Doctor-patient collaborative management system and method based on perioperative period

Abstract

The invention relates to the field of medical care informatics, in particular to a doctor-patient collaborative management system and method based on a perioperative period. Comprising the steps of collecting and preprocessing all necessary information of a patient, and performing structured processing on preprocessed medical data to obtain structured medical data; based on the login request of the doctor and the patient, verifying the access authority of the doctor and the patient to obtain a verified login request; based on the verified login request, calling structured medical data; performing real-time analysis and predictive analysis based on the structured medical data to obtain a risk assessment report; based on the risk assessment report, different treatment schemes are assessed and sorted, and doctors are helped to formulate the treatment schemes; and generating a comprehensive report in combination with the treatment scheme, the operation result and the patient satisfaction survey result. The technical problems that when doctor-patient collaborative management in the perioperative period is achieved, medical data cannot be accurately processed, patient health risks cannot be accurately predicted, and management individuation is insufficient are solved.

Description

Technical Field

[0001] The present invention relates to the field of medical care informatics, and in particular to a perioperative doctor-patient collaborative management system and method. Background Art

[0002] In the modern medical environment, the challenge of processing and managing large amounts of unstructured medical data is increasing. These data, including patients' personal information, medical history, treatment records, surgical history, and real-time vital signs, are usually scattered across various medical systems, such as hospital information systems, vital sign monitoring devices, and other related data sources, such as laboratory information systems and drug management systems. The unstructured characteristics of these data make it difficult to extract useful information from them, limiting their application in clinical decision support.

[0003] With the advancement of technology, natural language processing (NLP) and machine learning technologies have been widely used in the analysis of medical data to assist doctors in better understanding and utilizing this data. Through intelligent processing, unstructured text can be converted into a structured format, thereby supporting advanced data analysis, improving the accuracy of treatment recommendations, and providing more effective decision support. In addition, context-enhanced parsing technology allows the system to have a deeper understanding of the meaning of medical texts, thereby accurately identifying key medical information, which is of great significance for improving the accuracy of diagnosis and formulating personalized treatment plans.

[0004] However, the above technology still has at least the following technical problems: it cannot accurately process medical data when realizing perioperative doctor-patient collaborative management, it cannot provide accurate predictions of patient health risks, and there is a technical problem of insufficient management personalization. Summary of the invention

[0005] The present invention provides a perioperative doctor-patient collaborative management system and method to solve the technical problems of failure to accurately process medical data, failure to accurately predict patient health risks, and insufficient management personalization when implementing perioperative doctor-patient collaborative management.

[0006] The present invention provides a perioperative doctor-patient collaborative management system and method, which specifically includes the following technical solutions: A doctor-patient collaborative management method based on the perioperative period includes the following steps: S1. Collect and preprocess all necessary information of the patient to obtain preprocessed medical data; perform structured processing on the preprocessed medical data to obtain structured medical data, and store and manage the structured medical data; S2. Based on the login request of the doctor and the patient, verify the access rights of the doctor and the patient, and obtain the verified login request; based on the verified login request, retrieve the structured medical data; perform real-time analysis and predictive analysis based on the structured medical data to obtain a risk assessment report; S3. Based on the risk assessment report, different treatment options are evaluated and ranked to help doctors develop treatment plans; a comprehensive report is generated by combining treatment plans, surgical results, and patient satisfaction survey results.

[0007] Preferably, the S1 specifically includes: In the process of obtaining structured medical data, structural requirements are determined, and based on the structural requirements, natural language processing technology is used to parse and understand the pre-processed medical data, including using lexical analysis, syntactic analysis, and semantic analysis to extract entities and attributes in the processed medical data, and converting unstructured text into preliminarily labeled medical data elements; standardizing the preliminarily labeled medical data, and performing data quality checks on the standardized medical data; and obtaining verified structured medical data.

[0008] Preferably, the S1 specifically includes: In the process of obtaining structured medical data, a context-enhanced parsing algorithm is introduced to obtain the semantic weight of the entity by introducing correlation coefficient and information entropy evaluation and utilizing context information.

