Acute postoperative pain assessment and management decision-making system based on patient report result

Abstract

The invention relates to the technical field of medical data management, and particularly discloses an acute postoperative pain assessment and management decision-making system based on a patient report result, which is used for solving multiple challenges facing postoperative acute pain management, including subjectivity of a traditional assessment method, lack of personalized treatment, insufficient intervention coordination and lack of real-time monitoring ability. The problems that an existing decision support system is insufficient in intelligence and complex in user interaction experience, so that the efficiency of medical staff is low, and finally rehabilitation and life quality of a patient are affected are solved, and the system comprises a patient pain data collection module, a data analysis and processing module, a decision support module and a user interface. The data analysis processing module analyzes the collected data by adopting a machine learning algorithm so as to evaluate the severity of the pain; according to the invention, individualized pain assessment is realized through a machine learning algorithm, patient pain data is analyzed in real time, a management scheme is rapidly adjusted, patient satisfaction is improved, a pain management scheme is optimized, and manual intervention is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data management, and more specifically, to an acute postoperative pain assessment and management decision-making system based on patient-reported results. Background Art

[0002] Acute postoperative pain is a common challenge faced by surgical patients, which has a significant impact on the rehabilitation process and quality of life. Traditional pain assessment methods mostly rely on the subjective judgment of medical staff, and there are large differences in the assessment results, and they often cannot fully reflect the true feelings of patients. Since pain is a highly individual experience, the lack of personalized treatment plans and low patient participation have led to poor pain management results. Many existing technologies have failed to effectively integrate multimodal interventions, resulting in insufficient coordination of interventions, which in turn affects the patient's rehabilitation effect. At the same time, traditional data collection methods are often regular assessments, lack of real-time monitoring, and are difficult to adapt to the dynamic changes in the patient's condition. In addition, the existing decision support system has limitations in terms of intelligence and data integration capabilities, and cannot provide comprehensive and timely information support for medical staff. The user interaction experience of the decision support system is also relatively complex, making medical staff inefficient during use. These problems have jointly led to a decrease in the timeliness and effectiveness of pain management. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, the present invention provides an acute postoperative pain assessment and management decision-making system based on patient-reported results. Through an intelligent decision support algorithm, it provides personalized and scientific pain management suggestions for medical staff. By integrating modern information technology and data analysis methods, it aims to solve the main technical problems in the current management of acute postoperative pain, achieve precision medicine and optimize the patient's rehabilitation experience.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] An acute postoperative pain assessment and management decision system based on patient-reported results includes a patient pain data collection module, a data analysis and processing module, a decision support module and a user interface. The patient pain data collection module is connected to the data analysis and processing module, the data analysis and processing module is connected to the decision support module, and the user interface is connected to the patient pain data collection module, the data analysis and processing module and the decision support module. The data analysis and processing module uses a machine learning algorithm to analyze the collected data to assess the severity of pain. The pain severity score is the weighted sum of the total pain score, pain duration, pain intensity score and other influencing factors. The pain severity score formula is:

[0006] P=α·D+β·S+γ·A

[0007] Where: P is the pain severity score, D is the pain duration, S is the pain intensity score, A is other influencing factors, including but not limited to medication and psychological state, α, β, γ are weighting coefficients, which are set according to actual needs.

[0008] As a further solution of the present invention, the patient pain data collection module is based on a user-friendly mobile application, and is provided with a clear pain score slider and level selection. The pain intensity score is input through a slider or a selection box, and a text box is provided to allow the patient to describe the nature of the pain and select the time period when the pain starts. The patient is required to fill in the current medication status, including the name of the drug, dosage and medication time. The patient's anxiety or depression level and emotional state are collected through a multiple-choice scoring questionnaire. The completeness and rationality of the input are checked before the patient submits the information, prompts are given in time to guide the patient's input, the collected data is stored in real time in a secure cloud database, and the collected data is sent to the data analysis and processing module using a RESTful API.

