems can access the data under specific conditions.

[0131] Specifically, symmetric encryption algorithms such as the Advanced Encryption Standard (AES) can be used for data encryption, or asymmetric encryption algorithms such as RSA can also be used. Symmetric encryption algorithms use the same key for encryption and decryption, while asymmetric encryption algorithms use a pair of keys, namely a public key and a private key. In this system, the patient care information stored in the database can be encrypted to ensure the security of the data during storage and transmission. Access control can be achieved by setting user roles and permissions. For example, doctors, nurses, and administrators can have different access rights and can only access the corresponding data when specific conditions (such as authentication and authorization) are met.

[0132] Preferably, when implementing the data encryption and access control functions, these security measures can be further refined and optimized. For example, for data encryption, a hybrid encryption mechanism can be adopted, combining the advantages of symmetric encryption and asymmetric encryption to improve encryption efficiency and security. In terms of access control, a fine-grained access control policy can be introduced to precisely control access rights to data according to the responsibilities and operation requirements of users.

[0133] Furthermore, the security performance of the system can be regularly evaluated and audited to promptly discover and fix security vulnerabilities. At the same time, in order to respond to security incidents such as data leakage, an emergency response mechanism can be established to ensure that measures can be quickly taken in the event of a security incident to reduce losses.

[0134] In some embodiments, step four further includes visually displaying the managed nursing information so that medical staff can quickly understand the patient's postoperative care status and adjust the care plan in a timely manner according to the display results.

[0135] It should be noted that the visual display of the managed nursing information mentioned in the present invention aims to enable medical staff to quickly and intuitively understand the patient's postoperative care status, so as to adjust the care plan in a timely manner. Visual display refers to presenting complex data information in an intuitive manner through forms such as graphs and charts, which is convenient for users to understand and analyze. In the management of neurosurgical postoperative nursing information, visual display can help medical staff quickly grasp the overall care situation of patients, identify potential problems, and make corresponding nursing decisions.

[0136] Specifically, the visual display can include various chart types, such as line charts, bar charts, pie charts, etc. For example, a line chart can be used to display the changing trends of physiological indicators such as the patient's body temperature and blood pressure after surgery, a bar chart can be used to display the execution frequencies of different nursing operations, and a pie chart can be used to display the distribution of the patient's pain management measures, etc. When setting the visual parameters, it is necessary to select the appropriate chart type and style according to the characteristics of the data and the display purpose. For example, for time series data, a line chart can be selected to display its changing trend over time; for categorical data, a bar chart or a pie chart can be selected to display the distribution of different categories. In addition, the title, axis labels, legend, etc. of the chart can also be set to enhance the readability and information transmission effect of the chart.

[0137] Preferably, when implementing the visual display, the display content and form can be further refined and optimized. For example, an interactive visual display can be implemented, allowing users to view detailed data or switch different display views through operations such as clicking and dragging. In addition, according to the needs and preferences of medical staff, personalized visual display solutions can be provided, such as allowing users to customize the display content, chart style, etc. To improve the real-time performance and accuracy of the visual display, the processes of data collection, processing, and display can be integrated to ensure that the displayed information can timely reflect the actual nursing status of the patient. At the same time, intelligent analysis functions can be introduced to further analyze and interpret the displayed data, providing more comprehensive and in-depth decision-making support for medical staff.

[0138] The above-mentioned various embodiments of the present invention have the following beneficial effects: First, by collecting and recording the patient's physiological data and nursing operation data, the comprehensiveness and real-time nature of the information can be ensured, providing a solid foundation for subsequent analysis and management. Processing the outliers and missing values in the data and standardizing the data into a unified format can improve the quality and consistency of the data, thereby enhancing the reliability and accuracy of the nursing information management system. Second, using the analysis set to train the optimized nursing information management system and adopting an improved intelligent optimization algorithm to adjust and optimize the parameters of the basic nursing information management model can improve the performance and adaptability of the system, enabling it to better meet the complex needs of postoperative nursing in neurosurgery. Inputting the validation set into the trained system can achieve the effective management of nursing information, ensuring the practicality and effectiveness of the system.

