A personalized planning and management system and method for gynecological postoperative rehabilitation path

Abstract

The present invention discloses a personalized planning and management system and method for gynecological postoperative rehabilitation paths, the method comprising the following steps: S1, collecting patient data; S2, analyzing and predicting the management plan of analgesics for patients in different rehabilitation paths based on the collected patient data, and selecting a preliminary rehabilitation path; S3, evaluating and continuously recording at different time points after surgery; S4, and simulating and predicting the analgesic effects and possible adverse reactions in different rehabilitation paths at different time points, and revising the preliminary rehabilitation path. By presetting a personalized analgesic plan and continuously evaluating the patient's pain state and analgesic effect, it is ensured that the patient can obtain the best analgesic effect at different rehabilitation points in the short term after surgery, and while ensuring effective analgesia, the use of opioids is selectively reduced, which effectively reduces the incidence of side effects of opioids, reduces the patient's dependence on opioids and the risk of addiction, and improves the safety of the rehabilitation process.

Description

Technical Field

[0001] The present invention relates to the field of medical care information technology, and in particular to a treatment or health improvement plan, and specifically to a personalized planning and management system and method for a gynecological postoperative rehabilitation path. Background Art

[0002] In the field of gynecological surgery, especially for complex and extensive surgeries such as radical resection of malignant tumors, pelvic organ resection, extensive hysterectomy or pelvic lymph node dissection, postoperative pain management has always been the focus of clinical attention. Such surgeries not only cause significant trauma to the patient's body, but are also often accompanied by severe postoperative pain, which greatly affects the patient's recovery process and quality of life.

[0003] Traditionally, postoperative pain management mainly relies on opioids, such as morphine and fentanyl. Although these drugs have definite analgesic effects, long-term use can easily lead to a series of adverse reactions, including but not limited to nausea, vomiting, constipation, respiratory depression, and even increase the risk of addiction, thus limiting their widespread application in postoperative rehabilitation.

[0004] Therefore, it is necessary to improve the deficiencies in the prior art to solve the above problems. Summary of the invention

[0005] The present invention overcomes the deficiencies of the prior art and provides a personalized planning and management system and method for gynecological postoperative rehabilitation pathways.

[0006] To achieve the above object, the technical solution adopted by the present invention is: a method for personalized planning and management of gynecological postoperative rehabilitation pathway, comprising the following steps:

[0007] S1. Collect the patient's basic information and health information, as well as the patient's previous response data to opioids;

[0008] S2. Based on the collected patient data, analyze the similarity with the rehabilitation pathway planning of previous patients, simulate and predict the management plan of analgesics for patients in different rehabilitation pathways, and evaluate the analgesic effect, adverse reactions and the impact on postoperative recovery, and select one of the plans as the preliminary rehabilitation pathway;

[0009] S3. Evaluate and continuously record the patient's pain score, opioid use, and adverse reaction rate at different time points after surgery;

[0010] S4. Simulate and predict the analgesic effects and possible adverse reactions in different rehabilitation pathways at different time points. According to the prediction results, modify the type, dosage and frequency of analgesics in the initial rehabilitation pathway to reduce the use of opioids and achieve personalized planning and management of gynecological postoperative rehabilitation pathways.

[0011] In a preferred embodiment of the present invention, the step S1 includes the following sub-steps:

[0012] S11. Collect patient data, including basic information, health information, and previous responses to opioids;

[0013] S12. Preprocess the collected patient data, including removing duplicate, incomplete or abnormal data items, and normalizing them to ensure that the data are on the same scale.

[0014] In a preferred embodiment of the present invention, in step S11, the basic information includes: age, weight, pain threshold, surgery type and details; the health information includes: allergy history and drug reaction history; the reaction of opioids includes: dosage, effect and side effects.

