Traditional Chinese medicine diagnosis and treatment decision-making method and system based on evidence

Abstract

The invention provides a traditional Chinese medicine diagnosis and treatment decision method and system based on evidence, and relates to the technical field of diagnosis and treatment decision, and the method comprises the steps: obtaining patient information, screening evidence, classifying syndromes, generating a personalized treatment scheme, collecting feedback and monitoring reactions, quantifying the curative effect, and dynamically adjusting the scheme. The method is systematized and scientific, and has a good application prospect and popularization value. Through a feedback mechanism and multi-round iterative learning, the diagnosis and treatment scheme is continuously optimized, and it is ensured that the diagnosis and treatment scheme adapts to the change requirements of patients; and by utilizing statistical analysis, the interpretability of the model is enhanced, a doctor is helped to understand a decision process, and clinical confidence is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of diagnosis and treatment decision-making, and in particular to a method and system for diagnosis and treatment decision-making in traditional Chinese medicine based on evidence-based evidence. Background Art

[0002] As a traditional medical system with a history of 5,000 years, the core concept of TCM is holistic view and syndrome differentiation and treatment. TCM emphasizes personalized diagnosis and treatment based on individual differences and disease characteristics of patients. It has the advantages of definite clinical efficacy, relatively safe medication, flexible treatment methods and relatively low cost. However, in actual clinical work, doctors often need to adjust the combination and dosage of Chinese medicine according to the specific conditions of patients to achieve better treatment effects. This process requires high experience and professional knowledge of doctors. It is a challenge for young TCM doctors who lack experience to master these complex adjustment methods.

[0003] The process of TCM diagnosis and treatment usually relies on the subjective judgment of doctors, including traditional diagnostic methods such as observation, smell, questioning, and palpation, which makes the diagnosis and treatment process of TCM subjective and uncertain. In addition, a large amount of TCM knowledge and experience is often scattered in ancient and modern documents and the minds of famous old TCM doctors, which need to be excavated and systematized. Therefore, how to transform this implicit knowledge into explicit knowledge that can be understood and applied by computers has become an important topic to promote personalized TCM treatment.

[0004] With the development of medical big data, artificial intelligence and knowledge graph technology, it has become possible to organize, analyze and apply TCM knowledge using modern technology. By constructing a TCM clinical knowledge graph and combining the processing and fusion of multimodal information, the accuracy and reliability of TCM diagnosis and treatment decisions can be effectively improved. This method can not only help doctors better understand and apply TCM theory, but also solve the knowledge sparsity and cold start problems in TCM diagnosis and treatment to a certain extent.

[0005] Therefore, multimodal information fusion technology based on the knowledge graph of traditional Chinese medicine can provide more scientific and systematic support for TCM diagnosis and treatment, promote the discovery and application of TCM knowledge, and promote the development of TCM diagnosis and treatment in a more precise and personalized direction.

[0006] The invention patent with application number 202211281449.0 discloses a method and device for TCM decision-making assistance that combines clinical knowledge graphs with multimodal information fusion, involving the fields of medical big data, knowledge graphs, and artificial intelligence. The existing technology of TCM emphasizes inheritance, practice, and complex systems, and a large amount of implicit knowledge exists in individual case verification. The existing technology combines heterogeneous network embedding, graph neural network reasoning, and deep learning interpretability technology to realize the construction of TCM knowledge graphs and the integrated framework of TCM four-diagnosis multimodal data collection, information extraction, correction filtering, and information fusion decision-making under representation learning. It has the advantages of small sample learning and strong interpretability, and has good application prospects in supporting the construction of personalized knowledge graphs for specialists / special diseases / famous doctors in human-computer collaboration, and promoting the transformation of TCM diagnosis and treatment knowledge discovery to diagnosis and treatment auxiliary decision-making. However, the technology mentions that the interpretability of the model is enhanced through feedback iterative learning, but the specific implementation of the feedback mechanism and the effect evaluation method are not detailed. This defect is likely to cause the problem that its diagnosis and treatment decision results are not accurate enough and the confidence is insufficient. Summary of the invention

[0007] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a method and system for TCM diagnosis and treatment decision-making based on evidence-based evidence, which continuously optimizes the diagnosis and treatment plan through feedback mechanism and multiple rounds of iterative learning to ensure that it adapts to the changing needs of patients; and uses statistical analysis to enhance the interpretability of the model, helping doctors understand the decision-making process and improve clinical confidence.

[0008] To achieve the above object, the present invention provides the following solutions:

[0009] An evidence-based TCM diagnosis and treatment decision-making method, including:

[0010] Obtain the target patient's basic information, TCM diagnosis data, and modern medical examination data;

[0011] Based on the established TCM evidence-based database, evidence screening is performed according to the basic information, the TCM diagnosis data and the modern medical examination data to obtain evidence-based evidence;

[0012] Inputting the TCM diagnosis data and the evidence-based evidence into the constructed symptom identification model to classify TCM syndromes and obtain syndrome identification results;

[0013] Based on the results of syndrome identification, a personalized treatment plan is generated by combining classical Chinese medicine theory and evidence-based evidence;

[0014] Collect patients' subjective feedback and objective data, and monitor patients' treatment response in real time through follow-up questionnaires, electronic medical records, and wearable devices;

[0015] Based on a statistical analysis method, quantify the therapeutic effect according to the subjective feedback, the objective data and the treatment response to obtain a quantitative therapeutic effect value, and compare the quantitative therapeutic effect value with the personalized treatment plan to obtain a comparison result;

[0016] Dynamically adjust syndrome identification results and parameters for generating personalized treatment plans according to the comparison results;

[0017] Through multiple rounds of iterative learning, the parameters for generating syndrome identification results and personalized treatment plans are continuously adjusted to make the syndrome identification results and personalized treatment plans more in line with the individual needs of patients.

