A breast cancer risk control system and medium

Abstract

The present application relates to a breast cancer risk control system and a medium. The system includes: at least one memory storing a computer program, and at least one processor configured to implement a breast cancer risk control method when executing the computer program. The specific steps are as follows: training a model using a preset and already trained random forest algorithm, calculating the contribution degree of each feature in the construction of the decision tree and giving a feature importance score, and calculating the weight of each risk factor on the breast cancer risk value according to different feature importance scores; analyzing and determining the breast cancer detection period according to the corresponding relationship between the weight range in which the weight of a specific risk factor on the breast cancer risk value falls, the risk value evaluation range in which the breast cancer risk value falls, and the detection period; forming a patient's breast cancer-related detection time schedule according to the analyzed and determined breast cancer detection period. The present application has the following effects: realizing the precise control of breast cancer risk and improving the prevention and treatment effects.

Description

Technical Field

[0001] The present invention relates to the field of medical health, and in particular, to a breast cancer risk control system and a medium. Background Art

[0002] The pathogenesis of breast cancer is complex and is affected by a variety of factors, including genetic factors, lifestyle, environmental factors, etc. Early detection, diagnosis, and intervention are crucial for improving the cure rate of breast cancer and the survival rate of patients. With the continuous development of technology, the application of digital and intelligent technologies in the medical field is becoming increasingly widespread, providing new ideas and methods for breast cancer risk control.

[0003] Currently, traditional breast cancer detection mainly relies on regular clinical examinations, such as mammography, breast ultrasound, etc.

[0004] Although these examination methods can detect breast lesions to a certain extent, they have limitations. On the one hand, the examination cycle is usually arranged at fixed time intervals, lacking personalized basis, which may lead to the development of the condition of some high-risk patients during the interval between two examinations without being detected in time, or over-examination of low-risk patients, resulting in waste of medical resources. On the other hand, traditional detection methods are difficult to comprehensively consider the impact of various factors in patients' daily lives on breast cancer risk, only focusing on the physiological characteristics of the breast locally, lacking effective integration and utilization of multi-source data, and it is difficult to meet the needs of precision medicine and efficient resource allocation. Summary of the Invention

[0005] In order to achieve precise control of breast cancer risk and improve the prevention and treatment effects, the present application provides a breast cancer risk control system and a medium.

[0006] In a first aspect, the present application provides a breast cancer risk control system, adopting the following technical solution:

[0007] A breast cancer risk control system includes:

[0008] A breast monitoring device;

[0009] At least one processor;

[0010] At least one memory storing a computer program, and at least one processor is configured to implement a breast cancer risk control method when executing the computer program. The specific steps are as follows:

[0011] Obtain patient-related data collected by the breast monitoring device and perform data preprocessing;

[0012] Input the patient-related data after completing data preprocessing into the breast cancer risk value assessment model that has completed training and considers patient personalized data, and output the breast cancer risk value;

[0013] Use the preset and trained random forest algorithm to train the model and calculate the weight of each risk factor on the breast cancer risk value;

[0014] Analyze and determine the breast cancer detection cycle according to the corresponding relationship between the weight range in which the weight of a specific risk factor on the breast cancer risk value falls, the risk value assessment range in which the breast cancer risk value falls, and the detection cycle;

[0015] Form a patient's breast cancer-related detection time schedule according to the analyzed and determined breast cancer detection cycle;

[0016] Form quantization recommendation information according to the corresponding relationship between the weight interval in which the weight of each risk factor on the breast cancer risk value falls and the quantization recommendation, and send the formed quantization recommendation information to the patient's terminal;

[0017] Collect the patient's latest data within the preset cycle range after sending the quantization recommendation, and re-analyze the breast cancer risk value and the weight of each risk factor on the breast cancer risk value according to the latest data;

[0018] Analyze whether the decrease amplitude of the breast cancer risk value generated by each risk factor alone reaches or exceeds the preset amplitude;

[0019] If yes, keep the original breast cancer detection cycle unchanged, and the original breast cancer detection cycle is the breast cancer detection cycle determined according to the corresponding relationship between the weight range in which the weight of a specific risk factor on the breast cancer risk value falls, the risk value assessment range in which the breast cancer risk value falls, and the detection cycle;