[0139] In addition, automatically collecting patients' physiological data through medical devices and having nursing staff enter nursing operation data in real time can further improve the timeliness and accuracy of the data and reduce human errors. Performing unit conversion and range normalization on patients' physiological data and unifying the format and encoding processing of nursing operation data can facilitate subsequent analysis and management and improve work efficiency. Adding data encryption and access control functions can ensure the security and privacy of patients' nursing information and prevent information leakage. Finally, visually displaying the managed nursing information can facilitate medical staff to quickly understand the postoperative nursing status of patients, timely adjust the nursing plan, and improve the nursing quality and the postoperative recovery effect of patients.

[0140] Furthermore, the storage medium of the embodiment of the present application stores program instructions capable of implementing all the above methods. Among them, the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0141] The above description is only some preferred embodiments of the present invention and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, technical solutions formed by mutually replacing the above features with (but not limited to) technical features having similar functions disclosed in the embodiments of the present invention.

Claims

1. A neurosurgery postoperative nursing information management method, characterized in that: The optimized nursing information management system is used to achieve efficient management of postoperative nursing information in neurosurgery. The specific steps are as follows: Step 1: Collect and record nursing-related data of patients after neurosurgery surgery, wherein the nursing-related data includes patient physiological data and nursing operation data; Step 2: Processing abnormal values ​​and missing values ​​in the nursing-related data, and standardizing the nursing-related data into a unified format; dividing the processed nursing-related data into an analysis set and a validation set; Step 3: using the analysis set to train an optimized nursing information management system, wherein the optimized nursing information management system uses an improved intelligent optimization algorithm to adjust and optimize the parameters of the basic nursing information management model, wherein the parameters include the number of data processing units H, the system operation cycle L, the initial response speed M, and the data accuracy coefficient N, and the improved intelligent optimization algorithm sets a data sensitivity factor and an information stability adjustment factor to improve the update frequency; Step 4: Input the verification set of nursing-related data of neurosurgery postoperative patients into the trained optimized nursing information management system to achieve effective management of neurosurgery postoperative nursing information.

2. The neurosurgery postoperative care information management method according to claim 1, characterized in that: In step one, the patient's physiological data includes the patient's postoperative body temperature, blood pressure and brain nerve function indicators, and the nursing operation data includes the nursing staff's dressing change operation records, rehabilitation training duration records and pain management measures implementation records for the patient; the collection and recording method is to combine the patient's physiological data and nursing operation data.

3. The neurosurgery postoperative care information management method according to claim 2, characterized in that: In the step 2, the method for finding the abnormal value is: for the i-th data point x of the nursing-related data i , calculate x i The statistical characteristic difference of the nursing-related data as a whole, and calculate x based on the difference i The abnormality of A i , the calculation formula of the abnormality is: Among them, μ is the mean of the nursing-related data as a whole, σ is the standard deviation of the nursing-related data as a whole; if the abnormality A i If x is greater than 2, then i is an outlier.

4. The neurosurgery postoperative care information management method according to claim 3, characterized in that: In step 2, the method for finding the missing value is: cluster analysis is performed on the nursing-related data set, and the data is divided into P clusters, and the pth cluster C p Contains a set of nursing-related data points, and calculates the missing probability P of the i-th data point of nursing-related data miss,i , the missing probability is calculated as follows: Among them, count(x i ) is the pth cluster with x i The number of data points of the same category, n p is the total number of data points in the pth cluster; if the missing probability P miss,i If it is higher than 0.7, then x i is a missing value.

