Clinical nursing system for interventional operation

Abstract

The invention relates to the technical field of clinical nursing, in particular to a clinical nursing system for interventional operations, which can accurately identify and predict potential complications by performing deep neural network analysis in combination with preoperative medical history, intraoperative real-time physiological data and operation types. It is ensured that a nursing scheme can be finely adjusted based on individual differences of patients, complex physiological data can be processed through a deep neural network, key physiological data are recognized from the complex physiological data, the scheme is dynamically adjusted in the nursing process through a long-short-term memory network, and the nursing accuracy is improved. The change trend of data in the operation is deeply mined, the fluctuation of physiological indexes is tracked, the abnormity is timely identified, the potential risk is predicted, the nursing decision and the physiological state of the patient can be synchronously updated, the working efficiency of nursing personnel is optimized, and the postoperative recovery effect and comfort of the patient are improved.

Description

Technical Field

[0001] The present invention relates to the field of clinical nursing technology, and particularly to a clinical nursing system for interventional surgery. Background Art

[0002] The field of clinical nursing technology aims to improve the treatment effect of patients, ensure patient safety, and optimize the use of nursing resources. It involves aspects such as patient health monitoring, formulation and implementation of nursing plans, management and optimization of the nursing process, improvement of patient comfort, and enhancement of the work efficiency of nursing staff, promoting the rapid recovery of patients and reducing medical errors.

[0003] The purpose of a clinical nursing system for interventional surgery is to optimize the nursing service during interventional surgery by integrating information technology and nursing processes, ensure the safety and comfort of patients during the surgery, and aims to achieve functions such as real-time monitoring, data collection, nursing plan management, and patient information integration, assisting clinical nursing staff to make timely and accurate nursing decisions, improving the nursing work efficiency, and enhancing the surgical safety and recovery effect of patients.

[0004] In the prior art, during the implementation of clinical nursing, there is a lack of real-time in-depth analysis and dynamic adjustment of the physiological state of patients during surgery. The nursing process is fixed and it is difficult to make effective personalized adjustments according to individual differences of patients. The real-time data during surgery is not fully utilized for accurate judgment, resulting in the nursing plan lagging behind the changes in the patient's state, and the physiological indicators are not tracked and adjusted in real time during the nursing process, affecting the recovery effect of patients, and making it so that clinical nursing staff can only intervene after complications occur, missing the best intervention opportunity. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose a clinical nursing system for interventional surgery.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: A clinical nursing system for interventional surgery includes: Complication risk prediction module: Based on the real-time physiological data of the patient during the surgery, preoperative medical history, and surgical type, using a deep neural network, conduct comparison and analysis of physiological data, identify the key physiological data that may trigger complications, evaluate the complication risk, and determine the potential complication type, generating a complication risk prediction result; Personalized nursing plan formulation module: Based on the complication risk prediction result and historical case data, combined with physiological data, evaluate the individual differences of patients, select suitable nursing content, and generate a personalized nursing plan; Nursing plan real-time adjustment module: Based on the personalized nursing plan, continuously monitor the changes in physiological data, analyze drug reactions and sign fluctuations, judge whether the personalized nursing plan needs to be adjusted according to the real-time physiological data, and generate a dynamic nursing adjustment plan; Physiological data time series analysis module: Obtain intraoperative physiological data in real time, perform time series analysis, track the change trend of patients' physiological indicators, analyze abnormal fluctuations, predict potential risks, and generate the results of the time series change of physiological data; Nursing execution decision-making module: Based on the results of the time series change of physiological data and the dynamic nursing adjustment plan, use a long short-term memory network, combine with the patient's physiological state, select an appropriate nursing strategy, and generate a nursing execution decision-making plan.