[0020] If not, analyze and obtain the risk factors with a decrease amplitude less than the preset amplitude as target risk factors, calculate the ratio of the decrease amplitude of the target risk factors to the preset amplitude, calculate the adjustment coefficient of all target factors regarding the breast cancer detection cycle according to the ratio of the decrease amplitude of the target risk factors to the preset amplitude and the weight of the target risk factors on the breast cancer risk value, and then calculate the adjusted breast cancer detection cycle according to the adjustment coefficient and the original breast cancer detection cycle;

[0021] Update the patient's breast cancer-related detection time schedule according to the finally determined breast cancer detection cycle.

[0022] By adopting the above technical solutions, through real-time monitoring, personalized risk assessment, and dynamic adjustment of the detection cycle, precise management is achieved. Quantitative suggestions are generated based on data-driven weight analysis, which can effectively intervene in high-risk factors and improve the early detection rate. The detection frequency is intelligently optimized to reduce medical costs, and at the same time, through a continuous tracking feedback mechanism, the timeliness and effectiveness of risk control are ensured.

[0023] Optionally, it also includes steps after collecting relevant patient data and performing data preprocessing, and before training a model using a preset and already trained random forest algorithm, specifically as follows:

[0024] Divide patients into different age groups, including the young group, middle-aged group, and elderly group;

[0025] If the patient is in the young group or middle-aged group, maintain the original settings;

[0026] If the patient is in the elderly group, select variables related to breast cancer risk, use the stepwise regression method for variable screening, and establish a preliminary multiple regression model;

[0027] Divide the preprocessed data into a training set and a validation set, train the multiple regression model on the training set, adjust the performance of the multiple regression model by adjusting the parameters of the multiple regression model until the accuracy of the multiple regression model on the validation set reaches the preset accuracy within a preset number of consecutive times, determine that the training of the multiple regression model is completed, and view the regression coefficient corresponding to each risk factor;

[0028] According to the regression coefficient corresponding to each risk factor, calculate the sum of the absolute values of all regression coefficients, and calculate the ratio of the absolute value of the regression coefficient of different risk factors to the sum of the absolute values of all regression coefficients to determine the weight of each risk factor on the breast cancer risk value;

[0029] According to the corresponding relationship between the weight range in which the weight of a specific risk factor on the breast cancer risk value falls, the risk value assessment range in which the breast cancer risk value falls, and the detection cycle, analyze and determine the breast cancer detection cycle.

[0030] By adopting the above technical solutions, through the introduction of age group classification, a more detailed risk assessment is carried out for elderly patients. The stepwise regression method is used to screen variables and a multiple regression model is established, so as to more accurately analyze the influence weight of each risk factor on breast cancer risk. This innovation not only improves the accuracy of risk assessment, but also tailors a more reasonable detection cycle for elderly patients.

[0031] Optionally, it also includes steps parallel to analyzing and obtaining risk factors with a decline amplitude less than the preset amplitude as target risk factors, specifically as follows:

[0032] Patients whose decline in breast cancer risk value caused by risk factors alone does not reach the preset range are regarded as patients who need follow-up;

[0033] Initiate the follow-up process, contact the patient through intelligent voice method, and obtain the implementation results of the patient regarding the quantified advice information, where the implementation results include exercise duration and dietary adjustment;

[0034] If the implementation results of the patient regarding the quantified advice information do not conform to the quantified content mentioned in the quantified advice information, then advise the patient to execute again according to the quantified content mentioned in the quantified advice information;

[0035] If the implementation results of the patient regarding the quantified advice information conform to the quantified content mentioned in the quantified advice information, then analyze the quantified content related to health not mentioned in the quantified advice information, and provide suggestions for other quantified content to be added to the quantified advice information to form new quantified advice information, and send it to the patient's terminal again.

[0036] By adopting the above technical solutions, through refined follow-up management, more considerate health services are provided for patients. For patients whose risk reduction does not meet the expectation, initiate the follow-up process, communicate in a timely manner and adjust the quantified advice. This not only improves the compliance of patients, but also can adjust the health plan according to the actual situation to achieve personalized health management.