[0009] Preferably, the S1 specifically includes: Integrate semantic weights into verified structured medical data and transform them into usable structured medical data.

[0010] Preferably, the S2 specifically includes: Perform feature extraction, feature derivation and feature selection on the retrieved structured medical data, select features related to disease risk assessment to identify the feature set with the most predictive value; apply the trained support vector machine model to the feature set obtained based on the structured medical data, assess the patient's health status and predict the risk of disease or disease development to obtain prediction results; and based on the prediction results, obtain the main factors affecting the risk and recommended monitoring or intervention measures; and finally generate a risk assessment report.

[0011] Preferably, the S2 specifically includes: During the feature selection process, a feature selection engine is designed to optimize feature selection.

[0012] Preferably, the S3 specifically includes: Integrate the risk assessment report into the decision support system, use the treatment preferences and clinical guidelines entered by the doctor to evaluate and rank different treatment options, obtain a treatment plan, and get personalized treatment recommendations based on the treatment plan; at the same time, adjust the treatment plan in combination with the communication platform to obtain the best treatment plan.

[0013] A perioperative doctor-patient collaborative management system is applied to the perioperative doctor-patient collaborative management method, and includes the following parts: Data collection module, central database module, authority management module, real-time interaction and communication module, risk assessment and management module, decision support module, report and feedback module; The data acquisition module is used to collect all necessary information of the patient, and pre-process and structure all necessary information to obtain structured medical data; the structured medical data is transmitted to the central database module; Central database module, which stores and manages structured medical data and real-time communication records between doctors and patients; The authority management module, based on the login request of doctors and patients, calls the structured medical data in the central database module, manages and verifies the access rights of doctors and patients, obtains the verified login request, and sends the verified login request to the real-time interaction and communication module and the risk assessment and management module; The real-time interaction and communication module, based on the verified login request, retrieves the structured medical data provided by the central database module, conducts real-time communication between doctors and patients through the communication platform, obtains the real-time communication records between doctors and patients, and stores them back in the central database module; at the same time, the real-time communication between doctors and patients is sent to the decision support module; The risk assessment and management module performs real-time analysis and predictive analysis on the structured medical data in the central database module based on the verified login request to obtain a risk assessment report; the risk assessment report is sent to the decision support module; The decision support module provides decision support based on risk assessment reports and real-time communication between doctors and patients, helps doctors develop treatment plans, and provides feedback to doctors and patients; the treatment plans are sent to the reporting and feedback module; The reporting and feedback module combines treatment plans, surgical results and patient satisfaction surveys to generate comprehensive reports for hospital management and patients to review.

[0014] The beneficial effects of the technical solution of the present invention are: 1. Through intelligent structural processing of collected medical information, unstructured text data is converted into a structured format that is easy to manage and analyze, thereby improving the accuracy and availability of data. Structured medical data facilitates more in-depth data analysis, supports complex data query and report generation, and thus provides doctors with more accurate treatment recommendations and decision support; the introduction of natural language processing and context-enhanced parsing algorithms can provide a deeper understanding of the semantics of medical texts, so that key medical information can be accurately identified and utilized, increasing the accuracy of analysis and providing a more reliable data foundation for decision support systems.

[0015] 2. By designing a feature selection engine to obtain refined feature selection and optimized model parameter settings, patients' health risks can be more accurately identified and predicted. Accurate predictions help doctors develop more effective treatment plans, thereby improving treatment outcomes.

[0016] 3. By using risk assessment reports, doctors' treatment preferences and clinical guidelines to evaluate and sort treatment options, the scientific nature and personalization of treatment plans are ensured, greatly improving the targetedness and effectiveness of treatment; through real-time communication on a secure communication platform, patients can directly participate in discussions on treatment plans, improving patient satisfaction, treatment compliance and overall treatment effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a structural diagram of a perioperative doctor-patient collaborative management system according to the present invention; Figure 2 This is a flow chart of a perioperative doctor-patient collaborative management method according to the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all 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.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The following is a detailed description of a specific scheme of a perioperative doctor-patient collaborative management system and method provided by the present invention in conjunction with the accompanying drawings.

