Intelligent data analysis and feedback method and system for OAB symptom management

Abstract

The invention provides an intelligent data analysis and feedback method for OAB symptom management. The method comprises the steps that feature information of a patient of a patient terminal is acquired; classifying the patients based on the feature information, and dividing the patients into different management levels; according to the classification result and the feature information of the patient, generating a personalized task plan and a periodic treatment course scheme, and sending the task plan and the periodic treatment course scheme to the patient terminal unit; the daily state information submitted by the patient through the patient terminal unit is received and stored, and the daily state information is fed back to the doctor terminal unit; and after the period course of treatment is finished, generating a corresponding treatment result report, and sending the treatment result report to the patient terminal unit and the doctor terminal unit. According to the method, through the personalized treatment course scheme and real-time state feedback, the accuracy and flexibility of OAB treatment are enhanced, a periodic treatment report provides comprehensive evaluation, and the interaction and treatment effect between a doctor and a patient is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent medical and health management technology, and in particular to an intelligent data analysis and feedback method and system for OAB disease management. Background Art

[0002] Overactive bladder (OAB) is a clinical syndrome characterized by symptoms such as urgency, frequency, and nocturia, which seriously affects the patient's quality of life and mental health. The diagnosis of OAB is usually based on clinical symptoms and patient self-reports, but due to the lack of effective quantitative evaluation methods, there are certain difficulties in the clinical evaluation of OAB symptoms. Currently, the treatment of OAB mainly includes drug therapy, physical therapy, and behavioral intervention. However, these treatment options often have certain limitations, especially in terms of patients' personalized needs and treatment compliance.

[0003] According to current clinical guidelines, behavioral intervention is recommended as the first-line treatment for OAB. Behavioral intervention includes scheduled urination, bladder training, bladder function reconstruction, lifestyle adjustment, etc., aiming to improve symptoms through patient self-management. However, although behavioral intervention has a certain efficacy in relieving OAB symptoms, traditional behavioral intervention methods rely on the active participation and self-supervision of patients, lack professional real-time guidance and personalized adjustments, and often lead to poor treatment compliance and unsustainable effects.

[0004] In order to solve the above problems, some urinary incontinence treatment devices in the prior art are highly dependent on the medical experience of the operator during operation, resulting in insufficient pertinence of the treatment plan and poor practicality. In addition, the existing treatment methods cannot effectively supervise and guide patients during the treatment process, resulting in poor patient compliance and difficulty in sustaining behavioral intervention treatment, which ultimately affects the treatment effect. These deficiencies in the prior art limit the effect of treatment and make it difficult to achieve accurate treatment, personalized and long-term management of overactive bladder. Summary of the invention

[0005] The purpose of this application is to provide an intelligent data analysis and feedback method for OAB management, the method comprising:

[0006] Obtain patient characteristic information;

[0007] Based on the characteristic information, the patients are classified into different management levels;

[0008] Generate a personalized task plan and a periodic treatment plan based on the patient's classification results and characteristic information, and send the task plan and the periodic treatment plan to the patient terminal unit;

[0009] receiving and storing daily status information submitted by the patient through the patient terminal unit, and feeding back the daily status information to the doctor terminal unit;

[0010] After the treatment cycle is completed, a corresponding treatment result report is generated and sent to the patient terminal unit and the doctor terminal unit.

[0011] Optionally, the specific steps of obtaining characteristic information of a patient at the patient terminal include:

[0012] Collect the patient's physiological parameter data and clinical data through treatment equipment;

[0013] Preprocessing the physiological parameter data and clinical data;

[0014] Perform feature extraction on the preprocessed physiological parameter data and clinical data to obtain physiological parameter features and clinical data features;

[0015] The physiological parameter characteristics and clinical data characteristics are integrated to obtain comprehensive characteristic information of the patient.

[0016] Optionally, the specific steps of classifying the patients based on the characteristic information and dividing the patients into different management levels include:

[0017] Build regression models through machine learning algorithms;

[0018] The regression model is trained using OABSS score samples to obtain an optimized regression model;

[0019] Inputting the patient's characteristic information into the optimized regression model to calculate the predicted patient's OABSS score;

[0020] Patients are classified based on their OABSS scores and divided into different management levels.

[0021] Optionally, the method further comprises:

[0022] Performing algorithm optimization on the regression model and adjusting parameters of the algorithm;

[0023] An independent test data set is used to verify the algorithm, and the optimized algorithm is evaluated through the verification results.

[0024] Optionally, the specific steps of generating a personalized task plan and a periodic treatment plan according to the classification result and characteristic information of the patient, and sending the task plan and the periodic treatment plan to the patient terminal unit include:

[0025] According to the classification result of the patient, a basic plan template of a corresponding level is selected from a preset basic plan template library;

[0026] Generate a personalized task plan based on the basic program template of the corresponding level and in combination with the patient's characteristic information;

[0027] A periodic treatment plan is generated according to the personalized task plan, and the personalized task plan and the periodic treatment plan are sent to the patient terminal unit.