[0015] In a preferred embodiment of the present invention, the step S2 includes the following sub-steps:

[0016] S21. Integrate the collected patient data and analyze and identify similarities with previous patients; including similarities in age, type of surgery, and pain sensitivity;

[0017] S22. Based on the similarity data analyzed, simulate and predict multiple possible recovery pathways for patients, covering different analgesic medication management plans; including the types of drugs involved, dosages, and dosing frequencies;

[0018] S23. For each rehabilitation pathway, simulate and predict the analgesic effect and possible adverse reactions, and evaluate the overall impact of different rehabilitation pathways on the patient's postoperative recovery;

[0019] S24. Based on the prediction and evaluation results, conduct a comprehensive assessment of various rehabilitation pathways and select the best rehabilitation pathway as the initial rehabilitation plan.

[0020] In a preferred embodiment of the present invention, in step S21, the similarity between the historical data of the current patient and a case of a previous patient is calculated: ;in, The normalized feature vector of the current patient; is the normalized feature vector of a case of a previous patient; is the number of eigenvectors; It is The weight of each feature; The current patient is The value of a feature; It is a previous patient The value of a feature;

[0021] Calculate the similarity score: ;

[0022] Calculate the average similarity of a case across multiple past patients: ;in, is the number of previous patient cases; It is The similarity score between a case of a previous patient and the current patient.

[0023] In a preferred embodiment of the present invention, in step S22, a threshold is set. , when the average similarity Greater than threshold , then the current patient is similar enough to a case of a previous patient, that is, multiple possible recovery paths for the patient are predicted , among which, the rehabilitation path Contains specific attributes of this path: drug type ,dose and dosing frequency .

[0024] In a preferred embodiment of the present invention, in step S23, the analgesic effect prediction and the adverse reaction prediction adopt a machine learning algorithm;

[0025] Analgesic effect prediction: ;in, is the predicted analgesic effect score; is the eigenvector , contains all relevant characteristic attributes of the patient, ,in, Represents age, represents body weight, and so on; is the intercept term, which is equivalent to when all features The logarithm of the predicted probability when is 0; is the model parameter , which means that for each feature The degree of influence on the predicted target variable;

[0026] Adverse reaction prediction: ;in, is the predicted probability of adverse reactions; is the base of natural logarithms;

[0027] Calculating the overall impact score : ;in, is the recovery speed score; is the complication rate score; is the quality of life improvement score; , , are the weights of the corresponding dimensions;

[0028] For each rehabilitation pathway , calculate the utility score : ;in, , , , , , , are weight factors, corresponding to analgesic effect, adverse reactions, cost-effectiveness, recovery speed, complication rate, quality of life improvement, and nonlinear adjustment factor of quality of life improvement; is a given patient characteristic At that time, Prediction of analgesic effect of various pathways; is a given patient characteristic At that time, Prediction of adverse reactions through various pathways; It is The cost of the path; It is The prediction error rate of the postoperative recovery speed of the two pathways; It is The complication rates of each route; No. Quality of life improvement scores of the two pathways.

[0029] In a preferred embodiment of the present invention, in step S24, according to each rehabilitation path in step S23 Utility score Select the best path: ; The order of priority for selection was: no adverse effects, rapid analgesia and less use of opioids.

[0030] In a preferred embodiment of the present invention, the step S4 includes the following sub-steps:

[0031] S41. Based on the data of patients’ pain scores, opioid use and adverse reaction rates collected at different time points, simulate and predict the analgesic effect and possible adverse reactions of patients in different rehabilitation pathways;

[0032] S42. Based on the prediction results, the types, dosages and frequency of analgesic drugs in the rehabilitation pathway are modified; including changing the types of drugs, adjusting the dosages and frequency of administration.

[0033] The present invention provides a system for personalized planning and management of gynecological postoperative rehabilitation pathways, comprising:

[0034] a data collection module for collecting and storing the patient's basic information, health status, and previous data on responses to opioids;

[0035] Similarity analysis module, used to analyze the similarity between the rehabilitation pathway planning of the current patient and previous patients;

[0036] The pathway planning module is used to simulate and predict the management plans of patients in different rehabilitation pathways for a variety of similar rehabilitation pathways;

[0037] A path selection module is used to select a rehabilitation path according to the management plans in different rehabilitation paths;

[0038] The data recording module is used to collect and record patients' pain scores, opioid usage, and adverse reaction rates at different time points.