[0021] See attached Figure 1, which shows a structure diagram of a perioperative doctor-patient collaborative management system provided by an embodiment of the present invention, the system includes the following parts: Data collection module, central database module, authority management module, real-time interaction and communication module, risk assessment and management module, decision support module, report and feedback module; The data collection module is used to collect all necessary information of the patient; all necessary information includes basic personal information, medical history, previous treatment records and surgical history, and current vital signs, and all necessary information is pre-processed and intelligently structured to obtain structured medical data, and the structured medical data is transmitted to the central database module; The central database module stores and manages structured medical data to ensure data integrity and security for subsequent processing; it also stores real-time communication records between doctors and patients; The authority management module, based on the login request of doctors and patients, calls the structured medical data in the central database module, manages and verifies the access rights of doctors and patients, ensures data security and privacy protection, obtains the verified login request, controls data access, and sends the verified login request to the real-time interaction and communication module and the risk assessment and management module; The real-time interaction and communication module retrieves the structured medical data provided by the central database module based on the verified login request, realizes real-time communication between doctors and patients through the communication platform, obtains the real-time communication records between doctors and patients, and stores them back in the central database module for subsequent query and analysis; at the same time, the real-time communication between doctors and patients is sent to the decision support module; Real-time communication including pre-operative consultation and post-operative care; communication platforms such as video conferencing, instant messaging or email; The risk assessment and management module, based on the verified login request, conducts real-time and predictive analysis on the structured medical data in the central database module, obtains a risk assessment report for reference by doctors and patients, and provides personalized surgical risk management suggestions; the risk assessment report is sent to the decision support module; The decision support module provides decision support based on the patient's risk assessment report and real-time communication between doctors and patients, helps doctors develop treatment plans, and provides feedback to doctors and patients; the treatment plan includes treatment recommendations and plans; and sends the treatment plan to the reporting and feedback module; The reporting and feedback module combines treatment plans, surgical results and patient satisfaction surveys to generate detailed comprehensive reports for hospital management and patients to review; the comprehensive report includes a surgical report and a follow-up tracking feedback form to evaluate treatment effectiveness and patient satisfaction.

[0022] See attached Figure 2, which shows a flow chart of a perioperative doctor-patient collaborative management method provided by an embodiment of the present invention, the method comprising the following steps: S1. Collect and preprocess all necessary information of the patient to obtain preprocessed medical data; perform structured processing on the preprocessed medical data to obtain structured medical data, and store and manage the structured medical data; First, all necessary information required for perioperative management is determined based on expert experience, including the patient's basic personal information, medical history, treatment records, surgical history, and real-time vital signs. All necessary information is collected through hospital information systems, vital signs monitoring equipment, and other possible data sources, such as laboratory information systems and drug management systems, to obtain all necessary information.

[0023] All necessary information collected is preprocessed, including data cleaning, formatting and preliminary data verification, to obtain preprocessed medical data, laying the foundation for subsequent structured processing; data cleaning, such as removing invalid or erroneous data; formatting, such as standardizing the date and time format; applying intelligent structuring technology to the preprocessed medical data to convert unstructured data into a structured format that is easy to manage and analyze, to obtain structured medical data; the specific implementation process is as follows: First, determine the structural requirements based on expert experience. The structural requirements include the data that needs to be structured and the format requirements that the structured data needs to meet, so as to ensure that all key medical information is correctly understood and standardized. Based on the structural requirements, use natural language processing technology to parse and understand the pre-processed medical data, including using lexical analysis, syntactic analysis and semantic analysis to extract entities (such as disease names, drug names, surgical names, etc.) and attributes (such as time, quantity, frequency, etc.) in the data, so as to convert unstructured text into preliminary labeled medical data elements, such as time, events, conditions, etc. Furthermore, the preliminarily labeled medical data is standardized, such as mapping disease and symptom names to ICD-10 codes and unifying date and time formats; the standardized medical data (i.e. structured medical data) is subjected to automated data quality checks using existing verification technologies, such as consistency checks and integrity verification, to ensure that the data is correct; and finally, verified structured medical data is obtained; In order to avoid insufficient context understanding in the natural language processing process, the context-enhanced parsing algorithm is introduced. By introducing the correlation coefficient and information entropy, the context information is accurately evaluated and used to obtain the semantic weight of the entity. The specific implementation formula is as follows:

[0024] in, Is Entity The semantic weight of Is Entity The surrounding set of context words; Is Entity With context words The distance between is the standard deviation parameter that controls the decay rate; and It is the weight parameter that adjusts the influence of distance and information entropy; is the context word Probability of appearing in the text; It is an information entropy term, which is used to enhance the weight of rare but informative words. It emphasizes the impact of uncommon but highly informative words on entities, and helps improve the sensitivity of the context-enhanced parsing algorithm to professional terms or keywords. Considering the entity and context words The closer the distance, the greater the impact. By adjusting the square distance and standard deviation, the influence of distance can be controlled more finely. Finally, the calculated semantic weights are integrated into the verified structured medical data and converted into usable structured medical data, ensuring the practicality and application value of the output of the context-enhanced parsing algorithm and providing accurate data support for subsequent medical decision support.

[0025] The verified structured medical data will be securely migrated to the central database using existing encryption transmission and data loading technologies to ensure the security of the structured medical data during transmission and its correct integration in the central database.

[0026] S2. Based on the login request of the doctor and the patient, verify the access rights of the doctor and the patient, and obtain the verified login request; based on the verified login request, retrieve the structured medical data; perform real-time analysis and predictive analysis based on the structured medical data to obtain a risk assessment report; Based on the login request of the doctor and the patient, the access rights of the doctor and the patient are verified, and the verified login request is obtained. The specific implementation process is as follows: Based on the login request from the doctor and the patient, a first-level verification is performed; the first-level verification is to verify whether the username and password match through existing matching technology; a second-level verification can also be performed, and the second-level verification uses a one-time password (OTP) or biometric technology sent to the mobile phone; after the login request is verified, the user's role's access rights to specific medical data are checked according to the user's role, such as doctor or patient, and the permission information is stored in the central database and associated with the user account; once the permission verification is completed, the scope of data that the user can access will be determined based on the user's permission level; structured medical data is retrieved from the central database based on the verified login request and user permissions; structured medical data includes the patient's historical medical records, real-time vital signs data and treatment plans; doctors and patients can communicate in real time through existing secure communication platforms, such as video conferencing, instant messaging or email; real-time communication enables doctors to provide more accurate consultation and support based on the retrieved structured medical data, while enhancing patient participation and satisfaction.

[0027] Doctors can retrieve medical data related to all patients undergoing the same type of surgery, while patients can only retrieve medical data related to themselves; Furthermore, real-time analysis and predictive analysis are performed based on the retrieved structured medical data to obtain a risk assessment report. The specific implementation process is as follows: The retrieved structured medical data is extracted using existing feature engineering technology, and feature derivation technology is used to derive features to obtain an expanded comprehensive feature set; based on expert experience and automated feature selection techniques, such as recursive feature elimination, key features related to disease risk assessment are selected to identify the most predictive feature set, and the above feature set is divided into a training set and a test set. The support vector machine model is trained using the training set data, and the support vector machine model parameters, such as the kernel function type, C value, and gamma parameter, are adjusted to optimize the performance of the support vector machine model. The accuracy and generalization ability of the support vector machine model are verified by cross-validation based on the test set; the trained support vector machine model is applied to the feature set obtained based on the patient's structured medical data to assess the patient's health status and predict the risk of illness or disease development, and the output of the support vector machine model is obtained, which is a risk score, indicating the probability of the patient suffering from a specific disease, that is, the prediction result; and the prediction result is generated using the Local Interpretable Model-Sensitive Explanation (LIME) or the Shapley Value Explanation (SHAP) tool based on game theory to obtain the main factors affecting the risk and the recommended monitoring or intervention measures. Finally, a detailed risk assessment report is generated, which includes risk score, main factors affecting risk, and recommended monitoring or intervention measures; In the feature selection process, in order to ensure that the selected features can reflect the significant impact on disease risk and avoid overfitting, a feature selection engine is designed to optimize the feature selection process and enhance the explanatory power and prediction accuracy of the support vector machine model. The specific implementation process is as follows: In medical data analysis, a feature usually represents a measurable variable, which can be quantitative, such as blood pressure, blood sugar level, weight, etc., or quantified qualitative data, such as gender male = 1, female = 0; smoking status yes / no, etc. For example, consider a simple feature "patient's systolic blood pressure" in a data set in the form of a column of values.