[0028] Optionally, the method further comprises generating learning material information corresponding to the periodic treatment regimen, and sending the learning material information to a patient terminal unit.

[0029] Optionally, the method further comprises generating a treatment progress chart corresponding to the periodic treatment regimen based on the daily status information, and sending the treatment progress chart to a patient terminal unit.

[0030] Optionally, the method further comprises:

[0031] Testing the patient's completion status according to the daily task completion time points in the cyclical treatment plan;

[0032] When it is detected that the patient has not completed the task, a reminder message is automatically generated and sent to the patient terminal unit.

[0033] Optionally, the method further comprises:

[0034] Acquire the real-time remote online communication information of the patient terminal unit, and send the real-time remote online communication information of the patient terminal unit to the doctor terminal unit, and receive feedback information from the doctor terminal unit, and send the feedback information to the patient terminal unit; or,

[0035] Acquire the real-time remote online communication information of the doctor terminal unit, send the real-time remote online communication information of the doctor terminal unit to the patient terminal unit, receive feedback information from the patient terminal unit, and send the feedback information to the doctor terminal unit.

[0036] In a second aspect, the present application further provides an intelligent data analysis and feedback system for OAB management using the above method, the system comprising:

[0037] The backend service unit is configured to obtain characteristic information of the patient; classify the patient based on the characteristic information and divide the patient into different management levels; generate a personalized task plan and a periodic treatment plan according to the classification result and characteristic information of the patient, and send the task plan and the periodic treatment plan to the patient terminal unit; receive and store the daily status information submitted by the patient through the patient terminal unit, and feed back the daily status information to the doctor terminal unit; generate a corresponding treatment result report after the periodic treatment ends, and send the treatment result report to the patient terminal unit and the doctor terminal unit;

[0038] A patient terminal unit configured to receive the periodic treatment plan, submit daily status information of the patient, and send the daily status information to a background service unit;

[0039] A doctor terminal unit is configured to receive the daily status information and task completion progress, provide feedback information and send the feedback information to the patient terminal unit through a background service unit;

[0040] The treatment device is connected to the patient terminal unit data, receives the periodic treatment plan and treats the patient.

[0041] The intelligent data analysis and feedback method for OAB management provided in this application, by comprehensively collecting the patient's physiological data, clinical data and daily status information, performs personalized classification of patients based on machine learning algorithms and generates targeted treatment plans, which effectively improves the treatment effect of OAB. Through intelligent analysis and personalized task plan generation, treatment plans can be tailored for different patients according to their characteristics and management levels, improving the accuracy and personalization of treatment, while overcoming the problem of over-reliance on doctor's experience in traditional treatment and improving patients' treatment compliance. Therefore, the technical solution of this application can not only achieve accurate treatment of OAB, but also improve the long-term treatment effect of patients through continuous task management and feedback.

[0042] Furthermore, this application ensures the accuracy of treatment plan generation through regression model optimization and algorithm verification, and further improves the reliability of the model through cross-validation and verification of independent data sets. By generating personalized task plans and periodic treatment plans, and coordinating the delivery of learning materials and progress charts, the patient's sense of participation and treatment motivation are enhanced. At the same time, this application combines a real-time feedback mechanism to detect and remind patients to complete tasks in a timely manner, thereby ensuring the effectiveness of the treatment process. Through real-time remote online communication functions, the flow of information between patients and doctors is smoother, which improves the interactivity of the treatment process and the patient's treatment satisfaction.

[0043] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic flow chart of an intelligent data analysis and feedback method for OAB disease management according to an embodiment of the present application is shown;

[0045] Figure 2 Shows Figure 1 A schematic flow chart of a method for obtaining characteristic information of a patient in step S110;

[0046] Figure 3 Shows Figure 1 A schematic flow chart of a method for obtaining characteristic information of a patient in step S120;

[0047] Figure 4 An intelligent data analysis and feedback system for OAB disease management according to one embodiment of the present application is shown. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only some structures related to the present application are shown in the accompanying drawings, rather than all structures. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0049] The terms "including" and "having" and any variations thereof in this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0050] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0051] Figure 1FIG. 1 is a schematic flow chart of an intelligent data analysis and feedback method for OAB management according to an embodiment of the present application. Figure 1 As shown, the intelligent data analysis and feedback method for OAB management includes the following steps:

[0052] Step S110, obtaining characteristic information of the patient.

[0053] By collecting the patient's physiological data, clinical data, living habits and other information, we can build a comprehensive profile of the patient. By comprehensively collecting the patient's multi-dimensional characteristic information, we can provide sufficient data support for the subsequent formulation of personalized treatment plans, improve the accuracy and personalization of the plans. The patient's health data is integrated into a unified information source to avoid information silos and provide a strong basis for subsequent steps.