5. The neurosurgery postoperative care information management method according to claim 1, characterized in that: In the improved intelligent optimization algorithm, the method for improving the update frequency f is: Set the data sensitivity factor S and the information stability adjustment factor I, and the calculation formula for the update frequency is: Among them, f min and f max are the minimum and maximum values ​​of the update frequency, respectively, and γ is the parameter for adjusting the steepness of the curve; The calculation formula of data sensitivity factor S is: in, and are the data processing speed values ​​of individual i at the t-th and t-1-th iterations, respectively. is the average data processing speed of the individual in the tth iteration; The calculation formula of information stability adjustment factor I is: Where Q is the number of individuals, is the accuracy value of the i-th individual information processing in the t-th iteration, is the mean of the individual information processing accuracy at the tth iteration, is the standard deviation of the individual information processing accuracy at the tth iteration.

6. The neurosurgery postoperative care information management method according to claim 1, characterized in that: The step of adjusting and optimizing the parameters of the basic nursing information management model using the improved intelligent optimization algorithm includes: S31, encoding the number of data processing units H, the system operation cycle L, the initial response speed M and the data accuracy coefficient N of the basic nursing information management model into a space vector X=(H, L, M, N), wherein the space vector X is mapped to the individual position of the improved intelligent optimization algorithm, and the problem dimension of the improved intelligent optimization algorithm is 4; S32, initialize the parameters of the improved intelligent optimization algorithm, including the maximum number of iterations T max , number of individuals Q, problem dimension, upper bound ub and lower bound lb of search space, feedback threshold α, minimum update frequency f min and the maximum value f max ; S33, Randomly initialize the improved intelligent optimization algorithm individual position X i (0) , if the individual position exceeds the boundary [lb,ub], then the individual position is set on the boundary; S34, if the current number of iterations t reaches the maximum number of iterations T max , then the individual position corresponding to the global minimum fitness value is output and parsed into the spatial vector of the number of data processing units H, the system operation cycle L, the initial response speed M and the data accuracy coefficient N as the optimal parameters of the basic nursing information management model; otherwise, step S35 is executed; S35, calculate the updated frequency f value after the current iteration and the cumulative number of iterations Δt since the last update of the current iteration number t, if Δt is greater than Then calculate the feedback result feedback value; otherwise, execute step S37; the calculation formula of the feedback result is: Among them, std(·) is the standard deviation function, F (t) is the fitness value set of individuals in the tth iteration; S36. If the feedback result feedback is greater than the equilibrium threshold α, the local optimization phase of the improved intelligent optimization algorithm is performed to update the new position of the individual; otherwise, the global search phase of the improved intelligent optimization algorithm is performed to update the new position of the individual; the calculation formula for the new position of the individual is: in, Individual new positions for improved intelligent optimization algorithms, is the best individual position of the improved intelligent optimization algorithm, Chaos(·) is the chaotic function; S37, using the objective function to calculate the position fitness value of the individual of the intelligent optimization algorithm improved in the current iteration, and record the minimum fitness value of the individual in the t-th iteration as And compare it with the minimum fitness value of the individual in the t-1th iteration, and take the smaller fitness value of the two as the current optimal fitness value; the calculation formula of the objective function MAE is: Among them, y j is the true value of the nursing information of the jth neurosurgery postoperative patient, is the predicted value of the jth neurosurgery postoperative patient care information, and s is the number of neurosurgery postoperative patient care related data; S38. Increase the current number of iterations t by 1, and return to step S34.

7. The neurosurgery postoperative care information management method according to claim 1, characterized in that: The collection and recording in step 1 also includes automatically collecting the patient's physiological data through medical equipment, and the nursing staff entering the nursing operation data in real time to ensure the real-time and accuracy of the data.

8. The neurosurgery postoperative care information management method according to claim 1, characterized in that: The standardization process in step 2 also includes unit conversion and range normalization of the patient's physiological data, and format unification and coding of the nursing operation data to facilitate subsequent analysis and management.

9. The neurosurgery postoperative care information management method according to claim 1, characterized in that: The optimized nursing information management system in step three also includes data encryption and access control functions to ensure the security and privacy of patient nursing information.

10. The neurosurgery postoperative care information management method according to claim 1, characterized in that: The step four also includes visually displaying the managed nursing information so that medical staff can quickly understand the patient's postoperative nursing status and adjust the nursing plan in time according to the display results.

Images