[0028] First, based on each feature Based on the variance and the correlation coefficient of the target variable, the initial weights are assigned while considering the nonlinear effect of feature variability and the reconciliation balance of the correlation between the feature and the target variable. :

[0029] in, Indicates Class features are features of any medical record data that represent a patient, such as age, blood pressure, and cholesterol level; yes The variance of The degree of variation of class features in samples. The larger the variance, the greater the difference between data points. yes The variance of yes With the target variable The correlation coefficient between them is used to measure the strength of the linear relationship between the two; the target variable Such as disease states; is assigned to The weight of the class feature is based on The variability of class features and their correlation with the target variable are calculated; The above process uses quantitative methods to preliminarily evaluate the contribution of each feature to the prediction task, making the subsequent feature selection process more targeted and efficient; Furthermore, the recursive feature elimination method is applied to gradually remove the features with the lowest contribution. By gradually reducing the feature set, not only can the complexity of the support vector machine model be reduced, but also the interpretability of the support vector machine model can be improved. After each round of elimination, the importance of the remaining features is re-evaluated to ensure that the final retained feature set is the optimal one.

[0030] S3. Based on the risk assessment report, different treatment options are evaluated and ranked to help doctors develop treatment plans; a comprehensive report is generated by combining treatment plans, surgical results, and patient satisfaction survey results.

[0031] Integrate the risk assessment report into the existing decision support system. The decision support system uses the treatment preferences and clinical guidelines entered by the doctor to evaluate and rank different treatment options, help doctors develop treatment plans, and obtain personalized treatment recommendations based on the treatment plan, including drug selection, surgical options, treatment duration, and possible side effects. At the same time, through a secure communication platform such as video conferencing or instant messaging, doctors and patients discuss the risk assessment report and recommended treatment plans. Finally, the doctor uses the expert experience method to adjust the treatment plan and obtain the best treatment plan. Once the treatment plan is discussed and agreed by the patient, it will be recorded and implemented in the hospital system, and specific measures and schedules for implementation will be obtained. After the operation, the patient's recovery data and surgical results are collected through existing means, and the patient's feedback on the treatment process and results is collected through a satisfaction survey, and a detailed report containing surgical results and patient satisfaction is generated. Combine the treatment plan, surgical results, risk assessment report, and patient satisfaction survey results to form a comprehensive report for hospital management and patients to review. The comprehensive report includes treatment effect evaluation, patient health improvement, and future medical advice.

[0032] Ultimately, collaborative management of doctors and patients based on the perioperative period will be achieved.

[0033] In summary, a perioperative doctor-patient collaborative management system and method was completed.

[0034] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0035] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0036] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A doctor-patient collaborative management method based on the perioperative period, characterized in that: The following steps are involved: S1. Collect and pre-process all necessary information of the patient to obtain pre-processed medical data; Structuring the preprocessed medical data to obtain structured medical data, and storing and managing the structured medical data; S2. Based on the login request of the doctor and the patient, verify the access rights of the doctor and the patient, and obtain the verified login request; based on the verified login request, retrieve the structured medical data; Conduct real-time and predictive analysis based on structured medical data to obtain risk assessment reports; S3. Evaluate and rank different treatment options based on the risk assessment report to help doctors develop treatment plans; Combine treatment plans, surgical outcomes, and patient satisfaction survey results to generate comprehensive reports.