[0054] Step S120: classify the patients based on the characteristic information and divide the patients into different management levels.

[0055] The system uses the collected characteristic information to classify patients and divide them into different management levels. For example, mild OAB, moderate OAB and severe OAB. Through classification based on patient characteristics, the severity of each patient's condition can be accurately assessed, thereby providing a basis for subsequent personalized treatment plans, so that treatment plans can be more targeted and designed according to individual differences of patients, avoiding "one-size-fits-all" treatment methods. The classification results help to distinguish the differences in treatment plans, making them more targeted and effect-oriented.

[0056] Step S130, generating a personalized task plan and a periodic treatment plan according to the classification result and characteristic information of the patient, and sending the task plan and the periodic treatment plan to the patient terminal unit.

[0057] According to patients with different management levels, the most suitable treatment task plan (such as behavioral intervention tasks, drug use guidance, lifestyle adjustments, etc.) is selected and adjusted according to the patient's personalized needs. At the same time, a corresponding cycle treatment plan is generated based on the patient's symptom manifestations and management level. The cycle treatment plan will clearly specify the specific steps, time nodes, drug use plans, behavioral intervention measures and other contents of the treatment. The cycle treatment plan usually covers a certain time period, such as 10 days, 15 days or one month, to ensure the continuity and systematic nature of the treatment. By sending the generated personalized task plan and cycle treatment plan to the patient terminal unit, it is ensured that the patient can perform the tasks in a timely and accurate manner and record the treatment process. Personalized task plans and cycle treatment plans can improve the targeted treatment and ensure that patients get the best results during the treatment process.

[0058] Step S140, receiving and storing the daily status information submitted by the patient through the patient terminal unit, and feeding back the daily status information to the doctor terminal unit.

[0059] Patients use the patient terminal to record daily symptom changes, task completion, and any discomfort or problems during treatment. This information can intuitively reflect the patient's treatment effect and compliance with the treatment plan. Daily status information will be automatically stored in the system background service unit and sent to the doctor terminal unit synchronously to ensure that the doctor obtains the patient's treatment progress and feedback data in real time. After receiving the patient's status information, the doctor can conduct remote intervention, adjust the treatment plan, or give feedback guidance in a timely manner to ensure that the treatment is sustained and effective. This step can provide real-time and dynamic data feedback, allowing doctors to fully and accurately understand the patient's treatment progress, detect problems early, and adjust the plan. At the same time, it enhances the interaction between doctors and patients, improves patients' treatment compliance, and ensures the continuity and effectiveness of treatment.

[0060] Step S150, after the treatment cycle is completed, a corresponding treatment result report is generated and sent to the patient terminal unit and the doctor terminal unit.

[0061] The system generates a detailed treatment result report based on the patient's records during the treatment process (such as symptom changes, task completion, OABSS scores, etc.), including treatment effects, treatment course completion, symptom change trends, etc. The treatment result report is sent to the patient and doctor terminals through the system, which is convenient for doctors to evaluate the treatment effect, adjust the subsequent treatment plan, and let patients know their treatment progress. Doctors can evaluate the treatment effect and decide whether to adjust the treatment plan or continue a certain treatment based on the feedback from the treatment result report. The generated treatment result report provides an objective and comprehensive evaluation of the treatment effect, which helps doctors formulate the next treatment plan. The transparency and sharing mechanism of the report enhances patients' trust in treatment, improves patients' treatment participation, and promotes treatment compliance.

[0062] According to the above embodiments, by comprehensively collecting the patient's physiological data, clinical data, and daily status information, the patient is personalized and classified based on the machine learning algorithm and a targeted treatment plan is generated, which effectively improves the treatment effect of OAB disease. Through intelligent analysis and personalized task plan generation, treatment plans can be tailored for different patients according to their characteristics and management levels, improving the accuracy and personalization of treatment, while overcoming the problem of over-reliance on doctors' experience in traditional treatments and improving patients' treatment compliance. Therefore, the technical solution of the present application can not only achieve accurate treatment of OAB disease, but also improve the long-term treatment effect of patients through continuous task management and feedback.

[0063] Figure 2 Shows Figure 1 Schematic flow chart of the method for obtaining the characteristic information of the patient in step S110. Figure 2 As shown, step S110 includes:

[0064] Step S111, collecting the patient's physiological parameter data and clinical data through the treatment equipment.