[0037] Optionally, updating the patient's breast cancer-related detection time schedule according to the finally determined breast cancer detection cycle includes:

[0038] Obtain the relevant information of the patient's electronic medical record, and extract the key factors affecting the breast cancer detection results. Among them, the key factors affecting the breast cancer detection results include other ongoing disease treatment plans, specific drugs used, recent surgical history, and the severity of the patient's underlying diseases;

[0039] According to the corresponding relationship between the range of influence degree values in which the influence degree values of the key factors affecting the breast cancer detection results fall and the delay time, analyze and determine the overall delay time caused by the key factors affecting the breast cancer detection results;

[0040] According to the overall delay time caused by the key factors affecting the breast cancer detection results and the analyzed and determined breast cancer detection cycle, re-analyze to obtain the breast cancer detection cycle, and re-form the patient's breast cancer-related detection time schedule.

[0041] By adopting the above technical solution, by integrating key factors of electronic medical records (such as treatment plans, medications, surgical history, etc.), the detection cycle is dynamically adjusted to avoid interference from other medical interventions on the test results and improve the detection accuracy. Real-time analysis of treatment impacts and intelligent deferral not only ensure the effectiveness of the detection but also optimize resource allocation, ensuring that patients undergo screening at the best time and enhancing the comprehensiveness and adaptability of risk control.

[0042] In a second aspect, the present application provides a computer storage medium, adopting the following technical solution:

[0043] A computer storage medium includes a memory, a processor, and a program stored on the memory and executable on the processor. When the program is loaded and executed by the processor, it can implement the program of the breast cancer risk control method in the breast cancer risk control system as described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flowchart showing the process of the breast cancer risk control method in a breast cancer risk control system according to an embodiment of the present application.

[0045] Figure 2 is a flowchart showing the steps before collecting patient-related data, performing data preprocessing, and training a model using a preset and pre-trained random forest algorithm in another embodiment of the present application.

[0046] Figure 3 is a flowchart showing the process parallel to the step of "if no, then analyze and obtain risk factors with a decrease amplitude less than the preset amplitude as target risk factors" in another embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The present application will be further described in detail below with reference to the accompanying drawings.

[0048] Refer to Figure 1 , a breast cancer risk control system disclosed in the present application, includes a breast monitoring device, at least one processor, and at least one memory storing a computer program. The at least one processor is configured to implement the breast cancer risk control method when executing the computer program. The specific steps are as follows:

[0049] Step S100, obtain patient-related data collected by the breast monitoring device and perform data preprocessing.

[0050] Among them, patient-related data includes real-time physiological data, daily activity data, environmental data, and personalized data. Data preprocessing includes the following steps, specifically as follows: 1. Clean the collected raw data to remove outliers, duplicate values, and missing values to ensure the accuracy and integrity of the data. 2. Standardize the data to eliminate the dimensional differences between different data types, so that the adjusted risk assessment model can analyze more accurately. 3. Integrate the processed data into a format suitable for input into the breast cancer risk value assessment model. It should be noted that for the patient information, real-time physiological data, daily activity data, environmental data, personalized data, and other various related data involved in this application, the patient's full consent and authorization have been obtained before acquisition. During the process of data collection, use, and processing, this application strictly complies with the laws, regulations, and standards in aspects such as data privacy protection and medical data management in relevant countries and regions to ensure the security, legality, and compliance of the data and effectively protect the personal rights and interests of patients.

[0051] Among them, the patient's real-time physiological data refers to the physiological index data of the patient's breast and its surrounding areas collected in real time through breast monitoring devices. These data can reflect the health status of the patient's breast, including but not limited to the temperature, humidity, blood flow velocity, electrophysiological signals, etc. of the breast tissue. The acquisition method of the patient's real-time physiological data is as follows: Through wearable breast monitoring devices, such as smart bras or patch sensors, collect the patient's breast physiological data in real time. These devices can use wireless communication technology to transmit the data to the analysis platform.