[0018] Preferably, the basic information includes age, gender, medical history and living habits; the TCM diagnosis data includes: chief complaint, symptoms, tongue image and pulse condition; and the modern medical examination data includes blood test results and imaging data.

[0019] Preferably, based on the established TCM evidence-based evidence database, evidence screening is performed according to the basic information, the TCM diagnosis data and the modern medical examination data to obtain evidence-based evidence, including:

[0020] Construct a TCM evidence-based database; the TCM evidence-based database includes TCM classic literature, modern TCM research results and clinical trial data;

[0021] Using natural language processing technology to perform semantic analysis on the basic information, the TCM diagnosis data, and the modern medical examination data to extract evidence data related to the patient's symptoms;

[0022] Based on the Bayesian network, the evidence-based evidence most relevant to the evidence data is screened out in the TCM evidence-based evidence database; the screening criteria for the evidence-based evidence include: evidence level, applicability and safety.

[0023] Preferably, the symptom recognition model is obtained by training through a CNN-LSTM combined network model.

[0024] Preferably, the personalized treatment plan includes: Chinese medicine prescriptions, acupuncture plans and dietary conditioning suggestions.

[0025] Preferably, based on a statistical analysis method, the therapeutic effect is quantified according to the subjective feedback, the objective data and the treatment response to obtain a quantified therapeutic effect value, and the quantified therapeutic effect value is compared with the personalized treatment plan to obtain a comparison result, including:

[0026] Defining quantitative indicators of therapeutic efficacy; the quantitative indicators of therapeutic efficacy include therapeutic efficacy scores and change rates;

[0027] Scoring the treatment effect based on the subjective feedback and the objective data;

[0028] The efficacy score is calculated according to the score value of the subjective feedback and the score value of the objective data; efficacy score=(score value of subjective feedback+score value of objective data) / 2;

[0029] Calculate the change rate; change rate = (the index of the objective data after treatment - the index of the objective data before treatment) / the index of the objective data before treatment × 100%;

[0030] Determining the numerical value of the efficacy quantification index as the efficacy quantification value;

[0031] The quantitative value of the therapeutic effect is compared with the personalized treatment plan to analyze the relationship between the therapeutic effect and the treatment plan to obtain the comparison result; the comparison result includes a correlation analysis result and a therapeutic effect difference evaluation result.

[0032] Preferably, dynamically adjusting the syndrome identification results and the parameters for generating the personalized treatment plan according to the comparison results includes:

[0033] Performing statistical analysis on the comparison results to calculate the difference in effects of different treatment plans, and identifying key factors affecting the efficacy based on the difference in effects; the key factors include individual characteristics of the patient and symptom changes;

[0034] Determine adjustment strategies based on the key factors and different treatment options;

[0035] Apply the adjustment strategy to the syndrome recognition model, update the model parameters, and retrain the model using the gradient descent algorithm to adapt to the new parameter settings;

[0036] Regenerate personalized treatment plans based on the updated syndrome identification results.

[0037] Preferably, through multiple rounds of iterative learning, the parameters for generating the syndrome identification results and the personalized treatment plan are continuously adjusted to make the syndrome identification results and the personalized treatment plan closer to the individual needs of the patient, including:

[0038] After the new personalized treatment plan is implemented, continue to collect subjective feedback and objective data from the target patients, and return to the step of "based on the statistical analysis method, quantify the therapeutic effect according to the subjective feedback, the objective data and the treatment response to obtain a quantitative value of the therapeutic effect, and compare the quantitative value of the therapeutic effect with the personalized treatment plan to obtain a comparison result";

[0039] A closed-loop control process is formed through the feedback mechanism to continuously monitor the therapeutic effect and make dynamic adjustments.

[0040] An evidence-based TCM diagnosis and treatment decision-making system, including:

[0041] A data acquisition unit, used to acquire basic information of target patients, TCM diagnosis data and modern medical examination data;

[0042] An evidence acquisition unit, for performing evidence screening based on the established TCM evidence-based evidence database according to the basic information, the TCM diagnosis data and the modern medical examination data to obtain evidence-based evidence;

[0043] A result acquisition unit, used for inputting the TCM diagnosis data and the evidence-based evidence into the constructed symptom identification model to classify TCM syndromes and obtain syndrome identification results;

[0044] The plan generation unit is used to generate personalized treatment plans based on the syndrome identification results, combined with classical Chinese medicine theory and evidence-based evidence;

[0045] Data acquisition unit, which is used to collect patients' subjective feedback and objective data, and monitor patients' treatment response in real time through follow-up questionnaires, electronic medical records and wearable devices;

[0046] A comparison unit, configured to quantify the therapeutic effect according to the subjective feedback, the objective data and the treatment response based on a statistical analysis method to obtain a quantitative value of the therapeutic effect, and compare the quantitative value of the therapeutic effect with the personalized treatment plan to obtain a comparison result;

[0047] A feedback unit, used to dynamically adjust the syndrome identification results and the parameters for generating the personalized treatment plan according to the comparison results;

[0048] The iterative learning unit is used to continuously adjust the parameters of the syndrome identification results and the personalized treatment plan through multiple rounds of iterative learning, so that the syndrome identification results and the personalized treatment plan are closer to the individual needs of the patient.