[0065] Physiological parameter data and clinical data related to patients are collected in real time through treatment equipment (such as smart wearable devices, monitoring equipment or other medical instruments). For example, physiological parameter data may include bladder pressure data, urination frequency data, nocturia frequency data, etc., while clinical data include the patient's age, gender, medical history (such as diabetes, hypertension, etc.), medication use, etc. These data provide the basis for subsequent personalized analysis and treatment. By collecting comprehensive physiological and clinical data in real time, accurate and comprehensive information on the patient's health status can be ensured, providing data support for subsequent treatment plan customization and disease management. Collecting this data helps to provide personalized and precise diagnosis and treatment basis for the patient's OAB disease management, avoiding the limitations of traditional treatment methods that rely on a single indicator or experience.

[0066] Step S112, preprocessing the physiological parameter data and clinical data.

[0067] The collected physiological parameters and clinical data need to be cleaned, denoised and standardized, including removing outliers, filling missing data, eliminating noise caused by equipment errors, etc. For example, signal processing technology (such as filtering algorithms) can be used to remove sensor noise, and time series analysis methods can be used to identify and eliminate abnormal urination events.

[0068] The purpose of data standardization is to ensure the consistency of data from different sources and measurement units so that it can be effectively compared in subsequent analysis. Data preprocessing can ensure data quality and improve the accuracy and reliability of analysis results. Removing outliers and noise can effectively eliminate the interference of bad data on model training, thereby improving the accuracy of subsequent feature extraction and model prediction. Standardized data helps to effectively combine different data types (such as physiological and clinical data) to avoid errors caused by inconsistent dimensions.

[0069] Step S113, extracting features from the preprocessed physiological parameter data and clinical data to obtain physiological parameter features and clinical data features.

[0070] In this step, key features are extracted from the preprocessed data. For physiological parameter data, valuable features for OAB symptom prediction and treatment plan formulation are extracted from the preprocessed physiological data through statistical analysis methods (such as calculating mean, standard deviation, peak, etc.) and signal processing techniques (such as spectrum analysis, wavelet transform, etc.). For example, statistical features such as average value, fluctuation range, and change trend are extracted from time series data of urination frequency and bladder pressure. For clinical data, feature engineering techniques such as unique hot encoding and feature selection can be used to extract features related to OAB. For example, features such as the presence or absence of a specific medical history and the effect of drug use on bladder function. These features will provide core data for subsequent model training and patient classification.

[0071] Through precise feature extraction, raw data can be converted into efficient information that can be used for machine learning and algorithm analysis, so that the data can reveal potential health trends and disease patterns after quantification. Feature extraction also helps to eliminate irrelevant or redundant information, improving the efficiency and prediction accuracy of the algorithm model. In addition, the extraction of clinical data and physiological data features for OAB disease helps to identify the personalized needs of different patient groups and further optimize treatment plans.

[0072] Step S114, integrating the physiological parameter characteristics and the clinical data characteristics to obtain comprehensive characteristic information of the patient.

[0073] The feature information extracted from physiological parameters and clinical data is fused to form comprehensive patient feature information. Common methods include weighted summation, feature splicing and other technologies, through which data from different sources can be organically combined to form a complete feature vector for subsequent model training and analysis. Data fusion enables physiological and clinical features to be comprehensively evaluated at the same level, thereby improving the richness and comprehensiveness of the features. Comprehensive feature information can more comprehensively reflect the patient's health status and help accurately assess the patient's OAB symptoms, course of disease and treatment response. Through feature fusion, the predictive ability of the algorithm can be improved, personalized health management and treatment plan formulation can be achieved, and information loss caused by a single data source can be avoided.

[0074] The above steps S111 to S114 can form high-quality, multi-dimensional patient feature information through system acquisition, preprocessing, feature extraction and feature fusion. This information provides reliable data support for the subsequent OAB disease intelligent management system, ensuring the accurate formulation and personalized adjustment of the treatment plan, thereby improving the treatment effect and patient compliance.

[0075] Figure 3 Shows Figure 1 Schematic flow chart of the method for obtaining characteristic information of a patient in step S120. Figure 3 As shown, step S120 includes:

[0076] Step S121, establishing a regression model through a machine learning algorithm.

[0077] A regression model was built using machine learning methods to predict the patient's OABSS score, which is used to assess the severity of OAB symptoms. The model was built based on historical data and clinical cases, including the patient's physiological characteristics, clinical characteristics, and other relevant health information. By selecting an appropriate machine learning algorithm, the regression model was ensured to have high predictive and generalization capabilities.

[0078] In some embodiments, the above machine learning method can be linear regression, random forest regression, support vector regression, etc.

[0079] The regression model established through machine learning algorithms can effectively capture the complex relationship between patient characteristics and OABSS scores, thereby providing more accurate predictions. Compared with traditional manual scoring methods, machine learning models can avoid human errors, learn based on big data, and improve the accuracy and stability of predictions.

[0080] Step S122, training the regression model using the OABSS score samples to obtain an optimized regression model.