[0009] As a further solution of the present invention, the data analysis and processing module receives data transmitted from the patient pain data collection module through a RESTful API, cleans the received data, removes duplicate, missing and unreasonable records, converts data from different sources into a unified format, extracts important features from the symptom description, including but not limited to pain type and triggering factors, uses statistical analysis methods to select features that have a greater impact on pain assessment, converts categorical variables into numerical variables, selects a machine learning algorithm suitable for a decision tree based on data characteristics and analysis objectives, trains the selected algorithm using historical data, optimizes model parameters, evaluates the performance of the model through cross-validation, inputs the newly received data into the trained model, evaluates the patient's pain level in real time, generates a total pain score, organizes the evaluation results into a report, regularly collects new data, retrains and updates the model, analyzes feedback from medical staff and patients on the evaluation results, adjusts model parameters and feature selection, sends the analysis results to the decision support module through an API interface, and stores the data and model outputs during the analysis process in a cloud database.

[0010] As a further solution of the present invention, the decision support module receives the evaluation results from the data analysis and processing module through the API interface, retrieves the patient's historical medical records, past pain management plans and treatment responses from the cloud database, obtains the patient's individual differences, integrates the evaluation results with the patient's individual difference results, applies an intelligent decision-making algorithm, generates a personalized pain management plan, analyzes the patient's current condition and historical records, identifies the patient's potential risks, establishes a rule-based early warning mechanism, monitors the patient's condition in real time, promptly prompts medical staff, and generates a decision report, regularly uses new mobile phone data and feedback, updates and optimizes the decision support algorithm, and maintains a knowledge base of clinical guidelines and best practices.

[0011] As a further solution of the present invention, the decision support module retrieves the patient's historical medical records, past pain management plans and treatment responses from the cloud database to obtain the individual differences of the patient. The algorithm implementation process includes:

[0012] Step 11, database training and query: Use the Alibaba Cloud database connection library to establish a connection to the cloud database, enter the patient's ID, and return the patient's name, age, and gender;

[0013] Step 12, search historical medical records: input the patient's ID, and output a list of the patient's medical records sorted by time, including but not limited to surgical records and drug prescriptions;

[0014] Step 13, retrieve past pain management plans: input patient ID, and output chronological pain management records, including but not limited to medication use, non-drug interventions, and pain scores;

[0015] Step 14, obtaining management response: inputting the patient ID to obtain the patient's pain management response, including but not limited to changes in pain scores, patient feedback content, and side effect records;

[0016] Step 15, data integration and feature extraction: merge the data obtained from steps 11 to 14 to generate a patient pain management history file, extract the patient's most recent pain score, repeatedly used medications, and patient satisfaction;

[0017] Step 16, individual difference analysis: Apply variance analysis to analyze the individual differences of patients in pain management, structure the integrated information and extracted features, and return them to the decision support module.

[0018] As a further scheme of the present invention, in step 16, the variance analysis method is used to calculate the variance, mean, between-group sum of squares, within-group sum of squares, total sum of squares, between-group mean square, and F statistic of each group of data of patients in pain management. The calculated F statistic is compared with the critical F value to determine whether there are significant differences between the groups. If there are significant differences, a post hoc test is performed to determine which groups have significant differences. The analysis results are structured to form an individual patient file, which includes the mean and standard deviation of each group, group pair information with significant differences, and the specific performance and feedback of individual patients in pain management.

[0019] As a further aspect of the present invention, in step 16, the method for performing the post hoc test uses the standardized value of the mean difference, and the formula is:

[0020]

[0021] Where: q is the standardized value of the mean difference of the patient, i and j are the indexes of the data group, n is the sample size of each group of data, are the means of the i-th group and the j-th group respectively, and MSW is the within-group mean square.