2. The perioperative doctor-patient collaborative management method according to claim 1, characterized in that: The S1 specifically includes: In the process of obtaining structured medical data, structural requirements are determined, and based on the structural requirements, natural language processing technology is used to parse and understand the pre-processed medical data, including using lexical analysis, syntactic analysis, and semantic analysis to extract entities and attributes in the processed medical data, and converting unstructured text into preliminarily labeled medical data elements; standardizing the preliminarily labeled medical data, and performing data quality checks on the standardized medical data; and obtaining verified structured medical data.

3. The perioperative doctor-patient collaborative management method according to claim 2, characterized in that: The S1 specifically includes: In the process of obtaining structured medical data, a context-enhanced parsing algorithm is introduced to obtain the semantic weight of the entity by introducing correlation coefficient and information entropy evaluation and utilizing context information.

4. The perioperative doctor-patient collaborative management method according to claim 3 is characterized in that: The S1 specifically includes: Integrate semantic weights into verified structured medical data and transform them into usable structured medical data.

5. The perioperative doctor-patient collaborative management method according to claim 1, characterized in that: The S2 specifically includes: Perform feature extraction, feature derivation and feature selection on the retrieved structured medical data, select features related to disease risk assessment to identify the feature set with the most predictive value; apply the trained support vector machine model to the feature set obtained based on the structured medical data, assess the patient's health status and predict the risk of disease or disease development to obtain prediction results; and based on the prediction results, obtain the main factors affecting the risk and recommended monitoring or intervention measures; and finally generate a risk assessment report.

6. The perioperative doctor-patient collaborative management method according to claim 5, characterized in that: The S2 specifically includes: During the feature selection process, a feature selection engine is designed to optimize feature selection.

7. The perioperative doctor-patient collaborative management method according to claim 1, characterized in that: The S3 specifically includes: Integrate the risk assessment report into the decision support system, use the treatment preferences and clinical guidelines entered by the doctor to evaluate and rank different treatment options, obtain a treatment plan, and get personalized treatment recommendations based on the treatment plan; at the same time, adjust the treatment plan in combination with the communication platform to obtain the best treatment plan.

8. A perioperative doctor-patient collaborative management system, applied to the perioperative doctor-patient collaborative management method according to claim 1, characterized in that: Includes the following parts: Data collection module, central database module, authority management module, real-time interaction and communication module, risk assessment and management module, decision support module, report and feedback module; The data collection module is used to collect all necessary information of the patient, and pre-process and structure all necessary information to obtain structured medical data; Transfer structured medical data to a central database module; Central database module, which stores and manages structured medical data and real-time communication records between doctors and patients; The authority management module, based on the login request of doctors and patients, calls the structured medical data in the central database module, manages and verifies the access rights of doctors and patients, obtains the verified login request, and sends the verified login request to the real-time interaction and communication module and the risk assessment and management module; The real-time interaction and communication module, based on the verified login request, retrieves the structured medical data provided by the central database module, conducts real-time communication between doctors and patients through the communication platform, obtains the real-time communication records between doctors and patients, and stores them back in the central database module; at the same time, the real-time communication between doctors and patients is sent to the decision support module; The risk assessment and management module performs real-time and predictive analysis on the structured medical data in the central database module based on the verified login request to obtain a risk assessment report; Send risk assessment report to decision support module; The decision support module provides decision support based on risk assessment reports and real-time communication between doctors and patients, helps doctors develop treatment plans, and provides feedback to doctors and patients; the treatment plans are sent to the reporting and feedback module; The reporting and feedback module combines treatment plans, surgical results and patient satisfaction surveys to generate comprehensive reports for hospital management and patients to review.

Images