[0049] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0050] The present invention provides a TCM diagnosis and treatment decision-making method and system based on evidence-based evidence, the method comprising: obtaining basic information, TCM diagnosis data and modern medical examination data of a target patient; based on a constructed TCM evidence-based evidence database, performing evidence screening according to the basic information, the TCM diagnosis data and the modern medical examination data to obtain evidence-based evidence; inputting the TCM diagnosis data and the evidence-based evidence into a constructed symptom recognition model to classify TCM syndromes to obtain syndrome recognition results; generating a personalized treatment plan based on the syndrome recognition results in combination with TCM classical theories and evidence-based evidence; and collecting subjective feedback from patients. and objective data, and monitor the patient's treatment response in real time through follow-up questionnaires, electronic medical records and wearable devices; based on statistical analysis methods, quantify the therapeutic effect according to the subjective feedback, the objective data and the treatment response, obtain the quantified value of the therapeutic effect, and compare the quantified value of the therapeutic effect with the personalized treatment plan to obtain a comparison result; dynamically adjust the syndrome identification results and the parameters generated by the personalized treatment plan according to the comparison result; through multiple rounds of iterative learning, continuously adjust the syndrome identification results and the parameters generated by the personalized treatment plan, so that the syndrome identification results and the personalized treatment plan are closer to the individual needs of the patient. The present invention provides a systematic and scientific TCM diagnosis and treatment decision-making method, which has good application prospects and promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] 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 will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0052] Figure 1 A flow chart of a method provided by an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of the system structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] 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.

[0055] The purpose of the present invention is to provide a method and system for TCM diagnosis and treatment decision-making based on evidence-based evidence. Through feedback mechanism and multiple rounds of iterative learning, the diagnosis and treatment plan is continuously optimized to ensure that it adapts to the changing needs of patients. Statistical analysis is used to enhance the interpretability of the model, help doctors understand the decision-making process, and improve clinical confidence.

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] Figure 1 A flow chart of a method provided by an embodiment of the present invention, such as Figure 1 As shown, the present invention provides a TCM diagnosis and treatment decision-making method based on evidence, comprising:

[0058] Step 100: Obtain basic information, TCM diagnosis data, and modern medical examination data of the target patient;

[0059] Step 200: Based on the established TCM evidence-based database, evidence screening is performed according to basic information, TCM diagnosis data and modern medical examination data to obtain evidence-based evidence;

[0060] Step 300: inputting TCM diagnosis data and evidence-based evidence into the constructed symptom identification model to classify TCM syndromes and obtain syndrome identification results;

[0061] Step 400: Generate a personalized treatment plan based on the syndrome identification results, combined with classical Chinese medicine theory and evidence-based evidence;

[0062] Step 500: Collecting subjective feedback and objective data from patients, and monitoring the patient's treatment response in real time through follow-up questionnaires, electronic medical records, and wearable devices;

[0063] Step 600: Based on the statistical analysis method, the efficacy is quantified according to the subjective feedback, objective data and treatment response to obtain a quantified efficacy value, and the quantified efficacy value is compared with the personalized treatment plan to obtain a comparison result;

[0064] Step 700: Dynamically adjust the syndrome identification results and the parameters for generating the personalized treatment plan according to the comparison results;

[0065] Step 800: Through multiple rounds of iterative learning, the parameters for generating syndrome identification results and personalized treatment plans are continuously adjusted to make the syndrome identification results and personalized treatment plans more in line with the individual needs of patients.

[0066] Preferably, the basic information includes age, gender, medical history and living habits; the TCM diagnosis data includes: chief complaint, symptoms, tongue image and pulse condition; and the modern medical examination data includes blood test results and imaging data.

[0067] Optionally, step 100 of this embodiment is specifically as follows:

[0068] Step 101: Collect basic patient information

[0069] When obtaining the basic information of the target patient, data entry is first required through the electronic medical record system (EMR) or patient management system. When the patient first visits the doctor, medical staff collects the patient's basic information, including age, gender, medical history, living habits, etc., through face-to-face interviews or electronic questionnaires. This information can be collected in the form of standardized questionnaires to ensure the consistency and completeness of the data. In addition, the system should have a data verification function to ensure that the input information is accurate, such as by setting age ranges and gender options to prevent incorrect input.

[0070] Step 102: Acquisition of TCM diagnosis data

[0071] The acquisition of TCM diagnostic data mainly relies on the clinical observation and diagnosis of TCM doctors. During the diagnosis and treatment process, doctors use traditional TCM diagnostic methods such as observation, smell, questioning, and palpation to record the patient's chief complaint, symptoms, tongue image, pulse, and other information in detail. In order to improve the accuracy and repeatability of the data, it is recommended to use a standardized TCM diagnostic record form to ensure that each doctor follows the same standards when recording. In addition, combined with modern technology, image recognition technology can be used to take pictures and analyze tongue images, further improving the objectivity and accuracy of tongue image data.

[0072] Step 103: Integration of modern medical examination data

[0073] The acquisition of modern medical examination data is usually carried out through the hospital's laboratory and imaging departments. After the patient sees the doctor, the doctor will issue relevant examination orders according to the patient's condition, including blood tests, imaging examinations (such as X-rays, CT, MRI, etc.). The examination results will be automatically uploaded to the patient's electronic medical record through the hospital's information system (HIS). Medical staff need to check and update this data regularly to ensure that all relevant modern medical examination results can be reflected in the patient's medical record in a timely and accurate manner. In addition, the system should have a data integration function to associate traditional Chinese medicine diagnosis data with modern medical examination data for subsequent analysis and decision support.

[0074] Preferably, based on the established TCM evidence-based evidence database, evidence screening is performed according to the basic information, the TCM diagnosis data and the modern medical examination data to obtain evidence-based evidence, including:

[0075] Construct a TCM evidence-based database; the TCM evidence-based database includes TCM classic literature, modern TCM research results and clinical trial data;

[0076] Using natural language processing technology to perform semantic analysis on the basic information, the TCM diagnosis data, and the modern medical examination data to extract evidence data related to the patient's symptoms;

[0077] Based on the Bayesian network, the evidence-based evidence most relevant to the evidence data is screened out in the TCM evidence-based evidence database; the screening criteria for the evidence-based evidence include: evidence level, applicability and safety.