[0022] As a further solution of the present invention, the user interface reflects the effect of the patient's pain management through a comprehensive score of the pain management data based on the data obtained by the patient pain data collection module, the data analysis and processing module, and the decision support module. The formula for the comprehensive score of the pain management data is:

[0023]

[0024] Where: M is the comprehensive score of the patient's pain management data, k is the index of the pain data group currently being processed, m is the total number of data groups, P k is the pain score of group k, E k is the score of the kth group of influencing factors, μ is the preset pain score critical value, τ is the adjustment factor, which is set according to actual needs, and δ k is the weight coefficient, set according to actual needs, ε k ,θ k is the sensitivity impact index, which is set according to actual needs, T is the current patient's pain management time, R is the patient satisfaction score, ρ and σ are weight factors, which are set according to actual needs.

[0025] The technical effects and advantages of the acute postoperative pain assessment and management decision-making system based on patient-reported results of the present invention are as follows: the present invention utilizes a machine learning algorithm to analyze the patient's pain data to achieve individualized pain assessment, and can more accurately identify the pain characteristics and management needs of each patient. Through the real-time collection and analysis of the patient's pain data, medical staff can quickly obtain the patient's pain changes, adjust the management plan in time, and improve patient satisfaction. By integrating multiple influencing factors (such as pain duration, intensity, and psychological state), a weighted scoring formula is used to improve the scientificity and effectiveness of the pain management plan, provide data-driven decision support for medical staff, reduce manual intervention through automated data collection and analysis, and improve the efficiency of the pain management process, thereby saving time and resources. The analysis model can be updated regularly, and the pain assessment and management strategy can be optimized through continuous collection and feedback of new data, thereby promoting the improvement of medical quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 The figure is a system block diagram of the system proposed in the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solution in the present invention. Obviously, the described technical solution is only a part of the present invention but not all of it. Based on the technical solution in the present invention, all other technical solutions obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0028] An acute postoperative pain assessment and management decision system based on patient-reported results includes a patient pain data collection module, a data analysis and processing module, a decision support module and a user interface. The patient pain data collection module is connected to the data analysis and processing module, the data analysis and processing module is connected to the decision support module, and the user interface is connected to the patient pain data collection module, the data analysis and processing module and the decision support module. The data analysis and processing module uses a machine learning algorithm to analyze the collected data to assess the severity of pain. The pain severity score is the weighted sum of the total pain score, pain duration, pain intensity score and other influencing factors. The pain severity score formula is:

[0029] P=α·D+β·S+γ·A

[0030] Where: P is the pain severity score, D is the pain duration, S is the pain intensity score, A is other influencing factors, including but not limited to medication and psychological state, α, β, γ are weighting coefficients, which are set according to actual needs.

[0031] The present invention uses machine learning algorithms to analyze patients' pain data to achieve individualized pain assessment, which can more accurately identify each patient's pain characteristics and management needs. Through real-time collection and analysis of patients' pain data, medical staff can quickly obtain patients' pain changes, adjust management plans in time, and improve patient satisfaction. It integrates multiple influencing factors (such as pain duration, intensity, and psychological state) and uses weighted scoring formulas to improve the scientificity and effectiveness of pain management plans, provide data-driven decision support for medical staff, reduce manual intervention through automated data collection and analysis, and improve the efficiency of the pain management process, thereby saving time and resources. It can regularly update analysis models, optimize pain assessment and management strategies through continuous collection and feedback of new data, and promote the improvement of medical quality.

[0032] It should be noted that the patient pain data collection module is based on a user-friendly mobile application, with a clear pain score slider and level selection. The pain intensity score is entered through a slider or selection box, and a text box is provided to allow the patient to describe the nature of the pain and select the time period when the pain started. The patient is required to fill in the current medication status, including the name of the drug, dosage and medication time. The patient's anxiety or depression level and emotional state are collected through a multiple-choice scoring questionnaire. The completeness and rationality of the input are checked before the patient submits the information, prompts are given in time to guide the patient's input, and the collected data are stored in a secure cloud database in real time. The collected data are sent to the data analysis and processing module using a RESTful API.