[0081] The regression model is trained with a large amount of patient data with known OABSS scores. The training data includes the patient's physiological characteristics, clinical data, and the OABSS scores of these patients. The regression model gradually optimizes its parameters by learning the relationship between these data. In addition, by using cross-validation or other optimization algorithms, it is ensured that the model can still have high accuracy and generalization ability on new and unseen patient data. By training the regression model with OABSS score samples, the model can effectively learn and optimize its ability to predict OABSS scores. The trained regression model has strong adaptability and can quickly adjust and make accurate predictions in large-scale patient data. The optimized model not only improves the accuracy of the prediction, but also reduces the errors that may be caused by differences in experience, ensuring a more objective and consistent assessment of OAB patients.

[0082] Step S123, inputting the patient's characteristic information into the optimized regression model to calculate the predicted patient's OABSS score.

[0083] In this step, the patient's characteristic information (including physiological parameters, clinical data, etc.) will be input into the optimized regression model. The model will calculate and output the patient's predicted OABSS score based on the input characteristic data. The score reflects the severity of the patient's overactive bladder (OAB) symptoms and provides a quantitative basis for the subsequent treatment plan. By inputting the patient's characteristic information into the optimized regression model, the OABSS score can be quickly and accurately obtained, avoiding the subjective bias in traditional evaluation methods. This step makes the evaluation process more objective and efficient, and provides a scientific and quantitative basis for the subsequent patient classification and formulation of personalized treatment plans.

[0084] Step S124, classifying the patients based on their OABSS scores and dividing them into different management levels.

[0085] According to the calculated OABSS score, patients will be divided into different management levels. According to the preset grading standards, such as: OABSS scores less than 5 points are mild, 5 to 11 points are moderate, and 12 points and above are severe. Patients at each level will develop corresponding treatment plans according to the severity of their symptoms. Mild patients may take behavioral interventions, while severe patients may need comprehensive drug therapy, physical therapy and other means. Through the grading of OABSS scores, a personalized treatment plan that best suits their condition can be developed for each patient. Grading not only enables patients to receive more targeted treatment, but also effectively improves the efficiency and effectiveness of treatment. The implementation of this step provides patients with OAB with a precise and scientific treatment path, avoiding overtreatment or undertreatment. At the same time, through accurate grading, doctors can have a clearer understanding of the patient's condition, optimize resource allocation, and improve the overall effect of treatment.

[0086] Through the application of machine learning algorithms and the calculation and grading of OABSS scores, the above steps S121 to S124 can accurately assess the severity of the patient's OAB symptoms and develop a personalized treatment plan for them. This process not only improves the accuracy of predictions and reduces the limitations of relying on doctors' experience, but also makes treatment more scientific, systematic and efficient through hierarchical management, ultimately improving the treatment effect and compliance of patients.

[0087] In some embodiments, step S120 further includes the following steps:

[0088] Step S125, optimizing the regression model algorithm and adjusting the algorithm parameters.

[0089] In this step, techniques such as cross-validation and regularization are used to optimize the performance of the regression model. Cross-validation avoids overfitting and ensures the generalization ability of the model by dividing the data into multiple subsets and taking turns to use one subset for training and the other subsets for validation. Regularization methods (such as L2 regularization) help to suppress the complexity of the model and reduce the risk of overfitting. By adjusting the hyperparameters of the model (such as the learning rate in the regression model, the number of trees in the random forest, etc.), the training process of the model can be optimized to improve its predictive ability and stability on unknown data. The optimization process may include adjusting multiple hyperparameters and using methods such as grid search or random search to determine the best parameter combination.

[0090] By applying optimization techniques such as cross-validation and regularization, the model can achieve better generalization performance on different data sets, thereby improving accuracy and stability in practical applications. The optimized regression model avoids overfitting, improves the prediction accuracy of OABSS scores, and ensures that the model can adapt to the diverse data characteristics of different patients. After further adjusting the hyperparameters, the model has achieved significant improvements in accuracy and stability, which helps to improve the formulation of personalized treatment plans for OAB patients and enhances the targetedness and effectiveness of treatment.

[0091] Step S126, using an independent test data set to verify the algorithm, and evaluating the optimized algorithm based on the verification results.

[0092] In this step, an independent test dataset is used to verify and evaluate the optimized regression model. The test dataset should be completely independent of the training dataset to ensure that the verification results can truly reflect the performance of the model in actual applications. During the verification process, the prediction ability of the model is evaluated by calculating multiple performance indicators (such as accuracy, recall, F1 value, etc.). The optimized model can also be compared with the traditional OABSS score calculation method to analyze whether the optimized model has significant improvements in accuracy, robustness, computational efficiency, etc.

[0093] Using an independent test data set for verification and evaluation can ensure that the optimized regression model will not be affected by overfitting and has good generalization ability. By comparing the traditional OABSS score calculation method, it is verified whether the new model has advantages in prediction accuracy, efficiency and practicality. If the optimized model can significantly improve the prediction accuracy and real-time performance of the OABSS score, it can provide patients with more accurate treatment guidance, thereby improving treatment effects and patient compliance. At the same time, this also provides a reliable basis and confidence for the clinical application of the model, ensuring that it can play a role in real-world medical environments.