[0039] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0040] The present invention provides a personalized planning and management method for gynecological postoperative rehabilitation pathways. By presetting a personalized analgesic plan, it ensures that the analgesic effect matches the patient's needs, and by continuously evaluating the patient's pain state and analgesic effect, it ensures that the patient can obtain the best analgesic effect at different rehabilitation points in the short term after surgery, significantly reducing the patient's postoperative pain. While ensuring effective analgesia, it selectively reduces the use of opioids, effectively reduces the incidence of side effects caused by long-term use of opioids, and also reduces the patient's dependence on and addiction risk of opioids, thereby improving the safety of the rehabilitation process. It is not only a concrete practice of the ERAS concept, but also an innovation and optimization of the traditional postoperative pain management model.

[0041] In the present invention, the patient's pain score, opioid usage, and adverse reaction rate are continuously recorded at different time points after surgery, and the analgesic effect and possible adverse reactions in different rehabilitation pathways are simulated and predicted based on the patient's actual rehabilitation data and historical data of the rehabilitation pathway. The type, dosage, and frequency of administration of analgesics in the rehabilitation pathway are adjusted according to the simulation prediction results and the patient's actual situation. This can better meet the patient's personalized needs, and can achieve dynamic monitoring and timely adjustment of the patient's rehabilitation process. This can not only improve the effectiveness and safety of analgesic management and reduce the use of opioids, but also promote the patient's rapid recovery and improve their quality of life.

[0042] The present invention provides a personalized planning and management system for gynecological postoperative rehabilitation paths. The system makes the rehabilitation path in the short term after gynecological surgery more comprehensive and systematic through the cooperation of a data collection module, a similarity analysis module, a path planning module, a path selection module and a data recording module, effectively improves the efficiency of planning and management, and enhances the personalization of gynecological postoperative rehabilitation and the selectivity of multiple rehabilitation paths, which helps to reduce the dependence of gynecological patients on opioids during postoperative recovery and provides patients with a better quality and personalized rehabilitation plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 It is a flow chart of a method for personalized planning and management of gynecological postoperative rehabilitation pathways according to a preferred embodiment of the present invention;

[0045] Figure 2 It is a structural schematic diagram of a personalized planning and management system for gynecological postoperative rehabilitation pathways in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0048] Application Overview:

[0049] With the promotion of the concept of Enhanced Recovery After Surgery (ERAS), multimodal analgesia strategy has gradually become the mainstream direction of gynecological postoperative pain management. The ERAS program emphasizes multimodal analgesia, that is, the use of multiple analgesic methods and drugs to reduce dependence on opioids. This includes the use of non-opioid drugs such as acetaminophen, nonsteroidal anti-inflammatory drugs (NSAIDs) and regional anesthesia techniques such as nerve blocks, and other auxiliary treatment measures to achieve more accurate, safe and efficient pain control, while reducing the use of opioids and their related side effects; in clinical operations, there are certain limitations in the postoperative rehabilitation path planning for gynecological patients by doctors alone.

[0050] Given that different patients have significant differences in their perception of pain and response to drugs, systematic and personalized analgesia management is particularly important.

[0051] In response to the above technical problems, the concept of the present invention is to propose a personalized planning and management system and method for gynecological postoperative rehabilitation pathways, which can achieve rapid and effective pain relief by monitoring and adjusting analgesia regimens at different time points, while reducing adverse reactions, promoting postoperative recovery, and reducing the use of opioids.

[0052] like Figure 1 As shown, a method for personalized planning and management of gynecological postoperative rehabilitation pathways includes the following steps:

[0053] S1. Collect the patient's basic information and health information, as well as the patient's previous response data to opioids;

[0054] S2. Based on the collected patient data, analyze the similarity with the rehabilitation pathway planning of previous patients, simulate and predict the management plan of analgesics for patients in different rehabilitation pathways, and evaluate the analgesic effect, adverse reactions and the impact on postoperative recovery, and select one of the plans as the preliminary rehabilitation pathway;

[0055] S3. Evaluate and continuously record the patient's pain score, opioid use, and adverse reaction rate at different time points after surgery;

[0056] S4. Simulate and predict the analgesic effects and possible adverse reactions in different rehabilitation pathways at different time points. According to the prediction results, modify the type, dosage and frequency of analgesics in the initial rehabilitation pathway to reduce the use of opioids and achieve personalized planning and management of gynecological postoperative rehabilitation pathways.