[0052] The daily activity data refers to the patient's behavior habits and activity patterns in daily life, such as exercise frequency, exercise intensity, sleep duration, work pressure, etc. These data help to analyze the impact of the patient's lifestyle on the risk of breast cancer. The acquisition method of the daily activity data is as follows: Record the patient's daily activity data through a smartphone application or wearable devices (such as smart watches, health bracelets, etc.). The patient can also manually input some activity information, such as diet records, work hours, etc.

[0053] The environmental data refers to the relevant information of the patient's environment, including air quality, ultraviolet intensity, eating habits, living environment, etc. The acquisition method of the environmental data is as follows: Use environmental monitoring devices, such as air quality detectors, ultraviolet sensors, etc., to collect the relevant data of the patient's environment. At the same time, the patient can record some environmental information through a mobile application, such as changes in residence, changes in eating habits, etc.

[0054] The patient's personalized data includes the patient's unique biomarkers, genotypes, living habits, and family medical history.

[0055] Suppose patient B wears a smart breast patch, a smart watch in daily life, and uses an environmental monitoring mobile application. The smart breast patch collects the temperature and density data of breast tissue in real time, while the smart watch records the patient's daily activity level and sleep quality. Meanwhile, the mobile application monitors and records the air quality index and ultraviolet exposure time of the environment where the patient is located. These data are regularly uploaded to the cloud server for preprocessing. The preprocessing process includes steps such as data cleaning, standardization, and integration to ensure the accuracy and availability of the data.

[0056] Step S200: Input the patient-related data that has completed data preprocessing into the breast cancer risk value assessment model that has completed training and takes into account the patient's personalized data, and output the breast cancer risk value.

[0057] The formation process of the breast cancer risk value assessment model that has completed training and takes into account the patient's personalized data is as follows: 1. Collect the real-time physiological data, daily activity data, environmental data, personalized data, and corresponding diagnosis results (whether suffering from breast cancer) of a large number of patients as the training data set. Perform preprocessing on the data, including missing value processing, outlier processing, data standardization, etc. 2. Select the features related to breast cancer risk from the collected data, such as specific physiological indicators, daily activity patterns, environmental factors, etc.; 3. Randomly select a part of the data as the training set and another part as the test set, and determine the number of decision trees in the random forest (for example, 100 trees). For each decision tree: randomly select a subset of features and recursively split the data until a predetermined stop condition is reached (such as the number of samples contained in the leaf node is less than the threshold, the depth of the tree reaches the upper limit, etc.). 4. Use the training set to train each decision tree to make each tree classify or predict the training data as accurately as possible. 5. Use the test set to evaluate the performance of the random forest model. Common evaluation indicators include accuracy, recall rate, F1 value, etc. If the model performance does not meet the requirements, adjust the model parameters (such as the number of decision trees, the size of the feature subset, the splitting condition, etc.), retrain until the accuracy of the model reaches 95% continuously for 3 times, and determine the formation of the breast cancer risk value assessment model.

[0058] Suppose we have collected a data set containing 1000 women, among which 500 are diagnosed as breast cancer patients and the other 500 are healthy people. The data set includes real-time physiological data (such as breast temperature, blood flow velocity), daily activity data (such as weekly exercise volume, eating habits), and environmental data (such as the air quality index of the place of residence).

[0059] After analysis, we have selected the following features related to breast cancer risk: Physiological indicators: breast temperature, blood flow velocity, breast tissue density; Daily activities: weekly exercise volume, high-fat diet frequency; Environmental factors: air quality index of the place of residence, long-term ultraviolet exposure.

[0060] We used the data of 800 women as the training set and the remaining 200 as the test set. We decided to use a random forest model consisting of 100 decision trees. During the training process, each decision tree randomly selected a subset of features and recursively split the data based on these features. We set the minimum number of samples in a leaf node to 5 and the maximum depth of the tree to 10.

[0061] After training, we used the test set to evaluate the model. The accuracy of the initial model was 90%, the recall rate was 85%, and the F1 value was 87.5%. To improve the model performance, we adjusted the following parameters: increasing the number of decision trees to 150, reducing the size of the feature subset, and adjusting the splitting conditions to make the tree deeper but with fewer samples in the leaf nodes. After several rounds of adjustment and optimization, the accuracy of the model reached 95% three times in a row. We believe that the model is stable enough and has good performance. Now, this trained breast cancer risk value assessment model can receive real-time physiological data, daily activity data, and environmental data of new patients and output a breast cancer risk value.