[0078] Optionally, step 200 of this embodiment is specifically as follows:

[0079] Step 201: Construct a TCM evidence-based database

[0080] The first step in building a TCM evidence-based evidence database is to collect and organize relevant TCM classic literature, modern TCM research results, and clinical trial data. TCM classic literature can include ancient medical books such as Huangdi Neijing and Shanghan Lun, as well as research papers in modern TCM journals and databases. In order to ensure the comprehensiveness and accuracy of the data, researchers need to conduct a systematic literature review and screening of the literature to extract valid evidence related to TCM diagnosis and treatment. At the same time, clinical trial data should come from research that has undergone ethical review to ensure its scientificity and reliability. Ultimately, all collected data will be organized into a structured database for subsequent retrieval and analysis.

[0081] Step 202: Perform semantic analysis using natural language processing technology

[0082] After obtaining the patient's basic information, TCM diagnosis data, and modern medical examination data, natural language processing (NLP) technology is then used to perform semantic analysis on these data. First, the input data is cleaned using text preprocessing technology, including noise removal, word segmentation, and part-of-speech tagging. Then, named entity recognition (NER) and relationship extraction technology are applied to extract key symptoms, signs, and related medical terms from the patient information. By building a semantic model, the extracted information is matched with the data in the TCM evidence-based evidence database to identify evidence data related to the patient's symptoms. This process not only improves the efficiency of data processing, but also enhances the accuracy of information extraction.

[0083] Step 203: Evidence screening based on Bayesian network

[0084] After completing the semantic analysis, the evidence database of traditional Chinese medicine is screened based on the Bayesian network. The Bayesian network is a graphical model used to represent conditional dependencies between variables, which can effectively handle uncertainty. In this stage, a Bayesian network model containing patient symptoms, diagnostic data, and related evidence is first constructed. By inputting the extracted evidence data, the posterior probability between each piece of evidence and the patient's symptoms is calculated. According to the set screening criteria, including the level of evidence (such as randomized controlled trials, observational studies, etc.), applicability (whether the evidence is suitable for the specific situation of the current patient) and safety (whether the evidence has potential side effects), the evidence-based evidence most relevant to the patient's symptoms is screened. This process ensures the scientificity and clinical applicability of the selected evidence, and provides a solid basis for subsequent TCM diagnosis and treatment decisions.

[0085] Preferably, the symptom recognition model is obtained by training through a CNN-LSTM combined network model.

[0086] Optionally, step 300 of this embodiment includes:

[0087] Step 301: Build a CNN-LSTM combined network model

[0088] When building a symptom recognition model, we first need to design a combined model that combines a convolutional neural network (CNN) and a long short-term memory network (LSTM). The CNN part is mainly used to extract local features in TCM diagnostic data, such as image features of tongue and pulse, and key symptoms and signs in text data. Through multi-layer convolution and pooling operations, CNN can effectively capture the spatial characteristics of input data. The LSTM part is used to process time series data and can memorize and analyze patients' historical diagnostic information and treatment responses. Combining CNN and LSTM can make full use of the advantages of both and improve the model's ability to recognize complex TCM syndromes.

[0089] Step 302: Data preprocessing and feature extraction

[0090] Before model training, TCM diagnosis data and evidence-based evidence need to be preprocessed and feature extracted. First, the TCM diagnosis data is standardized, including converting tongue and pulse images into a unified size and format, and performing data enhancement to improve the generalization ability of the model. At the same time, the text data is segmented, stop words are removed, and word embedding is performed to convert symptoms and signs into vector representations. For evidence-based evidence, patient-related features are extracted and integrated with TCM diagnosis data to form an input data set containing multiple features. Finally, a feature matrix containing TCM diagnosis data and evidence-based evidence is constructed for model training.

[0091] Step 303: Model training

[0092] After completing data preprocessing, the constructed CNN-LSTM combined network model is used for training. First, the preprocessed feature matrix is ​​divided into a training set and a validation set, usually 80% as the training set and 20% as the validation set. The cross entropy loss function is used as the optimization target, and the Adam optimizer is used for model training. Through multiple rounds of iterations, the model parameters are gradually adjusted to minimize the loss function. After each training cycle, the validation set is used to evaluate the performance of the model, monitor the accuracy and loss value to prevent overfitting. During the training process, the Early Stopping method can be used to determine the best training rounds for the model to ensure that the model performs best on the validation set.

[0093] Step 304: Syndrome identification and result output

[0094] After training, the TCM diagnosis data and evidence-based evidence are input into the trained CNN-LSTM model for syndrome identification. The model extracts the features of the input data through forward propagation calculation, processes the time series information through the LSTM layer, and finally outputs the syndrome classification results. The output results include the probability distribution of each syndrome, and doctors can judge the main syndrome type of the patient based on these results. In order to improve the interpretability of the model, methods such as SHAP (SHapley Additive ex Planations) can be combined to analyze the contribution of the model to each input feature to help doctors understand the decision-making process of the model. Ultimately, the syndrome identification results will provide an important basis for the subsequent generation of personalized treatment plans.

[0095] Preferably, the personalized treatment plan includes: Chinese medicine prescriptions, acupuncture plans and dietary conditioning suggestions.

[0096] Specifically, step 400 of this embodiment includes:

[0097] Step 401: Analyze the syndrome identification results

[0098] Before generating a personalized treatment plan, the syndrome identification results need to be analyzed in detail. Based on the syndrome classification results output by the model, the doctor will identify the patient's main syndrome types and their related symptoms. At this time, combined with the classical theories of traditional Chinese medicine, doctors can refer to classic literature such as "Huangdi Neijing" and "Shanghan Lun" to understand the causes, pathogenesis and corresponding treatment principles of different syndromes. This process not only helps doctors confirm the nature of the syndrome, but also provides a theoretical basis for subsequent treatment plans to ensure the scientificity and rationality of the treatment plans.