[0057] In some specific embodiments, the step of S1 includes the following sub-steps:

[0058] S11. Collect patient data, including basic information, health information, and previous responses to opioids;

[0059] S12. Preprocess the collected patient data, including removing duplicate, incomplete or abnormal data items, and normalizing them to ensure that the data are on the same scale.

[0060] In this embodiment, in step S11, basic information includes: age, weight, pain threshold, surgery type and details; health information includes: allergy history and drug reaction history; opioid drug reactions include: dosage, effect and side effects.

[0061] The pain threshold was assessed by visual analogue scale (VAS), numeric rating scale (NRS) or Wong-Baker facial expression scale in the early postoperative period, with 0-3 points for mild pain, 4-6 points for moderate pain, and 7-10 points for severe pain. The type and details of the surgery were as follows: the surgeon provided detailed information on the name of the surgery, surgical site, and duration of the surgery. The history of allergies and drug reactions was obtained by asking the patient or checking his medical records to understand the patient's history of adverse reactions to specific drugs (especially analgesics).

[0062] In this embodiment, in step S12, it is necessary to remove duplicate data from the acquired patient data, identify and process abnormal values: abnormal values ​​may be caused by data entry errors or special circumstances of the patient, and need to be processed according to the actual situation, such as replacing them with mean, median or deleting them; the normalization process is specifically to scale the data so that it falls into a small specific interval, such as [0,1] or [-1,1], which helps to eliminate the influence of the dimension on the result. The calculation formula is: ;in, It is the original data; is the normalized data.

[0063] In some specific embodiments, the step of S2 includes the following sub-steps:

[0064] S21. Integrate the collected patient data and analyze and identify similarities with previous patients; including similarities in age, type of surgery, and pain sensitivity;

[0065] S22. Based on the similarity data analyzed, simulate and predict multiple possible recovery pathways for patients, covering different analgesic medication management plans; including the types of drugs involved, dosages, and dosing frequencies;

[0066] S23. For each rehabilitation pathway, simulate and predict the analgesic effect and possible adverse reactions, and evaluate the overall impact of different rehabilitation pathways on the patient's postoperative recovery;

[0067] S24. Based on the prediction and evaluation results, conduct a comprehensive assessment of various rehabilitation pathways and select the best rehabilitation pathway as the initial rehabilitation plan.

[0068] In this embodiment, in step S21, the similarity between the historical data of the current patient and a case of a previous patient is calculated: ;in, The normalized feature vector of the current patient; is the normalized feature vector of a case of a previous patient; is the number of eigenvectors; It is The weight of each feature; The current patient is The value of a feature; Is the patient in the past The value of a feature;

[0069] Calculate the similarity score: ;

[0070] Calculate the average similarity of a case across multiple past patients: ;in, is the number of previous patient cases; It is The similarity score between a case of a previous patient and the current patient.

[0071] Among them, The weight of the feature , combined with the existing entropy weight method for calculation, the entropy weight method is an objective weight allocation method, which determines the weight based on the discrete degree of data, rather than based on subjective judgment. The combination of the two ensures the distribution of weights. Specifically, calculate the indicator proportion: for the normalized data, calculate each indicator In each sample The proportion of , ;in It is The sample in The value of each influencing factor;

[0072] Calculate information entropy: Calculate the information entropy of each indicator using the weight , ;in, ; is the sample size;

[0073] Calculate the coefficient of variation and weights: Coefficient of variation , calculate the weight according to the coefficient of difference .

[0074] In this embodiment, in step S22, the threshold is set , when the average similarity Greater than threshold , then the current patient is similar enough to a case of a previous patient, that is, multiple possible recovery paths for the patient are predicted , among which, the rehabilitation path Contains specific attributes of this path: drug type ,dose and dosing frequency .