[0033] The patient pain data collection module is based on a user-friendly mobile application and has several significant advantages. First, a clear pain score slider and level selection are set up to enable patients to intuitively express the intensity of pain and improve the accuracy of data collection. Secondly, a text box is provided to allow patients to describe the nature of pain, helping medical staff to fully understand the pain situation. By collecting current medication status and emotional states (such as anxiety and depression), more dimensional data support can be provided for personalized pain management. In addition, the completeness and rationality of the input information are checked before submission to ensure data quality and reduce the risk of erroneous submission. Storing data in a secure cloud database in real time and quickly transmitting information to the data analysis and processing module with the RESTful API can help achieve real-time monitoring and feedback, and improve the response speed and effectiveness of pain management. Overall, this design enhances the patient experience, improves the validity and security of data, and promotes more accurate pain management.

[0034] It should be noted that the data analysis and processing module receives data transmitted from the patient pain data collection module through the RESTful API, cleans the received data, removes duplicate, missing and unreasonable records, converts data from different sources into a unified format, extracts important features from the symptom description, including but not limited to pain type and triggering factors, uses statistical analysis methods to select features that have a greater impact on pain assessment, converts categorical variables into numerical variables, selects a machine learning algorithm suitable for the decision tree based on data characteristics and analysis objectives, trains the selected algorithm using historical data, optimizes model parameters, evaluates the performance of the model through cross-validation, inputs the newly received data into the trained model, evaluates the patient's pain level in real time, generates a total pain score, organizes the evaluation results into a report, collects new data regularly, retrains and updates the model, analyzes the feedback from medical staff and patients on the evaluation results, adjusts model parameters and feature selection, sends the analysis results to the decision support module through the API interface, and stores the data and model outputs during the analysis process in the cloud database.

[0035] The data analysis and processing module receives and processes data from the patient pain data collection module through a RESTful API. Its design brings many advantages. First, the data cleaning process ensures the high quality of the data, and improves the accuracy of subsequent analysis by removing duplicate, missing and unreasonable records. The conversion of unified data formats enables the effective integration of data from different sources, laying the foundation for feature extraction. By extracting important features such as pain type and triggering factors, the module can deeply analyze the patient's pain situation, thereby providing support for personalized treatment. The use of statistical analysis methods to select features that have a greater impact on pain assessment and convert categorical variables into numerical variables further improves the performance of the model. The selection of a suitable decision tree machine learning algorithm and its training, and the optimization of model parameters ensure the scientificity and accuracy of the analysis. The model performance is evaluated through cross-validation and adjusted in time to cope with the changing clinical data, making it possible to assess the patient's pain level in real time. The generated total pain score report provides clear and actionable data support for medical staff, which helps to adjust the pain management plan in time. In addition, regular collection of new data for model retraining and updating ensures the dynamic adaptability of the system. The feedback mechanism of the analysis results improves the participation of medical staff and patients and promotes the continuous optimization of treatment effects. Overall, this module enhances the accuracy, real-timeness, and personalization of pain assessment, helping to improve patients' overall treatment experience.

[0036] It should be noted that the decision support module receives the evaluation results from the data analysis and processing module through the API interface, retrieves the patient's historical medical records, past pain management plans and treatment responses from the cloud database, obtains the patient's individual differences, integrates the evaluation results with the patient's individual difference results, applies intelligent decision-making algorithms, generates personalized pain management plans, analyzes the patient's current condition and historical records, identifies the patient's potential risks, establishes a rule-based early warning mechanism, monitors the patient's condition in real time, promptly prompts medical staff, and generates decision reports. It regularly uses data and feedback from new mobile phones to update and optimize decision support algorithms and maintain a knowledge base of clinical guidelines and best practices.

[0037] The decision support module receives the evaluation results through the API interface, and can generate a personalized pain management plan based on the patient's historical medical records and individual differences. This integration not only improves the pertinence and effectiveness of pain management, but also can identify the patient's potential risks in real time and establish a rule-based early warning mechanism, thereby prompting medical staff to take measures in a timely manner. In addition, regular updates to algorithms and maintenance of clinical guidelines ensure that the system always reflects best practices, improving overall pain management effectiveness and patient safety. Through these measures, personalized care for patients has been strengthened and the efficiency of the use of medical resources has been optimized.