[0094] Figure 3 Shows Figure 1Schematic flow chart of the method for obtaining the characteristic information of the patient in step S130. Figure 3 As shown, step S130 includes:

[0095] Step S131 : selecting a basic plan template of a corresponding level from a preset basic plan template library according to the classification result of the patient.

[0096] In this step, according to the classification result of the patient in step S120 (such as mild, moderate or severe), a basic program template suitable for the management level is selected from the preset basic program template library. Each management level corresponds to a basic program template, which covers the treatment and intervention content usually required by patients at this level. The core of this step is to accurately match the treatment plan template based on the patient's OABSS score and classification results, providing a framework and basis for the subsequent generation of personalized task plans.

[0097] By accurately selecting the basic plan template according to the patient's management level, it can ensure that the treatment content of the selected plan matches the severity of the patient's condition, improving the pertinence and rationality of the treatment. In this process, the preset plan template can greatly reduce the workload of doctors and reduce human judgment errors, thereby providing patients with a more standardized and systematic treatment framework to ensure the effectiveness and consistency of the treatment plan.

[0098] Step S132, generating a personalized task plan based on the basic program template of the corresponding level and combining the patient's characteristic information.

[0099] In this step, the task plan is personalized according to the selected basic program template and the patient's characteristic information (such as age, medical history, living habits, etc.). This means that although all patients start treatment based on the same basic program template, specific tasks and intervention content (such as drug dosage, specific details of behavioral intervention, monitoring frequency, etc.) will be customized according to the patient's characteristics and needs. The personalized task plan takes into account the patient's specific situation to maximize the treatment effect and patient treatment compliance. By generating a task plan based on the patient's personalized characteristics, the adaptability and flexibility of the treatment plan can be improved to ensure that the treatment content is more in line with the actual needs of each patient. This personalized adjustment can significantly improve the patient's treatment compliance, because the patient will feel that the treatment plan is more in line with their physical condition and living habits, improving the effectiveness of the treatment and patient satisfaction.

[0100] Step S133, generating a periodic treatment plan according to the personalized task plan, and sending the personalized task plan and the periodic treatment plan to the patient terminal unit.

[0101] This step further develops a detailed cycle treatment plan based on the generated personalized task plan. The cycle treatment plan includes specific goals, tasks, time nodes and evaluation criteria for each treatment cycle to ensure that the treatment process has clear guidance and phased goals. The generated cycle treatment plan will be sent to the patient terminal unit (such as a mobile phone APP or other medical device terminal). Patients can perform treatment tasks on time according to the plan, and the system will also track and provide feedback on their treatment progress in real time.

[0102] By generating a detailed cycle treatment plan, a clear treatment roadmap can be provided for patients, ensuring that patients can complete each treatment step by step and on time, which helps improve patients' treatment compliance and self-management ability. In addition, the formulation of the cycle treatment plan is phased and traceable, which can help patients and doctors evaluate the treatment effect in a timely manner and make necessary adjustments. This standardized and standardized treatment process management not only improves treatment efficiency, but also significantly enhances patients' sense of trust and participation, and promotes the maximization of treatment effects.

[0103] In some embodiments, the intelligent data analysis and feedback method for OAB management also includes generating learning material information corresponding to the periodic treatment plan, and sending the learning material information to the patient terminal unit.

[0104] According to the cycle treatment plan, relevant learning materials are generated. These materials may include treatment precautions, behavioral intervention techniques, healthy living suggestions, etc., aiming to help patients better understand and cooperate with the treatment. These learning materials are sent to the patient terminal unit, that is, the patient's terminal device, such as a mobile phone or tablet computer, so that the patient can view and refer to it at any time. Through the learning materials, patients can better understand the importance and specific steps of treatment, so that patients can better cooperate with the treatment, maximize the treatment effect, and improve compliance.

[0105] In some embodiments, the intelligent data analysis and feedback method for OAB management further includes generating a treatment progress chart corresponding to the periodic treatment plan based on the daily status information, and sending the treatment progress chart to the patient terminal unit.

[0106] The backend service unit generates an intuitive treatment progress chart based on the post-treatment status information submitted by the patient every day, showing the progress of the treatment process, such as symptom improvement trends, treatment compliance, etc. The progress chart is sent to the patient's terminal device, allowing the patient to check his or her treatment progress at any time. By viewing the progress chart, the patient can clearly see the treatment effect, enhance confidence and motivation. At the same time, the patient can also adjust his or her behavior in time according to the information in the progress chart to avoid deviations or misunderstandings.