[0007] As a further solution of the present invention, the complication risk prediction module includes: Data comparison sub-module: Based on the real-time physiological data of the patient during the operation, preoperative medical history and surgical type, compare the physiological data of the patient, use a deep neural network, collect indicators such as blood pressure, heart rate and blood oxygen concentration, analyze the deviation between the current value and the historical value, evaluate the changes in various physiological data, and generate the results of the comparison of physiological data; Risk assessment sub-module: Based on the results of the comparison of physiological data, evaluate whether the patient's blood pressure and heart rate indicators exceed the safe range during the operation, analyze the change range of various risk indicators, combine with the risk factors in the patient's historical medical record, calculate the complication risk score, and generate the results of the complication risk assessment; Complication judgment sub-module: Based on the results of the complication risk assessment, combine with the patient's medical history and the real-time physiological data obtained during the monitored operation, analyze the risk factors associated with related complications, judge the type of complications that the patient has, and generate the results of the complication risk prediction.

[0008] As a further solution of the present invention, the deep neural network adopts the formula:

[0009] Where: Is the total deviation value, Is the real-time data of the th item of physiological data at the current moment, Is the value of the corresponding th item of physiological data in the historical data, Is the average physiological data based on the same patient group, Is the physiological data threshold obtained through the evaluation of medical experts, Is the target physiological data value, 、 、 、 Are the weight coefficients of each item of data, The total number of physiological data involved in the comparison.

[0010] As a further solution of the present invention, the personalized care plan formulation module includes: Patient difference assessment sub-module: Based on the complication risk prediction result and historical case data, extract the patient's age, weight, and past medical history information, analyze the impact of various physiological data and historical factors on the nursing needs, evaluate individual differences, and generate an individual difference assessment result; Nursing content selection sub-module: Based on the individual difference assessment result, combine the patient's physiological data, and compare it with the expected intraoperative physiological change range, evaluate the patient's recovery situation, select nursing measures suitable for the patient, and generate a nursing content selection result; Nursing plan generation sub-module: Based on the nursing content selection result, integrate the patient's individual differences and suitable nursing content, formulate a detailed nursing plan, and specify specific nursing steps to generate a personalized nursing plan; The specific nursing steps include vital sign monitoring, wound care, nutritional management, activity guidance and functional training, pain management, psychological and emotional counseling, complication prevention and monitoring, respiratory function training, drug management, discharge preparation, and follow-up nursing plan.

[0011] As a further solution of the present invention, the nursing plan real-time adjustment module includes: Physiological data monitoring sub-module: Based on the personalized nursing plan, continuously collect the current patient's physiological data, and real-time monitor the changes in physiological data. At the same time, compare the historical records to generate a physiological data monitoring result; Nursing response analysis sub-module: Based on the physiological data monitoring result, use support vector machines to automatically analyze the changes in the patient's physiological data, identify the laws of drug reactions and sign fluctuations, construct a time series analysis model, real-time detect the change trend of the patient's physiological data, and combine the set threshold to judge the possibility of drug side effects and complication signs, and generate a nursing response analysis result; Nursing plan adjustment sub-module: Based on the nursing response analysis result, combine the real-time physiological data changes, match nursing measures according to the patient's health status, and generate a dynamic nursing adjustment plan.

[0012] As a further solution of the present invention, the physiological data time series analysis module includes: Data collection sub-module: Real-time obtain intraoperative physiological data, organize it into time series data in chronological order, and generate a physiological data collection result; Data Trend Analysis Sub-module: Based on the physiological data collection results, through time series analysis methods, identify the evolution patterns of each physiological data in the time dimension, analyze the long-term change trends of different physiological indicators, mine potential periodic changes and abnormal patterns, and predict the future direction of physiological changes to generate physiological data trend analysis results; Risk Prediction Sub-module: Based on the physiological data trend analysis results, analyze and identify abnormal fluctuations in physiological data, determine whether there are potential risk factors, predict the physiological abnormalities and complications of patients, and generate physiological data time series change results.