[0038] It should be noted that the decision support module retrieves the patient's historical medical records, past pain management plans, and treatment responses from the cloud database to obtain the patient's individual differences. The algorithm implementation process includes:

[0039] Step 11, database training and query: Use the Alibaba Cloud database connection library to establish a connection to the cloud database, enter the patient's ID, and return the patient's name, age, and gender;

[0040] Step 12, search historical medical records: input the patient's ID, and output a list of the patient's medical records sorted by time, including but not limited to surgical records and drug prescriptions;

[0041] Step 13, retrieve past pain management plans: input patient ID, and output chronological pain management records, including but not limited to medication use, non-drug interventions, and pain scores;

[0042] Step 14, obtaining management response: inputting the patient ID to obtain the patient's pain management response, including but not limited to changes in pain scores, patient feedback content, and side effect records;

[0043] Step 15, data integration and feature extraction: merge the data obtained from steps 11 to 14 to generate a patient pain management history file, extract the patient's most recent pain score, repeatedly used medications, and patient satisfaction;

[0044] Step 16, individual difference analysis: Apply variance analysis to analyze the individual differences of patients in pain management, structure the integrated information and extracted features, and return them to the decision support module.

[0045] By systematically retrieving and integrating the patient's historical medical records, pain management plans, and treatment responses, the accuracy and personalization of decision support are greatly improved. Through steps 11 to 16, the system can fully understand the patient's medical background and pain management process, thereby identifying individual differences. This individualized analysis lays the foundation for patients to develop targeted pain management plans, ensuring that medical interventions are more in line with the actual needs of patients. Using variance analysis, the differences in responses of different patients in pain management can be effectively identified, and treatment strategies can be further optimized. In addition, by real-time monitoring and updating of patient data, the system can quickly respond to changes in patients, adjust management plans in a timely manner, and improve the overall pain management effect. Such a process not only enhances the decision-making ability of medical staff, but also improves patient satisfaction and safety, thereby achieving higher quality medical services.

[0046] It should be noted that in step 16, the variance analysis method is used to calculate the variance, mean, between-group sum of squares, within-group sum of squares, total sum of squares, between-group mean square, and F statistic of each group of patients' pain management data. The calculated F statistic is compared with the critical F value to determine whether there are significant differences between the groups. If there are significant differences, post hoc tests are performed to determine which groups have significant differences. The analysis results are structured to form individual patient files, which include the mean and standard deviation of each group, group pair information with significant differences, and the specific performance and feedback of individual patients in pain management.

[0047] In step 16, by applying the analysis of variance method, the system can effectively evaluate the differences in the responses of different patients in pain management. By calculating the F statistic and comparing it with the critical F value, significant differences between groups can be identified, thereby revealing which specific management plans are most effective for patients' pain relief. This method not only provides a scientific basis, but also allows for targeted post-hoc testing to further analyze the specific differences between groups and form a structured individual patient profile. This process improves the level of personalization of pain management, helps optimize pain management plans, and enhances patient experience and satisfaction.

[0048] It should be noted that in step 16, the method for performing the post hoc test uses the standardized value of the mean difference, and its formula is:

[0049]

[0050] Where: q is the standardized value of the mean difference of the patient, i and j are the indexes of the data group, n is the sample size of each group of data, are the means of the i-th group and the j-th group respectively, and MSW is the within-group mean square.

[0051] In step 16, the standardized value of the mean difference is used for post hoc testing, which can effectively quantify the impact of different pain management programs on patients. By calculating the standardized value q, the system can compare the mean differences between different groups and provide a more intuitive effect evaluation. The parameters in the formula, such as and The q value represents the mean of each group, and the MSW reflects the degree of variation within the group. This method can effectively eliminate the impact of sample size differences and ensure the reliability of the results. Using the q value, it is possible to quickly identify which groups have significant differences, thereby guiding clinical decision-making and program optimization. This technical effect improves the scientificity and pertinence of the pain management system, helps to develop personalized pain management strategies, and thus improves the overall experience and effect of patients.