[0075] In this embodiment, in step S23, the analgesic effect prediction and adverse reaction prediction use machine learning algorithms, so that it can automatically learn and discover laws and patterns from the data, and then use these laws and patterns to perform prediction, classification, clustering, and dimensionality reduction tasks. It is preferably a deep learning model, combined with modeling and simulation by artificial intelligence algorithms, and regression learning using neural network tools;

[0076] Analgesic effect prediction: ;in, is the predicted analgesic effect score; is the eigenvector , contains all relevant characteristic attributes of the patient, ,in, Represents age, represents body weight, and so on; is the intercept term, which is equivalent to when all features The logarithm of the predicted probability when is 0; is the model parameter , which means that for each feature The degree of influence on the predicted target variable;

[0077] Adverse reaction prediction: ;in, is the predicted probability of adverse reactions; is the base of natural logarithms;

[0078] Calculating the overall impact score : ;in, is the recovery speed score, obtained by regression analysis of the difference between the patient's discharge time and the normal recovery time; is the complication rate score, which is obtained by calculating the ratio of the actual incidence to the expected incidence; is the quality of life improvement score, which is obtained by calculating the change in the score of the SF-36 health self-assessment scale; , , are the weights of the corresponding dimensions;

[0079] For each rehabilitation pathway , calculate the utility score : ;in, , , , , , , are weight factors, corresponding to analgesic effect, adverse reactions, cost-effectiveness, recovery speed, complication rate, quality of life improvement, and nonlinear adjustment factor of quality of life improvement; is a given patient characteristic At that time, Prediction of analgesic effect of various pathways; is a given patient characteristic At that time, Prediction of adverse reactions through various pathways; It is The cost of the path; It is The prediction error rate of the postoperative recovery speed of the two pathways; It is The complication rates of each route; No. Quality of life improvement scores of the two pathways.

[0080] It should be noted that the entropy weight method is used to calculate , , The weights of recovery speed, complication rate and improvement of quality of life are shown in Table 1. The calculation steps of entropy weight method are consistent with those in S21.

[0081] In this embodiment, in step S24, according to each rehabilitation path in step S23, Utility score Select the best path: ; The priority order of selection is: no adverse reactions, rapid analgesia and less use of opioids, including but not limited to the combination of different categories of analgesic drugs or methods, such as non-opioid drugs (acetaminophen, NSAIDs), local anesthetic techniques (nerve blocks), physical therapy, etc.

[0082] In some specific implementation schemes, in step S3, different time points are used, such as 24 hours, 36 hours, 48 ​​hours, 72 hours after surgery, etc.; the pain score is assessed by visual analog scale (VAS), numeric rating scale (NRS) or Wong-Baker facial expression scale to evaluate the pain degree; the opioid use is the type, dosage, frequency of administration and route of administration of opioids, and the effectiveness and safety of drug use are monitored; the incidence of adverse reactions is whether the patient has nausea, vomiting, constipation, respiratory depression and other common adverse reactions of opioids, and other non-drug-related adverse reactions (such as infection, bleeding, etc.) should also be recorded and evaluated.

[0083] In some specific embodiments, the step of S4 includes the following sub-steps:

[0084] S41. Based on the data of patients’ pain scores, opioid use and adverse reaction rates collected at different time points, simulate and predict the analgesic effect and possible adverse reactions of patients in different rehabilitation pathways;

[0085] S42. Based on the prediction results, the types, dosages and frequency of analgesic drugs in the rehabilitation pathway are modified; including changing the types of drugs, adjusting the dosages and frequency of administration.

[0086] In this embodiment, in step S41, the same machine learning algorithm as in step S23 is used to predict the analgesic effect and adverse reactions;

[0087] Each recovery path , calculate the utility score : ;in, is a feature vector, including the patient’s basic information, health information, postoperative pain score, and opioid use; is a given patient characteristic At that time, Prediction of analgesic effect of various pathways; is a given patient characteristic At that time, Prediction of adverse reactions through various pathways; It is The incidence of adverse reactions by route Function prediction value, ,in, and are model parameters; , , are weight factors corresponding to the relative importance of analgesic effect, adverse reactions, and opioid dosage.