[0107] In some embodiments, the intelligent data analysis and feedback method for OAB management further includes:

[0108] The patient's completion status is tested based on the daily task completion time points in the cyclical treatment plan.

[0109] The background service unit automatically detects whether the patient is receiving treatment within the specified time according to the daily treatment time points in the preset cycle treatment plan, that is, whether the signal of the patient receiving treatment is received at this time point. The background service unit connects and communicates with the patient's treatment equipment through the patient terminal unit, and can monitor the patient's treatment equipment in real time, including checking whether the patient has started the treatment equipment and whether the prescribed treatment tasks have been completed on time. Whenever the patient starts or ends treatment, the treatment equipment will upload the treatment data to the background service unit through the patient terminal device. The treatment data includes information such as the start time of treatment, treatment duration, and completion status. Through automatic detection, it is possible to timely find out whether the patient is receiving treatment according to the requirements of the plan, avoiding treatment interruptions due to negligence or forgetfulness. Maintaining the continuity and regularity of treatment is a very important part of OAB treatment. Timely detection helps ensure that treatment is carried out as planned, thereby improving the overall treatment effect.

[0110] When it is detected that the patient has not completed the task, a reminder message is automatically generated and sent to the patient terminal unit.

[0111] When the backend service unit detects that the patient has not received treatment within the prescribed time, it will automatically generate a reminder message to remind the patient to receive treatment as soon as possible. The backend service unit sends the generated reminder message to the patient terminal unit to ensure that the patient can receive the reminder in time. Timely reminders help patients avoid incomplete treatment due to forgetfulness or delay, help maintain the continuity of treatment, ensure the maximum efficacy, and thus improve treatment compliance.

[0112] In some embodiments, the intelligent data analysis and feedback method for OAB management further includes: obtaining real-time remote online communication information of the patient terminal unit, sending the real-time remote online communication information of the patient terminal unit to the doctor terminal unit, receiving feedback information from the doctor terminal unit, and sending the feedback information to the patient terminal unit. Or obtaining real-time remote online communication information of the doctor terminal unit, sending the real-time remote online communication information of the doctor terminal unit to the patient terminal unit, receiving feedback information from the patient terminal unit, and sending the feedback information to the doctor terminal unit.

[0113] When patients encounter problems during treatment, they can initiate real-time remote online communication through the patient terminal unit, make video calls or chats to discuss treatment progress, adjust plans or solve questions. At the same time, when doctors detect problems during the treatment of patients, they can initiate real-time remote online communication through the doctor terminal unit and make video calls or chats with patients. The patient terminal unit and the doctor terminal unit establish real-time communication through the background service unit, transmit the real-time communication information to the other party's terminal device, and realize instant communication. The real-time communication function enhances the interaction between doctors and patients, making the treatment process more flexible and personalized.

[0114] In some embodiments, the intelligent data analysis and feedback method for OAB management further includes:

[0115] Generate a personalized follow-up treatment plan based on the treatment result report and doctor feedback, and send the follow-up treatment plan to the patient terminal unit.

[0116] Combined with the patient's treatment outcome report and the doctor's professional feedback, the effectiveness of the current treatment plan is analyzed. The treatment outcome report includes treatment effect evaluation, symptom changes, etc. According to the analysis results, a personalized follow-up treatment plan is formulated to ensure that patients can get the best treatment measures at different treatment stages. By continuously adjusting and optimizing the treatment plan, changes in OAB symptoms can be better responded to and the effect of long-term treatment can be improved.

[0117] Figure 4 FIG. 2 shows an intelligent data analysis and feedback system for OAB management according to an embodiment of the present application. Figure 4 As shown, the intelligent data analysis and feedback system for OAB management includes:

[0118] The backend service unit 102 is configured to obtain characteristic information of the patient; classify the patient based on the characteristic information and divide the patient into different management levels; generate a personalized task plan and a periodic treatment plan according to the classification result and characteristic information of the patient, and send the task plan and the periodic treatment plan to the patient terminal unit 103; receive and store the daily status information submitted by the patient through the patient terminal unit 103, and feed back the daily status information to the doctor terminal unit 101; after the periodic treatment is completed, generate a corresponding treatment result report, and send the treatment result report to the patient terminal unit 103 and the doctor terminal unit 101;

[0119] The patient terminal unit 103 is configured to receive the periodic treatment plan, submit the patient's daily status information, and send the daily status information to the background service unit 102;

[0120] The doctor terminal unit 101 is configured to receive daily status information and task completion progress, provide feedback information and send the feedback information to the patient terminal unit 103 via the background service unit 102;

[0121] The treatment device 104 is data-connected to the patient terminal unit 103, receives the periodic treatment plan and treats the patient.

[0122] In the above-mentioned intelligent data analysis and feedback system for OAB disease management, the specific functions of the doctor terminal unit 101, the background service unit 102 and the patient terminal unit 103 refer to the relevant contents of the embodiments in the above-mentioned method, and will not be described in detail here.