[0052] It should be noted that the user interface is based on the data obtained by the patient pain data collection module, data analysis and processing module, and decision support module, and reflects the effect of patient pain management through the comprehensive score of pain management data. The formula for the comprehensive score of pain management data is:

[0053]

[0054] Where: M is the comprehensive score of the patient's pain management data, k is the index of the pain data group currently being processed, m is the total number of data groups, P k is the pain score of group k, E k is the score of the kth group of influencing factors, μ is the preset pain score critical value, τ is the adjustment factor, which is set according to actual needs, and δ k is the weight coefficient, set according to actual needs, ε k , is the sensitivity impact index, which is set according to actual needs, T is the current patient's pain management time, R is the patient satisfaction score, ρ and σ are weight factors, which are set according to actual needs.

[0055] The pain management data comprehensive scoring formula M comprehensively reflects the patient's pain management effect through multi-dimensional data integration. k 、E k The pain scores and influencing factors can be effectively captured, making the scoring system highly flexible and adaptable. k , can be optimized according to actual clinical needs to enhance the accuracy of the score. In addition, the sensitivity impact index ε k and The application of further improves the ability to respond to subtle changes in pain management and ensures the scientificity and reliability of the evaluation results. The introduction of the current patient's pain management time T and satisfaction score R forms a dynamic feedback mechanism, which helps to adjust the pain management plan in a timely manner. This comprehensive score not only provides support for medical decision-making, but also enhances patients' understanding and satisfaction with the pain management process, thereby improving the overall quality of care.

[0056] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0057] Finally: The above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An acute postoperative pain assessment and management decision system based on patient-reported outcomes, characterized in that: It includes a patient pain data collection module, a data analysis and processing module, a decision support module and a user interface. The patient pain data collection module is connected to the data analysis and processing module, the data analysis and processing module is connected to the decision support module, and the user interface is connected to the patient pain data collection module, the data analysis and processing module and the decision support module. The data analysis and processing module uses a machine learning algorithm to analyze the collected data to assess the severity of pain. The pain severity score is the weighted sum of the total pain score, pain duration, pain intensity score and other influencing factors. The pain severity score formula is: P=α·D+β·S+γ·A Where: P is the pain severity score, D is the pain duration, S is the pain intensity score, A is other influencing factors, including but not limited to medication and psychological state, α, β, γ are weighting coefficients, which are set according to actual needs.

2. The acute postoperative pain assessment and management decision-making system based on patient-reported outcomes according to claim 1, characterized in that: The patient pain data collection module is based on a user-friendly mobile application, with a clear pain score slider and level selection. The pain intensity score is entered through a slider or selection box. A text box is provided to allow the patient to describe the nature of the pain and select the time period when the pain started. The patient is required to fill in the current medication status, including the name of the drug, dosage and medication time. The patient's anxiety or depression level and emotional state are collected through a multiple-choice scoring questionnaire. The completeness and rationality of the input are checked before the patient submits the information, prompts are given in time to guide the patient's input, and the collected data is stored in a secure cloud database in real time. The collected data is sent to the data analysis and processing module using a RESTful API.

3. The acute postoperative pain assessment and management decision-making system based on patient-reported outcomes according to claim 2, characterized in that: The data analysis and processing module receives data transmitted from the patient pain data collection module through the RESTful API, cleans the received data, removes duplicate, missing and unreasonable records, converts data from different sources into a unified format, extracts important features from the symptom description, including but not limited to pain type and triggering factors, uses statistical analysis methods to select features that have a greater impact on pain assessment, converts categorical variables into numerical variables, selects a machine learning algorithm suitable for the decision tree based on data characteristics and analysis objectives, trains the selected algorithm using historical data, optimizes model parameters, evaluates the performance of the model through cross-validation, inputs the newly received data into the trained model, evaluates the patient's pain level in real time, generates a total pain score, organizes the evaluation results into a report, collects new data regularly, retrains and updates the model, analyzes the feedback from medical staff and patients on the evaluation results, adjusts model parameters and feature selection, sends the analysis results to the decision support module through the API interface, and stores the data and model output during the analysis process in the cloud database.