[0013] As a further solution of the present invention, the nursing execution decision-making module includes: Data Analysis Sub-module: Based on the physiological data time series change results and dynamic nursing adjustment plans, collect the current physiological data of patients, use long short-term memory networks for classification and sorting of each physiological data, calculate the change ratios of each physiological data, identify the fluctuation ranges of each physiological data, and generate data analysis results; Nursing Plan Comparison Sub-module: Based on the data analysis results, compare the effects of different nursing plans under the same physiological conditions, conduct simulation evaluations of each plan, analyze the impacts of each plan on patients' physiological indicators, and generate nursing plan comparison results; Nursing Decision Generation Sub-module: Based on the nursing plan comparison results, combined with the individual needs and physiological responses of patients, select appropriate nursing measures to generate nursing execution decision-making plans.

[0014] As a further solution of the present invention, the long short-term memory network adopts the formula:

[0015] Where: is the weighted relative change rate of the th item of physiological data, is the value of the th item of physiological data at the current moment, is the value of the th item of physiological data at the previous moment, is the population average value of the th item of physiological data, is the medical threshold of the th item of physiological data, is the weight coefficient of physiological data at the current moment, is the weight coefficient of physiological data at the historical moment, is the weight coefficient of the population average value, is the weight coefficient of the medical threshold, is the normalized weight coefficient of historical data.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are as follows: 1. In the present invention, through the in-depth neural network analysis by combining the preoperative medical history, intraoperative real-time physiological data and the type of surgery, it is possible to accurately identify and predict potential complications, ensuring that the nursing plan can be refined and adjusted based on the individual differences of patients; 2. In the present invention, through the deep neural network, it is possible to process complex physiological data, identify key physiological data from it, evaluate the risk of complications, making the real-time data comparison and analysis more accurate and efficient, ensuring the timely assessment and effective management of risks during the operation; 3. In the present invention, through the long short-term memory network, the plan is dynamically adjusted during the nursing process, deeply mining the changing trend of intraoperative data, tracking the fluctuations of physiological indicators, timely identifying abnormalities and predicting potential risks, ensuring that the nursing decision can be updated synchronously with the physiological state of the patient, optimizing the work efficiency of nursing staff, and improving the postoperative recovery effect and comfort of the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is the system flow chart of the present invention; Figure 2 is the schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0019] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, in the description of the present invention, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0020] Please refer to Figure 1 , the present invention provides a technical solution: a clinical nursing system for interventional surgery includes: Complication risk prediction module: Based on the real-time physiological data of the patient during the operation, the preoperative medical history, and the type of surgery, a deep neural network is used to perform comparative analysis of the physiological data, identify the key physiological data that may trigger complications, evaluate the complication risk, and determine the potential complication type, generating a complication risk prediction result; Personalized nursing plan formulation module: Based on the complication risk prediction result and historical case data, combined with physiological data, evaluate the individual differences of the patient, select the appropriate nursing content, and generate a personalized nursing plan; Nursing plan real-time adjustment module: Based on the personalized nursing plan, continuously monitor the changes in physiological data, analyze the drug reactions and sign fluctuations, and determine whether the personalized nursing plan needs to be adjusted according to the real-time physiological data, generating a dynamic nursing adjustment plan; Physiological data time series analysis module: Real-time obtain the intraoperative physiological data, perform time series analysis, track the change trend of the patient's physiological indicators, analyze the abnormal fluctuations, predict the potential risks, and generate the physiological data time series change result; Nursing execution decision-making module: Based on the physiological data time series change result and the dynamic nursing adjustment plan, use a long short-term memory network, combined with the patient's physiological state, select the appropriate nursing strategy, and generate a nursing execution decision-making plan.