[0099] Step 402: Integrate evidence-based evidence

[0100] On the basis of analyzing the syndrome, the doctor will further refine the treatment plan in combination with the evidence-based evidence previously screened. Evidence-based evidence includes modern Chinese medicine research results and clinical trial data, which can provide empirical support for Chinese medicine prescriptions, acupuncture programs and dietary conditioning. The doctor will select appropriate Chinese medicinal materials and acupuncture points according to the patient's specific situation (such as age, gender, constitution, etc.) and syndrome characteristics. For example, for the syndrome of "liver qi stagnation", Chinese medicines such as Bupleurum and Cyperus rotundus that soothe the liver and relieve depression may be selected, combined with corresponding acupuncture points such as Taichong and Ganshu, in order to achieve better treatment effects.

[0101] Step 403: Develop a personalized treatment plan

[0102] After comprehensively considering the results of syndrome identification and evidence-based evidence, the doctor will develop a personalized treatment plan. The plan usually includes three main parts: Chinese medicine prescription, acupuncture plan and dietary conditioning suggestions. The Chinese medicine prescription will select appropriate Chinese medicinal materials and their dosages according to the patient's specific syndrome and physical characteristics to ensure the effectiveness and safety of the medicine. The acupuncture plan will select appropriate acupuncture points and treatment frequency according to the syndrome type and the patient's specific situation. Dietary conditioning suggestions will combine the dietary health theory of traditional Chinese medicine to provide a diet plan suitable for patients and help patients to self-regulate in their daily lives.

[0103] Step 404: Recording and feedback mechanism of treatment plan

[0104] Finally, the doctor records the personalized treatment plan in the patient's electronic medical record for follow-up tracking and adjustment. At the same time, a feedback mechanism is established to encourage patients to regularly feedback their subjective feelings and objective changes during the treatment process. Through follow-up and regular evaluation, doctors can dynamically adjust the treatment plan based on the patient's feedback and treatment response to ensure the continued effectiveness of the treatment. This personalized treatment plan based on syndrome identification and evidence-based evidence not only improves the pertinence and effectiveness of TCM treatment, but also enhances the patient's sense of participation and satisfaction.

[0105] Optionally, step 500 of this embodiment includes:

[0106] Step 501: Design follow-up questionnaire

[0107] When collecting subjective feedback from patients, a structured follow-up questionnaire needs to be designed first. The questionnaire should include questions on multiple dimensions, such as symptom improvement, treatment satisfaction, quality of life, etc. In order to ensure the validity and reliability of the questionnaire, existing standardized scales such as the visual analogue scale (VAS) or the health questionnaire (SF-36) can be used as reference. The questionnaire should use concise and clear language and avoid professional terms so that patients can easily understand and answer accurately. The questionnaire can be distributed in paper form or electronic form (such as mobile phone applications or online survey platforms) to ensure that patients can fill it out conveniently during treatment.

[0108] Step 502: Update of electronic medical records

[0109] During the patient's visit, the doctor needs to update the electronic medical record (EMR) in real time to record the patient's subjective feedback and objective data. During each follow-up visit, the doctor should ask the patient about changes in symptoms, treatment response and any discomfort, and enter this information into the electronic medical record system in a timely manner. The electronic medical record system should have data integration and analysis functions, and can automatically generate patients' treatment history records and change trend charts to help doctors better evaluate the treatment effect. In addition, the system should also support secure data storage and privacy protection to ensure the security and confidentiality of patient information.

[0110] Step 503: Application of wearable devices

[0111] In order to achieve real-time monitoring of patients' treatment responses, wearable devices (such as smart watches, health monitors, etc.) can be introduced. These devices can collect patients' physiological data in real time, such as heart rate, blood pressure, sleep quality, and activity level. Patients wear these devices during treatment, and the data will be automatically uploaded to the cloud or the hospital's information system. Doctors can use the data analysis platform to view changes in patients' physiological indicators in real time and promptly identify potential health problems or treatment reactions. This real-time monitoring not only improves the efficiency of data collection, but also enhances doctors' grasp of patients' health status.

[0112] Step 504: Data integration and analysis

[0113] After collecting the patient's subjective feedback, electronic medical records, and wearable device data, the next step is to integrate and analyze this data. Through data analysis tools, data from different sources are aggregated into a unified platform to form a comprehensive health profile of the patient. Using statistical analysis methods, doctors can evaluate the effectiveness of treatment, identify key factors affecting efficacy, and dynamically adjust treatment plans based on patient feedback and physiological data. In addition, regularly generated reports can help doctors and patients jointly evaluate treatment progress and promote patient participation and treatment compliance. This comprehensive data collection and analysis method ensures the scientificity and personalization of the treatment process.

[0114] Preferably, based on a statistical analysis method, the therapeutic effect is quantified according to the subjective feedback, the objective data and the treatment response to obtain a quantified therapeutic effect value, and the quantified therapeutic effect value is compared with the personalized treatment plan to obtain a comparison result, including:

[0115] Defining quantitative indicators of therapeutic efficacy; the quantitative indicators of therapeutic efficacy include therapeutic efficacy scores and change rates;

[0116] Scoring the treatment effect based on the subjective feedback and the objective data;

[0117] The efficacy score is calculated according to the score value of the subjective feedback and the score value of the objective data; efficacy score=(score value of subjective feedback+score value of objective data) / 2;

[0118] Calculate the change rate; change rate = (the index of the objective data after treatment - the index of the objective data before treatment) / the index of the objective data before treatment × 100%;

[0119] Determining the numerical value of the efficacy quantification index as the efficacy quantification value;

[0120] The quantitative value of the therapeutic effect is compared with the personalized treatment plan to analyze the relationship between the therapeutic effect and the treatment plan to obtain the comparison result; the comparison result includes a correlation analysis result and a therapeutic effect difference evaluation result.