[0062] Step S300: Use a preset and trained random forest algorithm to train the model and calculate the weight of each risk factor on the breast cancer risk value.

[0063] Among them, the process of calculating the weight of each risk factor on the breast cancer risk value is as follows: Calculate the contribution degree of each feature in the construction of the decision tree and give a feature importance score, and calculate the weight of each risk factor on the breast cancer risk value according to different feature importance scores. The process of calculating the contribution degree of each feature in the construction of the decision tree and giving a feature importance score is as follows: In the random forest algorithm, the following common methods are usually used to calculate the contribution degree of each feature, such as average impurity reduction or average precision reduction. Taking average impurity reduction as an example: When constructing a decision tree, each time a feature is selected for node splitting to reduce the impurity of the data (usually measured by the Gini coefficient or information entropy). The average of the impurity reduction amounts of each feature in all decision trees is calculated to obtain the average impurity reduction value of the feature, which is used as a measure of its contribution degree. The feature importance score can be obtained by normalizing or standardizing the contribution degree, so that the sum of the importance scores of all features is 1 or within the range of 0 to 1.

[0064] Suppose a random forest model constructs 100 decision trees. For the feature of age: Among these 100 decision trees, the total reduction in impurity when age is used to split nodes is 500. For the feature of hormone level: The total reduction in impurity when used to split nodes is 800. For the feature of exercise duration: The total reduction in impurity is 200. For the feature of family medical history: The total reduction in impurity is 600. Then calculate the feature importance scores: The importance score of age = 500 / (500 + 800 + 200 + 600) = 0.2. The importance score of hormone level = 800 / 2100 ≈ 0.38. The importance score of exercise duration = 200 / 2100 ≈ 0.095. The importance score of family medical history = 600 / 2100 ≈ 0.286.

[0065] The process of calculating the weight of each risk factor for the breast cancer risk value is as follows: Use the importance score as the weight. Suppose the risk factors we define are: high hormone level risk, family medical history risk, low exercise duration risk. The weight of high hormone level risk = 0.38; The weight of family medical history risk = 0.286; The weight of low exercise duration risk = 0.095.

[0066] Through the above calculations, we obtain the weights of each risk factor for the breast cancer risk value, which can be used for subsequent assessment of breast cancer risk and determination of the detection cycle.

[0067] Furthermore, after the random forest model outputs the breast cancer risk value of the patient according to the calculated weights of each risk factor, the SHAP analysis method can be introduced. The specific steps are as follows:

[0068] Step S301, based on the SHAP analysis method, conduct an attribution explanation for the breast cancer risk value output by the model. SHAP analysis is based on cooperative game theory. By calculating the marginal contribution of each feature in the model prediction, the contribution degree of each risk factor to the individual risk score is generated. For example, if the breast cancer risk score of a certain patient is 80%, the SHAP analysis may show: the specific contributions of various factors such as high hormone level (+35%), family medical history (+25%), low exercise duration (+15%), age factor (+5%) to the risk score.

[0069] Step S302: Dynamically adjust the SHAP analysis display threshold according to the patient's real-time risk level. The system classifies the patient's real-time risk level based on the breast cancer risk value output by the model. For high-risk patients (risk value ≥ 0.7), the SHAP analysis display threshold is reduced from the default 10% to 5%. This is because there may be multiple potential factors jointly affecting the breast cancer risk of high-risk patients. Reducing the display threshold can comprehensively present these potential influencing factors and avoid missing important information. For example, factors such as "long-term mental stress" and "poor emotional state", which were not displayed originally due to their small influence proportion, can be presented under the dynamic threshold adjustment. For low-risk patients (risk value < 0.3), the SHAP analysis display threshold is increased to 15%. The main goal of low-risk patients is to prevent the occurrence of breast cancer. Increasing the display threshold can help focus on the most critical factors affecting the risk, such as "high hormone levels" and "family history", so as to formulate more precise prevention strategies.