[0021] Please refer to Figure 2 , the complication risk prediction module includes: Data comparison sub-module: Based on the real-time physiological data of the patient during the operation, the preoperative medical history, and the type of surgery, perform a comparison of the patient's physiological data. Use a deep neural network to collect indicators such as blood pressure, heart rate, and blood oxygen concentration, analyze the deviation between the current value and the historical value, evaluate the changes in each physiological data, and generate a physiological data comparison result; Risk assessment sub-module: Based on the physiological data comparison result, evaluate whether the patient's blood pressure and heart rate indicators exceed the safe range during the operation, analyze the change range of each risk indicator, and combine the risk factors in the patient's historical medical record to calculate the complication risk score and generate a complication risk assessment result; Complication judgment sub-module: Based on the complication risk assessment result, combined with the patient's medical history and the real-time physiological data obtained during the operation, analyze the risk factors associated with the relevant complications, judge the type of complications that the patient may have, and generate a complication risk prediction result; Data comparison sub-module: Based on the real-time physiological data of the patient during the operation, the preoperative medical history, and the type of operation, compare the physiological data of the patient. Use a deep neural network with 3 hidden layers, with 512, 256, and 128 neurons in each layer. Use the ReLU function as the activation function. Input the blood pressure, heart rate, and blood oxygen concentration indicators. Through the backpropagation algorithm, use the gradient descent method with a learning rate of 0.001 and a momentum of 0.9. Compare the deviation between the current value and the historical value, calculate the error using the mean square error, optimize the parameters, evaluate the changes in various physiological data, and generate the physiological data comparison result; Risk assessment sub-module: Based on the results of the surgical physiological data comparison, evaluate whether the patient's blood pressure and heart rate indicators exceed the safe range during the operation, analyze the change range of various risk indicators, and combine the risk factors in the patient's historical medical records to calculate the complication risk score. Use the linear regression algorithm, solve the parameters by the least squares method, use the patient's blood pressure and heart rate data as independent variables, set the risk score of complication occurrence as the dependent variable, fit the patient's data, analyze whether it exceeds the set blood pressure and heart rate thresholds, and generate the complication risk assessment result; Complication judgment sub-module: Based on the results of the surgical complication risk assessment, combine the patient's medical history and the real-time physiological monitoring data during the operation, analyze the risk factors associated with relevant complications, use the K-nearest neighbor algorithm, set the K value to 5, calculate the similarity using the Euclidean distance, select the simple weighted average method for classification, classify the patient's risk factors, calculate the similarity between each patient and the known cases, judge the type of complication that the patient may have, and generate the complication risk prediction result.

[0022] Please refer to Figure 2 , the deep neural network, using the formula:

[0023] Where: is the total deviation value, is the real-time data of the th item of physiological data at the current moment, is the value of the corresponding th item of physiological data in the historical data, is the average physiological data based on the same patient group, is the physiological data threshold obtained through medical expert evaluation, is the target physiological data value, , , , are the weight coefficients of each item of data, is the total number of physiological data involved in the comparison; Execution process: First, collect the physiological data of the current patient and compare with historical data to calculate the deviation between the current physiological data and the historical data, and by comparing the current data with the average data based on the same patient group to evaluate the degree of deviation of the patient's physiological data. Next, compare the current data with the physiological data threshold evaluated by medical experts to ensure that the parameter values are within the normal range, and calculate the deviation between the current data and the target physiological data value to ensure that the patient's physiological state meets the expected goal. All deviation values are weighted and summed according to the corresponding weight coefficients , , , to obtain the total deviation value for evaluating whether there is an abnormality in the patient's current physiological state and providing clinical decision support.