[0121] Specifically, step 600 of this embodiment includes:

[0122] Step 601: Define quantitative indicators of efficacy

[0123] Before quantifying the efficacy, it is necessary to first clarify the definition of efficacy quantification indicators. These indicators usually include efficacy score and change rate. The efficacy score is a comprehensive indicator that evaluates the treatment effect by combining the patient's subjective feedback and objective data, while the change rate reflects the degree of change in the patient's health status before and after treatment. By setting these indicators, doctors can evaluate the treatment effect more systematically and provide a quantitative basis for subsequent analysis.

[0124] Step 602: Calculation of treatment effect score

[0125] After collecting the patient's subjective feedback and objective data, the next step is to score the treatment effect of these data. The score of subjective feedback can be quantified through the questions in the follow-up questionnaire, for example, using a scoring system of 1 to 10, and the patient scores the degree of improvement of symptoms based on their own feelings. The score of objective data is based on the results of medical examinations, such as changes in blood pressure, blood sugar and other indicators. The doctor will calculate the subjective feedback score and objective data score for each patient based on these data to ensure the standardization and consistency of the scoring process.

[0126] Step 603: Calculate the efficacy score

[0127] After obtaining the subjective feedback score and the objective data score, the doctor will use the following formula to calculate the efficacy score:

[0128] Efficacy score = (subjective feedback score + objective data score) × Efficacy score = 2 (subjective feedback score + objective data score)

[0129] This formula is designed to comprehensively consider the patient's subjective feelings and objective medical indicators to ensure that the efficacy score can fully reflect the treatment effect. In this way, doctors can obtain a comprehensive efficacy score as the basis for subsequent analysis.

[0130] Step 604: Calculate the rate of change

[0131] The calculation of the rate of change is an important part of evaluating the treatment effect. The formula for the rate of change is:

[0132] Change rate = (the index of objective data after treatment - the index of objective data before treatment) the index of objective data before treatment × 100% Change rate = the index of objective data before treatment (the index of objective data after treatment - the index of objective data before treatment) × 100%

[0133] This calculation method can quantify the degree of change in the patient's health status before and after treatment, reflecting the actual effect of the treatment. By calculating the rate of change, doctors can intuitively understand the impact of treatment on the patient's health and provide data support for subsequent efficacy analysis.

[0134] Step 605: Determine the quantified value of therapeutic effect

[0135] After calculating the efficacy score and the rate of change, the doctor will combine the values ​​of these two indicators to determine the efficacy quantitative value. The efficacy quantitative value not only reflects the patient's subjective feelings, but also combines the changes in objective data to provide a comprehensive efficacy evaluation. Through this quantitative method, doctors can understand the treatment effect more clearly and provide a basis for subsequent adjustments to the treatment plan.

[0136] Step 606: Comparison of the quantified value of the therapeutic effect with the personalized treatment plan

[0137] Finally, the doctor compares the quantitative value of the efficacy with the personalized treatment plan to analyze the relationship between the efficacy and the treatment plan. This comparison process includes correlation analysis and efficacy difference evaluation. Correlation analysis can evaluate the relationship between the quantitative value of the efficacy and the various components of the treatment plan (such as Chinese medicine prescriptions, acupuncture plans, etc.) through statistical methods (such as Pearson correlation coefficient), helping doctors identify which treatment methods have the greatest impact on the patient's efficacy. The efficacy difference evaluation compares the quantitative values ​​of the efficacy of different patients and analyzes the differences in the effects of different treatment plans, providing data support for the subsequent optimization of personalized treatment plans. This systematic analysis method ensures the scientificity and effectiveness of the treatment plan, and ultimately improves the patient's treatment experience and satisfaction.

[0138] Preferably, dynamically adjusting the syndrome identification results and the parameters for generating the personalized treatment plan according to the comparison results includes:

[0139] Performing statistical analysis on the comparison results to calculate the difference in effects of different treatment plans, and identifying key factors affecting the efficacy based on the difference in effects; the key factors include individual characteristics of the patient and symptom changes;

[0140] Determine adjustment strategies based on the key factors and different treatment options;

[0141] Apply the adjustment strategy to the syndrome recognition model, update the model parameters, and retrain the model using the gradient descent algorithm to adapt to the new parameter settings;

[0142] Regenerate personalized treatment plans based on the updated syndrome identification results.

[0143] Optionally, step 700 of this embodiment includes:

[0144] Step 701: Analyze the comparison results

[0145] After completing the comparison between the efficacy quantification value and the personalized treatment plan, the doctors and research team will conduct an in-depth analysis of the comparison results. By evaluating the results of the correlation analysis, the team can identify which treatments have a significant positive or negative correlation with the efficacy quantification value. This analysis not only helps doctors understand the effectiveness of the current treatment plan, but also reveals potential directions for improvement. For example, if a Chinese medicine prescription has a high correlation with the efficacy quantification value, the doctor may consider continuing to use the prescription in subsequent treatments, otherwise it may need to be adjusted or replaced.

[0146] Step 702: Dynamically adjust parameters

[0147] Based on the comparison results, doctors will dynamically adjust the parameters of the syndrome recognition model and the rules for generating personalized treatment plans. This process may involve re-evaluating the model input features, such as adding new symptom features or adjusting the weights of existing features to improve the accuracy of the model. At the same time, the rules for generating personalized treatment plans may also need to be adjusted based on patient feedback and quantitative efficacy values, such as changing the dosage of traditional Chinese medicine, adding new treatment methods, or optimizing acupuncture plans. This dynamic adjustment ensures that the treatment plan can respond to the patient's changing needs in a timely manner and improves the level of personalization of treatment.

[0148] Step 703: Establishment of feedback mechanism

[0149] In order to achieve effective dynamic adjustments, it is essential to establish a feedback mechanism. This mechanism should include regular patient follow-up and data collection to continuously monitor the patient's treatment response and health status. By incorporating patients' subjective feedback and objective data into the model update process, doctors can better understand the individual needs of patients and adjust the syndrome identification results and treatment plan generation parameters accordingly. This feedback mechanism not only improves the flexibility and adaptability of treatment, but also enhances patients' participation and satisfaction, ultimately promoting the improvement of treatment effects.