[0070] Step S303: Based on the local linear model, simulate the impact of multi-scenario interventions on the predicted risk value. For high-risk patients: Combining the key influencing factors determined by the SHAP analysis in Step S325, such as long-term mental stress and high hormone levels, use the local linear model to simulate the comprehensive intervention scenario. For example, the psychological counseling is set as professional psychological counseling twice a week, 50 minutes each time; the work and rest adjustment requires the patient to ensure 7 - 8 hours of high-quality sleep every day and go to bed before 11 pm; the drug intervention uses specific regulatory drugs according to the patient's specific hormone levels and other conditions; the exercise plan is aerobic exercise 3 - 4 times a week, 30 - 45 minutes each time, such as jogging and yoga. The model predicts the decline in the patient's breast cancer risk value after 3 - 6 months of implementing these intervention measures, such as specific quantitative results like dropping from 0.8 to 0.6. For low-risk patients: If the SHAP analysis shows that the unreasonable diet structure and insufficient exercise volume are the key factors, the local linear model simulates the corresponding prevention scenario. For example, the patient reduces the intake of high-sugar foods by 30%, increases the intake of foods rich in dietary fiber, and at the same time increases 2 hours of outdoor exercise per week. The model predicts the change in the patient's risk value after 6 - 12 months, such as remaining in the low-risk range from 0.2 or further dropping to 0.15.

[0071] Step S304: Synchronously output the contribution degree and quantitative health advice to the doctor's terminal. The system outputs the contribution degree of each risk factor obtained from the SHAP analysis to the individual risk score, as well as the quantitative health advice generated after simulating multi-scenario interventions by the local linear model, such as the specific psychological counseling plan, drug dosage, and exercise plan for high-risk patients, and the detailed diet adjustment and exercise increase advice for low-risk patients, etc., to the doctor's terminal in a clear and intuitive report form.

[0072] Step S400: Analyze and determine the breast cancer detection cycle based on the weight range in which the weight of the breast cancer risk value falls according to specific risk factors, the corresponding relationship between the risk value assessment range in which the breast cancer risk value falls, and the detection cycle.

[0073] Among them, specific risk factors usually refer to those factors that have a significant impact on breast cancer risk, including but not limited to the following: 1. Physiological factors, such as abnormal hormone levels (such as estrogen, progesterone), specific physiological characteristics of breast tissue, etc. 2. Genetic factors, such as specific gene mutations (such as BRCA1, BRCA2 gene mutations), multiple relatives with breast cancer in the family history, etc. 3. Lifestyle-related factors, like long-term smoking habits, excessive alcohol consumption, lack of exercise, unhealthy diet (high-fat, high-calorie diet), etc. 4. Environmental factors, such as long-term exposure to radiation environment, exposure to certain chemicals, etc. 5. Reproductive-related factors, such as older age at first childbirth, non-childbearing, short breastfeeding time, etc.

[0074] Determine the weight range of specific risk factors: First, set different weight ranges according to previous calculations and analyses. For example, divide the weight range into low (0 - 0.2), medium (0.2 - 0.5), and high (0.5 - 1).

[0075] Determine the breast cancer risk value assessment range as follows: Similarly, set different risk value assessment ranges, such as low risk (0 - 0.3), medium risk (0.3 - 0.7), and high risk (0.7 - 1).

[0076] Establish the corresponding relationship between the weight range, risk value assessment range, and detection cycle as follows: For low weight and low risk value, the detection cycle is once every 2 years. For medium weight and medium risk value, the detection cycle is once a year. For high weight and high risk value, the detection cycle is once every six months.

[0077] Step S500: Form a detection time schedule related to the patient's breast cancer according to the analyzed and determined breast cancer detection cycle.

[0078] Among them, the determination of the detection cycle is mainly based on the breast cancer detection cycle analyzed in step S400 to clarify the frequency of breast examinations required for the patient, such as once a week, once a month, or once a quarter, etc.

[0079] The formulation of the time schedule is as follows: Based on the determined detection cycle, plan specific detection time points for the patient. These time points can be a specific list of dates or a time pattern that repeats according to the cycle. Then organize the planned detection time points into a clear time schedule, which includes the detection date, detection time (optional), detection location (such as hospital, clinic, or home self-examination), and any additional precautions or reminders.