[0024] Please refer to Figure 2 , the personalized care plan formulation module includes:[[]] Patient difference assessment sub-module: Based on the complication risk prediction results and historical case data, extract the patient's age, weight, and past medical history information, analyze the impact of various physiological data and historical factors on the nursing needs, evaluate individual differences, and generate individual difference assessment results; Nursing content selection sub-module: Based on the individual difference assessment results, combine the patient's physiological data, and compare with the expected intraoperative physiological change range to evaluate the patient's recovery situation, select the nursing measures suitable for the patient, and generate nursing content selection results; Nursing plan generation sub-module: Based on the nursing content selection results, integrate the patient's individual differences and the suitable nursing content, formulate a detailed nursing plan, and specify the specific nursing steps to generate a personalized nursing plan; The specific nursing steps include vital sign monitoring, wound care, nutrition management, activity guidance and functional training, pain management, psychological and emotional counseling, complication prevention and monitoring, respiratory function training, drug management, discharge preparation and follow-up nursing plan; Patient difference assessment sub-module: Based on the complication risk prediction results and historical case data, extract the patient's age, weight, and past medical history information, analyze the impact of various physiological and historical factors on the nursing needs, use the decision tree algorithm, specifically the CART algorithm, set the maximum depth of the tree to 10, the minimum sample split number to 2, the minimum number of samples in the leaf node to 1, divide by the Gini coefficient, and use the CART algorithm to implement and construct a decision tree model, and analyze the importance of each factor in predicting nursing needs, and at the same time evaluate individual differences to generate individual difference assessment results; Nursing content selection sub-module: Based on the individual difference assessment results and combined with the patient's physiological data, use the logistic regression algorithm to evaluate the patient's recovery situation, select nursing measures suitable for the patient. Adopt the logistic regression algorithm, set the regularization coefficient to 0.01, fit the patient's physiological data and recovery situation through maximum likelihood estimation, generate the selection probability of nursing measures, select appropriate nursing steps, and generate the nursing content selection result; Nursing plan generation sub-module: Based on the nursing content selection result, integrate the patient's individual differences and the adapted nursing content, formulate a detailed nursing plan, and specify specific nursing steps. Adopt the linear programming algorithm and use the Simplex method for optimization. Construct a variable set xi to represent whether the i-th nursing measure is selected, where xi is 0 or 1. The nursing resource constraints include that the daily executable nursing time does not exceed 480 minutes, the maximum working hours of a single nurse per day do not exceed 240 minutes, and the number of simultaneously implemented nursing measures does not exceed 3. The constraint expression form is Ax ≤ b, where A is the nursing resource occupancy matrix and b is the resource upper limit vector. The resource items include time, personnel, per capita load, and medication frequency. Each element aij in the matrix represents the occupancy of the i-th nursing measure on the j-th resource. During the linear programming solution process, continuously adjust the value of xi according to the resource limitations, select the combination of nursing measures that meets all the constraint conditions, and generate a personalized nursing plan.

[0025] Please refer to Figure 2 , the nursing plan real-time adjustment module includes: Physiological data monitoring sub-module: Based on the personalized nursing plan, continuously collect the current patient's physiological data, monitor the changes in physiological data in real time, and compare the historical records at the same time to generate the physiological data monitoring result; Nursing response analysis sub-module: Based on the physiological data monitoring result, use the support vector machine to automatically analyze the changes in the patient's physiological data, identify the laws of drug reactions and sign fluctuations, construct a time series analysis model, detect the change trend of the patient's physiological data in real time, and combine the set threshold to judge the possibility of drug side effects and complication signs to generate the nursing response analysis result; Nursing plan adjustment sub-module: Based on the nursing response analysis result, combined with the real-time changes in physiological data, match nursing measures according to the patient's health status to generate a dynamic nursing adjustment plan; Physiological data monitoring sub-module: Based on the personalized nursing plan, continuously collect the patient's physiological data, monitor the changes in the data in real time, and compare the historical records. Adopt the Kalman filtering algorithm, set the process noise covariance to 0.1 and the measurement noise covariance to 0.05, calculate the weighted average value of the real-time data through the Kalman gain, smooth the noise in the physiological data, and generate the physiological data monitoring result; Nursing response analysis sub-module: Based on the monitoring results of physiological data, analyze the patient's response to drugs and fluctuations in physical signs, judge whether there are signs of drug side effects and complications, adopt the support vector machine algorithm, set the kernel function as the radial basis function, the C value as 1, and the gamma value as 0.5. Use cross-validation (K = 5) to optimize the model parameters, classify the patient's physiological data through the support vector machine, and the categories include normal response category, side effect sign category, and complication risk category, and generate the nursing response analysis result; Nursing plan adjustment sub-module: Based on the nursing response analysis result, combined with the changes in real-time physiological data, select appropriate nursing measures, adopt the greedy algorithm, set the objective function as the minimization of nursing resources, and the constraint conditions as the change range of the patient's physiological indicators and the availability of nursing resources, select the optimal nursing measures, and generate a dynamic nursing adjustment plan.