4. The acute postoperative pain assessment and management decision system based on patient reported outcomes according to claim 3, characterized in that: The decision support module receives the evaluation results from the data analysis and processing module through the API interface, retrieves the patient's historical medical records, past pain management plans and treatment responses from the cloud database, obtains the patient's individual differences, integrates the evaluation results with the patient's individual difference results, applies intelligent decision-making algorithms, generates personalized pain management plans, analyzes the patient's current condition and historical records, identifies the patient's potential risks, establishes a rule-based early warning mechanism, monitors the patient's condition in real time, promptly prompts medical staff, and generates decision reports. It regularly uses data and feedback from new phones to update and optimize decision support algorithms and maintain a knowledge base of clinical guidelines and best practices.

5. The acute postoperative pain assessment and management decision system based on patient reported outcomes according to claim 4, characterized in that: The decision support module retrieves the patient's historical medical records, past pain management plans, and treatment responses from the cloud database to obtain the patient's individual differences. The algorithm implementation process includes: Step 11, database training and query: Use the Alibaba Cloud database connection library to establish a connection to the cloud database, enter the patient's ID, and return the patient's name, age, and gender; Step 12, search historical medical records: input the patient's ID, and output a list of the patient's medical records sorted by time, including but not limited to surgical records and drug prescriptions; Step 13, retrieve past pain management plans: input patient ID, and output chronological pain management records, including but not limited to medication use, non-drug interventions, and pain scores; Step 14, obtaining management response: inputting the patient ID to obtain the patient's pain management response, including but not limited to changes in pain scores, patient feedback content, and side effect records; Step 15, data integration and feature extraction: merge the data obtained from steps 11 to 14 to generate a patient pain management history file, extract the patient's most recent pain score, repeatedly used medications, and patient satisfaction; Step 16, individual difference analysis: Apply variance analysis to analyze the individual differences of patients in pain management, structure the integrated information and extracted features, and return them to the decision support module.

6. The acute postoperative pain assessment and management decision system based on patient reported outcomes according to claim 5, characterized in that: In step 16, variance analysis is used to calculate the variance, mean, between-group sum of squares, within-group sum of squares, total sum of squares, between-group mean square, and F statistic of each group of data in pain management of patients. The calculated F statistic is compared with the critical F value to determine whether there are significant differences between groups. If there are significant differences, post hoc tests are performed to determine which groups have significant differences. The analysis results are structured to form individual patient files, which include the mean and standard deviation of each group, group information with significant differences, and the specific performance and feedback of individual patients in pain management.

7. The acute postoperative pain assessment and management decision system based on patient reported outcomes according to claim 6, characterized in that: In step 16, the method for conducting the post hoc test uses the standardized value of the mean difference, which is given by: Where: q is the standardized value of the mean difference of the patient, i and j are the indexes of the data group, n is the sample size of each group of data, are the means of the i-th group and the j-th group respectively, and MSW is the within-group mean square.

8. The acute postoperative pain assessment and management decision system based on patient reported outcomes according to claim 7, characterized in that: The user interface is based on the data obtained by the patient pain data collection module, data analysis and processing module, and decision support module. The comprehensive score of pain management data reflects the effect of patient pain management. The formula for the comprehensive score of pain management data is: Where: M is the comprehensive score of the patient's pain management data, k is the index of the pain data group currently being processed, m is the total number of data groups, P k is the pain score of group k, E k is the score of the kth group of influencing factors, μ is the preset pain score critical value, τ is the adjustment factor, which is set according to actual needs, and δ k is the weight coefficient, set according to actual needs, ε k , is the sensitivity impact index, which is set according to actual needs, T is the current patient's pain management time, R is the patient satisfaction score, ρ and σ are weight factors, which are set according to actual needs.

Images