[0088] In this embodiment, in step S42, according to each rehabilitation path in step S41, Utility score Select the best path: .

[0089] The present invention provides a system for personalized planning and management of gynecological postoperative rehabilitation pathways, comprising:

[0090] a data collection module for collecting and storing the patient's basic information, health status, and previous data on responses to opioids;

[0091] Similarity analysis module, used to analyze the similarity between the rehabilitation pathway planning of the current patient and previous patients;

[0092] The pathway planning module is used to simulate and predict the management plans of patients in different rehabilitation pathways for a variety of similar rehabilitation pathways;

[0093] A path selection module is used to select a rehabilitation path according to the management plans in different rehabilitation paths;

[0094] The data recording module is used to collect and record patients' pain scores, opioid usage, and adverse reaction rates at different time points.

[0095] In some specific implementation schemes, the patient's basic information, health information and previous reaction data to opioids are collected through the data collection module, and the collected patient data is transmitted to the similarity analysis module, which analyzes the similarity between the rehabilitation path planning of the current patient and previous patients. The path planning module simulates and predicts the patient's management plan in different rehabilitation paths for multiple similar rehabilitation paths, and transmits the management plan data of different rehabilitation paths to the path selection module, which selects a preliminary rehabilitation path; through the data recording module, the patient's pain score, opioid usage and adverse reaction rate at different time points are collected, recorded and stored, and transmitted to the path planning module. For different time points, the patient's analgesic effect and possible adverse reaction management plan in different rehabilitation paths are simulated and predicted, and transmitted to the selection module. The path selection module selects a rehabilitation path, realizes the correction of the preliminary rehabilitation path, and realizes personalized planning and management of gynecological postoperative rehabilitation path.

[0096] It should be noted that the system, through the cooperation of data collection module, similarity analysis module, path planning module, path selection module and data recording module, makes the rehabilitation path in the short term after gynecological surgery more comprehensive and systematic, effectively improves the efficiency of planning and management, and enhances the personalization of gynecological postoperative rehabilitation and the optionality of multiple rehabilitation paths, which helps to reduce the dependence of gynecological patients on opioids during postoperative recovery and provides patients with better-quality and personalized rehabilitation plans.