[0026] Please refer to Figure 2 , the physiological data time series analysis module includes: Data collection sub-module: Obtain intraoperative physiological data in real time, organize it into time series data in chronological order, and generate the physiological data collection result; Data trend analysis sub-module: Based on the physiological data collection result, through time series analysis methods, identify the evolution pattern of each physiological data in the time dimension, analyze the long-term change trend of different physiological indicators, mine potential periodic changes and abnormal patterns, and predict the future direction of physiological changes, and generate the physiological data trend analysis result; Risk prediction sub-module: Based on the physiological data trend analysis result, analyze and identify abnormal fluctuations in physiological data, judge whether there are potential risk factors, predict the patient's physiological abnormalities and complications, and generate the physiological data time series change result; Data collection sub-module: Based on the physiological data collection result, organize it into time series data in chronological order, use SQL query, use the SELECT statement to select all intraoperative physiological data fields, limit the time range from the start of the operation to the end of the operation, and sort it in ascending order according to the timestamp field, and generate the physiological data collection result; Data trend analysis sub-module: Based on the physiological data collection result, perform time series analysis on each physiological data, identify the trend of each indicator changing with time, detect fluctuations in the data, judge whether there are abnormal changes, adopt the autoregressive moving average model, set the ARIMA(1, 1, 1) model, use the AIC criterion to optimize the model parameters, analyze the time series data of each physiological indicator, and generate the physiological data trend analysis result; Risk prediction sub-module: Based on the analysis results of physiological data trends, analyze and identify abnormal fluctuations in physiological data, determine whether there are potential risk factors, predict possible physiological changes in patients, adopt an anomaly detection algorithm, set the number of trees to 100 and the maximum depth to 10, calculate the anomaly score for each data point, and based on the anomaly score, if the score ≥ 0.65, it is judged as a potential risk, and consecutive high-risk scores are marked as abnormal periods, generating the time-series change results of physiological data.

[0027] Please refer to Figure 2 , and the nursing execution decision-making module includes: Data analysis sub-module: Based on the time-series change results of physiological data and the dynamic nursing adjustment plan, collect the patient's current physiological data, use a long short-term memory network to classify and organize various physiological data, calculate the change ratio of each physiological data, identify the fluctuation range of each physiological data, and generate the data analysis results; Nursing plan comparison sub-module: Based on the data analysis results, compare the effects of different nursing plans under the same physiological conditions, conduct a simulation evaluation of each plan, analyze the impact of each plan on the patient's physiological indicators, and generate the nursing plan comparison results; Nursing decision generation sub-module: Based on the nursing plan comparison results, combined with the patient's individual needs and physiological responses, select appropriate nursing measures to generate a nursing execution decision-making plan; Data analysis sub-module: Based on the time-series change results of physiological data and the dynamic nursing adjustment plan, collect the patient's current physiological data, use a long short-term memory network, set the input layer dimension to 100, the number of hidden layer units to 128, the learning rate to 0.001, use the Adam optimizer for training, classify and organize each data item, calculate the relative changes between different physiological data, perform normalization operations through time-series data processing, identify the fluctuation range of each data item, and generate the data analysis results; Nursing plan comparison sub-module: Based on the data analysis results, compare the effects of different nursing plans under the same physiological conditions, conduct a simulation evaluation of each plan, adopt the Monte Carlo simulation algorithm, set the number of simulations to 1000, simulate the execution effects of each nursing plan, model the influencing factors of each nursing plan using a normal distribution, and use the mean and standard deviation to evaluate the impact of each nursing plan on the patient's physiological indicators, generating the nursing plan comparison results; Nursing decision generation sub-module: Based on the nursing plan comparison results, combined with the patient's individual needs and physiological responses, select appropriate nursing measures, adopt a genetic algorithm, set the population size to 50, the number of iterations to 100, the crossover probability to 0.8, and the mutation probability to 0.1, evaluate the fitness of each nursing plan, and select the optimal nursing plan through the roulette wheel selection method to generate a nursing execution decision-making plan.