[0123] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0124] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An intelligent data analysis and feedback method for OAB management, characterized in that: The method comprises: Obtain characteristic information of the patient at the patient terminal; Based on the characteristic information, the patients are classified into different management levels; Generate a personalized task plan and a periodic treatment plan based on the patient's classification results and characteristic information, and send the task plan and the periodic treatment plan to the patient terminal unit; receiving and storing daily status information submitted by the patient through the patient terminal unit, and feeding back the daily status information to the doctor terminal unit; After the treatment cycle is completed, a corresponding treatment result report is generated and sent to the patient terminal unit and the doctor terminal unit.

2. The intelligent data analysis and feedback method for OAB management according to claim 1, characterized in that: The specific steps of obtaining the characteristic information of the patient at the patient terminal include: Collect the patient's physiological parameter data and clinical data through treatment equipment; Preprocessing the physiological parameter data and clinical data; Perform feature extraction on the preprocessed physiological parameter data and clinical data to obtain physiological parameter features and clinical data features; The physiological parameter characteristics and clinical data characteristics are integrated to obtain comprehensive characteristic information of the patient.

3. The intelligent data analysis and feedback method for OAB management according to claim 1, characterized in that: The specific steps of classifying the patients based on the characteristic information and dividing the patients into different management levels include: Build regression models through machine learning algorithms; The regression model is trained using OABSS score samples to obtain an optimized regression model; Inputting the patient's characteristic information into the optimized regression model to calculate the predicted patient's OABSS score; Patients are classified based on their OABSS scores and divided into different management levels.

4. The intelligent data analysis and feedback method for OAB management according to claim 3, characterized in that: The method further comprises: Performing algorithm optimization on the regression model and adjusting parameters of the algorithm; An independent test data set is used to verify the algorithm, and the optimized algorithm is evaluated through the verification results.

5. The intelligent data analysis and feedback method for OAB management according to claim 1, characterized in that: The specific steps of generating a personalized task plan and a periodic treatment plan according to the classification results and characteristic information of the patient, and sending the task plan and the periodic treatment plan to the patient terminal unit include: According to the classification result of the patient, a basic plan template of a corresponding level is selected from a preset basic plan template library; Generate a personalized task plan based on the basic program template of the corresponding level and in combination with the patient's characteristic information; A periodic treatment plan is generated according to the personalized task plan, and the personalized task plan and the periodic treatment plan are sent to the patient terminal unit.

6. The intelligent data analysis and feedback method for OAB management according to claim 1, characterized in that: The method also includes generating learning material information corresponding to the periodic treatment plan, and sending the learning material information to the patient terminal unit.

7. The intelligent data analysis and feedback method for OAB management according to claim 1, characterized in that: The method further includes generating a treatment progress graph corresponding to the periodic treatment regimen based on the daily status information, and sending the treatment progress graph to a patient terminal unit.

8. The intelligent data analysis and feedback method for OAB management according to claim 1, characterized in that: The method further comprises: Testing the patient's completion status according to the daily task completion time points in the cyclical treatment plan; When it is detected that the patient has not completed the task, a reminder message is automatically generated and sent to the patient terminal unit.

9. The intelligent data analysis and feedback method for OAB management according to claim 1, characterized in that: The method further comprises: Acquire the real-time remote online communication information of the patient terminal unit, and send the real-time remote online communication information of the patient terminal unit to the doctor terminal unit, and receive feedback information from the doctor terminal unit, and send the feedback information to the patient terminal unit; or, Acquire the real-time remote online communication information of the doctor terminal unit, send the real-time remote online communication information of the doctor terminal unit to the patient terminal unit, receive feedback information from the patient terminal unit, and send the feedback information to the doctor terminal unit.

10. An intelligent data analysis and feedback system for OAB management using the method according to any one of claims 1 to 9, characterized in that: The system comprises: The backend service unit is configured to obtain characteristic information of the patient; classify the patient based on the characteristic information and divide the patient into different management levels; generate a personalized task plan and a periodic treatment plan according to the classification result and characteristic information of the patient, and send the task plan and the periodic treatment plan to the patient terminal unit; receive and store the daily status information submitted by the patient through the patient terminal unit, and feed back the daily status information to the doctor terminal unit; generate a corresponding treatment result report after the periodic treatment ends, and send the treatment result report to the patient terminal unit and the doctor terminal unit; A patient terminal unit configured to receive the periodic treatment plan, submit daily status information of the patient, and send the daily status information to a background service unit; A doctor terminal unit is configured to receive the daily status information and task completion progress, provide feedback information and send the feedback information to the patient terminal unit through a background service unit; The treatment device is connected to the patient terminal unit data, receives the periodic treatment plan and treats the patient.

Images