[0150] Preferably, through multiple rounds of iterative learning, the parameters for generating the syndrome identification results and the personalized treatment plan are continuously adjusted to make the syndrome identification results and the personalized treatment plan closer to the individual needs of the patient, including:

[0151] After the new personalized treatment plan is implemented, continue to collect subjective feedback and objective data from the target patients, and return to the step of "based on the statistical analysis method, quantify the therapeutic effect according to the subjective feedback, the objective data and the treatment response to obtain a quantitative value of the therapeutic effect, and compare the quantitative value of the therapeutic effect with the personalized treatment plan to obtain a comparison result";

[0152] Specifically, step 800 of this embodiment includes:

[0153] Step 801: Framework for iterative learning

[0154] When implementing multiple rounds of iterative learning, this embodiment establishes a systematic framework to collect and analyze data in each iterative cycle. At the beginning of each iteration, the doctor will update the input features and parameter settings of the syndrome recognition model based on the latest patient feedback and treatment response data. In this way, the model can continuously learn and adapt to new data, thereby improving its responsiveness to the individual needs of patients. The framework of iterative learning should include four key links: data collection, model update, result evaluation, and feedback mechanism to ensure that each link can be effectively connected.

[0155] Step 802: Self-optimization of the model

[0156] In each iteration, the syndrome recognition model will optimize itself using newly collected data. By applying machine learning algorithms (such as random forests, support vector machines, etc.), the model can identify the key factors that affect the results of syndrome recognition and adjust its parameter settings based on these factors. For example, if certain symptoms show stronger predictive power in new data, the model will automatically increase the weights of these features to improve the overall recognition accuracy. At the same time, the generation rules of personalized treatment plans will also be adjusted accordingly based on the optimization results of the model to ensure that the treatment plan better meets the actual needs of the patient.

[0157] Step 803: Continuous Evaluation and Improvement

[0158] After each iteration, doctors and research teams will evaluate the performance of the model and analyze its accuracy and effectiveness on new data. This evaluation process not only includes checking the accuracy of syndrome identification results, but also covers the evaluation of the efficacy of personalized treatment plans. By comparing the results of different iteration cycles, the team can identify the improvements and shortcomings of the model and formulate corresponding improvement measures accordingly. This continuous evaluation and improvement process ensures that the model and treatment plan can continue to adapt to the individual needs of patients, ultimately achieving higher treatment effects and patient satisfaction.

[0159] Corresponding to the above method, such as Figure 2 As shown, this embodiment also provides a TCM diagnosis and treatment decision-making system based on evidence, including:

[0160] A data acquisition unit, used to acquire basic information of target patients, TCM diagnosis data and modern medical examination data;

[0161] An evidence acquisition unit, for performing evidence screening based on the established TCM evidence-based evidence database according to the basic information, the TCM diagnosis data and the modern medical examination data to obtain evidence-based evidence;

[0162] A result acquisition unit, used for inputting the TCM diagnosis data and the evidence-based evidence into the constructed symptom identification model to classify TCM syndromes and obtain syndrome identification results;

[0163] The plan generation unit is used to generate personalized treatment plans based on the syndrome identification results, combined with classical Chinese medicine theory and evidence-based evidence;

[0164] Data acquisition unit, which is used to collect patients' subjective feedback and objective data, and monitor patients' treatment response in real time through follow-up questionnaires, electronic medical records and wearable devices;

[0165] A comparison unit, configured to quantify the therapeutic effect according to the subjective feedback, the objective data and the treatment response based on a statistical analysis method to obtain a quantitative value of the therapeutic effect, and compare the quantitative value of the therapeutic effect with the personalized treatment plan to obtain a comparison result;

[0166] A feedback unit, used to dynamically adjust the syndrome identification results and the parameters for generating the personalized treatment plan according to the comparison results;

[0167] The iterative learning unit is used to continuously adjust the parameters of the syndrome identification results and the personalized treatment plan through multiple rounds of iterative learning, so that the syndrome identification results and the personalized treatment plan are closer to the individual needs of the patient.

[0168] The beneficial effects of the present invention are as follows:

[0169] (1) The present invention enhances the scientificity and accuracy of diagnosis and treatment decisions by combining classical Chinese medical theories with modern medical data.

[0170] (2) The present invention generates a personalized treatment plan based on the patient's specific conditions, thereby improving the targetedness and effectiveness of the treatment.

[0171] (3) The present invention continuously optimizes the diagnosis and treatment plan through feedback mechanism and multiple rounds of iterative learning to ensure that it adapts to the changing needs of patients.

[0172] (4) The present invention uses statistical analysis to enhance the interpretability of the model, helping doctors understand the decision-making process and improving clinical confidence.

[0173] (5) The present invention can adapt to the individual differences of different patients, especially in small sample learning scenarios, and can still maintain a high accuracy rate.

[0174] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0175] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A TCM diagnosis and treatment decision-making method based on evidence, characterized in that: include: Obtain the target patient's basic information, TCM diagnosis data, and modern medical examination data; Based on the established TCM evidence-based database, evidence screening is performed according to the basic information, the TCM diagnosis data and the modern medical examination data to obtain evidence-based evidence; Inputting the TCM diagnosis data and the evidence-based evidence into the constructed symptom identification model to classify TCM syndromes and obtain syndrome identification results; Generate personalized treatment plans based on syndrome identification results, combining classical TCM theories and evidence-based evidence; Collect patients' subjective feedback and objective data, and monitor patients' treatment responses in real time through follow-up questionnaires, electronic medical records, and wearable devices; Based on a statistical analysis method, quantify the therapeutic effect according to the subjective feedback, the objective data and the treatment response to obtain a quantitative therapeutic effect value, and compare the quantitative therapeutic effect value with the personalized treatment plan to obtain a comparison result; Dynamically adjust syndrome identification results and parameters for generating personalized treatment plans according to the comparison results; Through multiple rounds of iterative learning, the parameters for generating syndrome identification results and personalized treatment plans are continuously adjusted to make the syndrome identification results and personalized treatment plans more in line with the individual needs of patients.