[0028] Please refer to Figure 2 , the long short-term memory network, which adopts the formula:

[0029] Where: is the weighted relative change rate of the th item of physiological data, is the value of the th item of physiological data at the current moment, is the value of the th item of physiological data at the previous moment, is the population average value of the th item of physiological data, is the medical threshold of the th item of physiological data, is the weight coefficient of the physiological data at the current moment, is the weight coefficient of the physiological data at the historical moment, is the weight coefficient of the population average value, is the weight coefficient of the medical threshold, is the normalized weight coefficient of the historical data; Execution process: First, collect the physiological data of the current patient , and at the same time obtain the physiological data at the previous moment , then use the population average value and the medical threshold to compare the differences between the patient's current data and the normal range of the same population and the medical standard, and assign weight coefficients , , , to control the influence degree of each data item. Then calculate the weighted differences of each data item, add the absolute values of the differences, and finally divide the result by the historical data and multiply by the normalized weight coefficient to obtain the weighted relative change rate , which can more accurately evaluate the change of the patient's physiological state and provide a basis for dynamic nursing adjustment for clinical nursing staff.

[0030] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical content of the technical solution of the present invention, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still belong to the protection scope of the technical solution of the present invention.

Claims

1. A clinical nursing system for interventional surgery, characterized in that: The system comprises: Complication risk prediction module: Based on the patient's real-time physiological data, preoperative medical history and surgical type during the operation, a deep neural network is used to compare and analyze physiological data, identify key physiological data that may cause complications, assess complication risks, determine potential complication types, and generate complication risk prediction results; Personalized nursing plan formulation module: Based on the complication risk prediction results and historical case data, combined with physiological data, evaluate individual differences of patients, select appropriate nursing content, and generate personalized nursing plans; Nursing plan real-time adjustment module: Based on the personalized nursing plan, continuously monitor the changes in physiological data, analyze drug reactions and physical sign fluctuations, determine whether the personalized nursing plan needs to be adjusted based on real-time physiological data, and generate a dynamic nursing adjustment plan; Physiological data time series analysis module: real-time acquisition of intraoperative physiological data, time series analysis, tracking of patient physiological index change trends, analysis of abnormal fluctuations, prediction of potential risks, and generation of physiological data time series change results; Nursing execution decision module: Based on the time series change results of the physiological data and the dynamic nursing adjustment plan, a long short-term memory network is used to select an adaptive nursing strategy in combination with the patient's physiological state to generate a nursing execution decision plan; The nursing execution decision module includes: Data analysis submodule: based on the physiological data time series change results and dynamic nursing adjustment plan, collect the patient's current physiological data, use long short-term memory network to classify and organize various physiological data, calculate the change ratio of various physiological data, identify the fluctuation range of various physiological data, and generate data analysis results; Nursing plan comparison submodule: based on the data analysis results, compare the effects of different nursing plans under the same physiological conditions, conduct simulation evaluation of each plan, analyze the impact of each plan on the patient's physiological indicators, and generate nursing plan comparison results; Nursing decision generation submodule: Based on the comparison results of the nursing plans, combined with the individual needs and physiological responses of the patient, appropriate nursing measures are selected to generate a nursing execution decision plan.

2. The clinical nursing system for interventional surgery according to claim 1, characterized in that: The complication risk prediction module includes: Data comparison submodule: Based on the patient's real-time physiological data during the operation, preoperative medical history and operation type, the patient's physiological data is compared. A deep neural network is used to collect blood pressure, heart rate and blood oxygen concentration indicators, analyze the deviation between the current value and the historical value, evaluate the changes in various physiological data, and generate physiological data comparison results; Risk assessment submodule: Based on the physiological data comparison results, evaluate whether the patient's blood pressure and heart rate indicators exceed the safe range during the operation, analyze the change range of various risk indicators, combine the risk factors in the patient's historical medical records, calculate the complication risk score, and generate complication risk assessment results; Complications judgment submodule: Based on the complication risk assessment results, combined with the patient's medical history and real-time physiological data obtained during the operation, analyze the risk factors associated with the relevant complications, judge the type of complications that occur in the patient, and generate complication risk prediction results.