[0097] The above is based on the ideal embodiment of the present invention. Through the above description, it is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is limited by the attached claims rather than the above description, and it is intended to include all changes within the meaning and scope of the equivalent elements of the claims. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0098] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A personalized planning and management method for gynecological postoperative rehabilitation pathway, characterized in that: The following steps are involved: S1. Collect the patient's basic information and health information, as well as the patient's previous response data to opioids; S2. Based on the collected patient data, analyze the similarity with the rehabilitation pathway planning of previous patients, simulate and predict the management plan of analgesics for patients in different rehabilitation pathways, and evaluate the analgesic effect, adverse reactions and the impact on postoperative recovery, and select one of the plans as the preliminary rehabilitation pathway; S3. Evaluate and continuously record the patient's pain score, opioid use, and adverse reaction rate at different time points after surgery; S4. Simulate and predict the analgesic effects and possible adverse reactions in different rehabilitation pathways at different time points. According to the prediction results, modify the type, dosage and frequency of analgesics in the initial rehabilitation pathway to reduce the use of opioids and achieve personalized planning and management of gynecological postoperative rehabilitation pathways. The step S2 includes the following sub-steps: S21. Integrate the collected patient data and analyze and identify similarities with previous patients; including similarities in age, type of surgery, and pain sensitivity; S22. Based on the similarity data analyzed, simulate and predict multiple possible recovery pathways for patients, covering different analgesic medication management plans; including the types of drugs involved, dosages, and dosing frequencies; S23. For each rehabilitation pathway, simulate and predict the analgesic effect and possible adverse reactions, and evaluate the overall impact of different rehabilitation pathways on the patient's postoperative recovery; S24. Based on the prediction and evaluation results, conduct a comprehensive evaluation of multiple rehabilitation pathways and select an optimal rehabilitation pathway as the initial rehabilitation plan; In step S21, the similarity between the historical data of the current patient and a case of a previous patient is calculated: ;in, The normalized feature vector of the current patient; is the normalized feature vector of a case of a previous patient; is the number of eigenvectors; It is The weight of each feature; The current patient is The value of a feature; It is a previous patient The value of a feature; Calculate the similarity score: ; Calculate the average similarity of a case across multiple past patients: ;in, is the number of previous patient cases; It is The similarity score between a case of a previous patient and the current patient; In step S22, a threshold is set. , when the average similarity Greater than threshold , then the current patient is similar enough to a case of a previous patient, that is, multiple possible recovery paths for the patient are predicted , among which, the rehabilitation path Contains specific attributes of this path: drug type ,dose and dosing frequency ; In the step S23, the analgesic effect prediction and adverse reaction prediction adopt a machine learning algorithm; Analgesic effect prediction: ;in, is the predicted analgesic effect score; is the eigenvector , contains all relevant characteristic attributes of the patient, ,in, Represents age, represents body weight, and so on; is the intercept term, which is equivalent to when all features The logarithm of the predicted probability when is 0; is the model parameter , which means that for each feature The degree of influence on the predicted target variable; Adverse reaction prediction: ;in, is the predicted probability of adverse reactions; is the base of natural logarithms; Calculating the overall impact score : ;in, is the recovery speed score; is the complication rate score; is the quality of life improvement score; , , are the weights of the corresponding dimensions; For each rehabilitation pathway , calculate the utility score : ;in, , , , , , , are weight factors, corresponding to analgesic effect, adverse reactions, cost-effectiveness, recovery speed, complication rate, quality of life improvement, and nonlinear adjustment factor of quality of life improvement; is a given patient characteristic At that time, Prediction of analgesic effect of various pathways; is a given patient characteristic At that time, Prediction of adverse reactions through various pathways; It is The cost of the path; It is The prediction error rate of the postoperative recovery speed of the two pathways; It is The complication rates of each route; No. Quality of life improvement scores of each pathway; In step S24, according to each rehabilitation path in step S23 Utility score Select the best path: ; The order of priority for selection was: no adverse effects, rapid analgesia and less use of opioids.

2. A method for personalized planning and management of gynecological postoperative rehabilitation pathways according to claim 1, characterized in that: The step S1 includes the following sub-steps: S11. Collect patient data, including basic information, health information, and previous responses to opioids; S12. Preprocess the collected patient data, including removing duplicate, incomplete or abnormal data items, and normalizing them to ensure that the data are on the same scale.

3. A method for personalized planning and management of gynecological postoperative rehabilitation pathways according to claim 2, characterized in that: In step S11, the basic information includes: age, weight, pain threshold, surgery type and details; the health information includes: allergy history and drug reaction history; the reaction of opioids includes: dosage, effect and side effects.

4. The method for personalized planning and management of gynecological postoperative rehabilitation pathway according to claim 1, characterized in that: The step S4 includes the following sub-steps: S41. Based on the data of patients’ pain scores, opioid use and adverse reaction rates collected at different time points, simulate and predict the analgesic effect and possible adverse reactions of patients in different rehabilitation pathways; S42. Based on the prediction results, the types, dosages and frequency of analgesic drugs in the rehabilitation pathway are modified; including changing the types of drugs, adjusting the dosages and frequency of administration.

5. A system for personalized planning and management of gynecological postoperative rehabilitation pathways based on any one of claims 1-4, characterized in that: include: a data collection module for collecting and storing the patient's basic information, health status, and previous data on responses to opioids; Similarity analysis module, used to analyze the similarity between the rehabilitation pathway planning of the current patient and previous patients; The pathway planning module is used to simulate and predict the management plans of patients in different rehabilitation pathways for a variety of similar rehabilitation pathways; A path selection module is used to select a rehabilitation path according to the management plans in different rehabilitation paths; The data recording module is used to collect and record patients' pain scores, opioid usage, and adverse reaction rates at different time points.

Images