2. The evidence-based TCM diagnosis and treatment decision-making method according to claim 1 is characterized in that: The basic information includes age, gender, medical history and living habits; the TCM diagnosis data includes: chief complaint, symptoms, tongue condition and pulse condition; the modern medical examination data includes blood test results and imaging data.

3. The method for TCM diagnosis and treatment decision-making based on evidence according to claim 1, characterized in that: Based on the established TCM evidence-based evidence database, evidence screening is performed according to the basic information, the TCM diagnosis data and the modern medical examination data to obtain evidence-based evidence, including: Construct a TCM evidence-based database; the TCM evidence-based database includes TCM classic literature, modern TCM research results and clinical trial data; Using natural language processing technology to perform semantic analysis on the basic information, the TCM diagnosis data, and the modern medical examination data to extract evidence data related to the patient's symptoms; Based on the Bayesian network, the evidence-based evidence most relevant to the evidence data is screened out in the TCM evidence-based evidence database; the screening criteria for the evidence-based evidence include: evidence level, applicability and safety.

4. The evidence-based TCM diagnosis and treatment decision-making method according to claim 1 is characterized in that: The symptom recognition model is obtained by training through a CNN-LSTM combined network model.

5. The evidence-based TCM diagnosis and treatment decision-making method according to claim 1 is characterized in that: The personalized treatment plan includes: Chinese medicine prescriptions, acupuncture plans and dietary conditioning recommendations.

6. The evidence-based TCM diagnosis and treatment decision-making method according to claim 1 is characterized in that: Based on the statistical analysis method, the therapeutic effect is quantified according to the subjective feedback, the objective data and the treatment response to obtain a quantitative therapeutic effect value, and the quantitative therapeutic effect value is compared with the personalized treatment plan to obtain a comparison result, including: Defining quantitative indicators of therapeutic efficacy; the quantitative indicators of therapeutic efficacy include therapeutic efficacy scores and change rates; Scoring the treatment effect based on the subjective feedback and the objective data; The efficacy score is calculated according to the score value of the subjective feedback and the score value of the objective data; efficacy score=(score value of subjective feedback+score value of objective data) / 2; Calculate the change rate; change rate = (the index of the objective data after treatment - the index of the objective data before treatment) / the index of the objective data before treatment × 100%; Determining the numerical value of the efficacy quantification index as the efficacy quantification value; The quantitative value of the therapeutic effect is compared with the personalized treatment plan to analyze the relationship between the therapeutic effect and the treatment plan to obtain the comparison result; the comparison result includes a correlation analysis result and a therapeutic effect difference evaluation result.

7. The evidence-based TCM diagnosis and treatment decision-making method according to claim 1 is characterized in that: Dynamically adjust the syndrome identification results and the parameters for generating the personalized treatment plan according to the comparison results, including: Performing statistical analysis on the comparison results to calculate the difference in effects of different treatment plans, and identifying key factors affecting the efficacy based on the difference in effects; the key factors include individual characteristics of the patient and symptom changes; Determine adjustment strategies based on the key factors and different treatment options; Apply the adjustment strategy to the syndrome recognition model, update the model parameters, and retrain the model using the gradient descent algorithm to adapt to the new parameter settings; Regenerate personalized treatment plans based on the updated syndrome identification results.

8. The evidence-based TCM diagnosis and treatment decision-making method according to claim 1 is characterized in that: Through multiple rounds of iterative learning, the parameters for generating the syndrome identification results and the personalized treatment plan are continuously adjusted to make the syndrome identification results and the personalized treatment plan closer to the individual needs of the patient, including: After the new personalized treatment plan is implemented, continue to collect subjective feedback and objective data from the target patients, and return to step "based on the statistical analysis method, quantify the therapeutic effect according to the subjective feedback, the objective data and the treatment response to obtain a quantitative value of the therapeutic effect, and compare the quantitative value of the therapeutic effect with the personalized treatment plan to obtain a comparison result"; A closed-loop control process is formed through the feedback mechanism to continuously monitor the therapeutic effect and make dynamic adjustments.

9. An evidence-based TCM diagnosis and treatment decision-making system, characterized in that: include: A data acquisition unit, used to acquire basic information of target patients, TCM diagnosis data and modern medical examination data; An evidence acquisition unit, for performing evidence screening based on the established TCM evidence-based evidence database according to the basic information, the TCM diagnosis data and the modern medical examination data to obtain evidence-based evidence; A result acquisition unit, used for inputting the TCM diagnosis data and the evidence-based evidence into the constructed symptom identification model to classify TCM syndromes and obtain syndrome identification results; The plan generation unit is used to generate personalized treatment plans based on the syndrome identification results, combined with classical Chinese medicine theory and evidence-based evidence; Data acquisition unit, which is used to collect patients' subjective feedback and objective data, and monitor patients' treatment response in real time through follow-up questionnaires, electronic medical records and wearable devices; A comparison unit, configured to quantify the therapeutic effect according to the subjective feedback, the objective data and the treatment response based on a statistical analysis method to obtain a quantitative value of the therapeutic effect, and compare the quantitative value of the therapeutic effect with the personalized treatment plan to obtain a comparison result; A feedback unit, used to dynamically adjust the syndrome identification results and the parameters for generating the personalized treatment plan according to the comparison results; The iterative learning unit is used to continuously adjust the parameters of the syndrome identification results and the personalized treatment plan through multiple rounds of iterative learning, so that the syndrome identification results and the personalized treatment plan are closer to the individual needs of the patient.

Images