3. The clinical nursing system for interventional surgery according to claim 2, characterized in that: The deep neural network adopts the formula: in: is the total deviation value, For the current moment Real-time data of physiological data, The corresponding The value of the physiological data, is the average physiological data based on the same patient population, is the physiological data threshold obtained through evaluation by medical experts. is the target physiological data value, , , , is the weight coefficient of each data, is the total number of physiological data involved in the comparison.

4. The clinical nursing system for interventional surgery according to claim 1, characterized in that: The personalized care program formulation module includes: Patient difference assessment submodule: Based on the complication risk prediction results and historical case data, extract the patient's age, weight and previous medical history information, analyze the impact of various physiological data and historical factors on nursing needs, evaluate individual differences, and generate individual difference assessment results; Nursing content selection submodule: Based on the individual difference assessment results, combined with the patient's physiological data, and compared with the expected physiological change range during the operation, the patient's recovery is evaluated, nursing measures suitable for the patient are selected, and nursing content selection results are generated; Nursing plan generation submodule: Based on the nursing content selection results, integrate the individual differences of patients and the adapted nursing content, formulate a detailed nursing plan, specify specific nursing steps, and generate a personalized nursing plan; The specific nursing steps include vital signs monitoring, wound care, nutritional management, activity guidance and functional training, pain management, psychological and emotional counseling, complication prevention and monitoring, respiratory function training, medication management, discharge preparation and follow-up care plan.

5. The clinical nursing system for interventional surgery according to claim 1, characterized in that: The nursing plan real-time adjustment module includes: Physiological data monitoring submodule: based on the personalized nursing plan, continuously collect the physiological data of the current patient, monitor the changes of the physiological data in real time, and compare the historical records to generate physiological data monitoring results; Nursing response analysis submodule: Based on the physiological data monitoring results, support vector machines are used to automatically analyze the changes in the patient's physiological data, identify the law of drug reaction and physical sign fluctuations, build a time series analysis model, detect the change trend of the patient's physiological data in real time, and judge the possibility of drug side effects and complication signs based on the set thresholds to generate nursing response analysis results; Nursing plan adjustment submodule: Based on the nursing response analysis results, combined with real-time physiological data changes, matching nursing measures according to the patient's health status, and generating a dynamic nursing adjustment plan.

6. The clinical nursing system for interventional surgery according to claim 1, characterized in that: The physiological data time series analysis module includes: Data collection submodule: acquire intraoperative physiological data in real time, organize it into time series data in chronological order, and generate physiological data collection results; Data trend analysis submodule: Based on the physiological data collection results, the time series analysis method is used to identify the evolution pattern of each physiological data in the time dimension, analyze the long-term change trend of different physiological indicators, explore potential periodic changes and abnormal patterns, and predict the future direction of physiological changes, and generate physiological data trend analysis results; Risk prediction submodule: Based on the physiological data trend analysis results, analyze and identify abnormal fluctuations in the physiological data, determine whether there are potential risk factors, predict the patient's physiological abnormalities and complications, and generate physiological data time series change results.

7. The clinical nursing system for interventional surgery according to claim 1, characterized in that: The long short-term memory network adopts the formula: in: For the The weighted relative change rate of each physiological data item, For the The value of the physiological data at the current moment, For the The value of the physiological data at the last moment, For the The group average of the physiological data, For the Medical thresholds for physiological data, is the weight coefficient of the physiological data at the current moment, is the weight coefficient of physiological data at historical moments, is the weight coefficient of the group average, is the weight coefficient of the medical threshold, is the normalized weight coefficient of historical data.

Images