[0080] Step S600: According to the corresponding relationship between the weight interval in which the weight of each risk factor for breast cancer risk value falls and the quantization advice, form quantization advice information, and send the formed quantization advice information to the terminal held by the patient.

[0081] In this step, multiple weight intervals are preset in advance, and corresponding quantization advice is formulated for each weight interval. Suppose the following three weight intervals are set: low weight interval (0 - 0.2), medium weight interval (0.2 - 0.5), high weight interval (0.5 - 1).

[0082] The following are some specific examples of risk factors and their corresponding quantization advice:

[0083] Risk factor "hormonal imbalance": If the weight falls into the low weight interval: It is recommended that the patient maintain regular work and rest, avoid staying up late, and conduct self - hormonal level monitoring once a month. If the weight falls into the medium weight interval: On the basis of maintaining regular work and rest, it is recommended that the patient conduct professional hormonal level tests once every three months, adjust the diet according to the doctor's advice, and reduce the intake of hormone - rich foods. If the weight falls into the high weight interval: It is recommended that the patient seek medical treatment immediately, follow the doctor's advice for drug treatment to regulate hormone levels, conduct hormonal level tests once a week, and strictly control the diet.

[0084] Risk factor "excessive alcohol consumption": If the weight falls into the low weight interval: It is recommended that the patient control the alcohol intake, with the number of drinking times not exceeding twice a month and no more than one glass each time. If the weight falls into the medium weight interval: It is recommended that the patient gradually reduce the alcohol intake within the next two months until the number of drinking times does not exceed once a month. If the weight falls into the high weight interval: It is recommended that the patient quit drinking immediately, join an alcohol - abstinence support group, and receive professional supervision.

[0085] Step S700: Collect the latest data of the patient within the preset cycle range after the quantization advice is sent, and re - analyze the breast cancer risk value and the weight of each risk factor for the breast cancer risk value based on the latest data.

[0086] The preset cycle can be set according to the actual situation, such as three months or half a year. Within this cycle, the latest data of the patient will be collected through various channels.

[0087] The data collected may include but are not limited to the following aspects: 1. The patient's daily physiological indicators, such as body temperature, blood pressure, heart rate, etc. 2. Changes in the patient's living habits, such as exercise frequency, sleep duration, diet structure, etc. 3. The evaluation results of the patient's emotional state and psychological stress.

[0088] Based on the collected latest data, re - apply the previously established model and algorithm to analyze the breast cancer risk value and the weight of each risk factor for this risk value.

[0089] Step S800: Analyze whether the decrease amplitude of the breast cancer risk value generated by each risk factor alone reaches or exceeds the preset amplitude. If yes, execute Step S900; if no, execute Step Sa00.

[0090] First, it is necessary to clarify the preset decrease amplitude set for each risk factor. For example, for the risk factor of "excessive long-term stress", the preset decrease amplitude may be 20%.

[0091] Then, calculate the actual decrease amplitude of the breast cancer risk value caused by each risk factor after a period of intervention (such as three months). For example, after three months of psychological adjustment and relaxation training, re-evaluate the impact of the risk factor of "excessive long-term stress" on the breast cancer risk value. The original risk value caused by this factor was 0.3, and after intervention, it became 0.21, with an actual decrease amplitude of 30%, exceeding the preset amplitude of 20%. Another example, for the risk factor of "staying up late for a long time", the preset decrease amplitude is 15%. After re-evaluation, it is found that the risk value changes from the original 0.25 to 0.22, with an actual decrease amplitude of 12%, which does not reach the preset amplitude of 15%.

[0092] Step S900: Keep the original breast cancer detection cycle unchanged. The original breast cancer detection cycle is determined according to the corresponding relationship between the weight range in which the weight of the breast cancer risk value by a specific risk factor falls, the risk value evaluation range in which the breast cancer risk value falls, and the detection cycle.

[0093] Step Sa00: Analyze and obtain the risk factors with a decrease amplitude less than the preset amplitude as target risk factors, calculate the ratio of the decrease amplitude of the target risk factors to the preset amplitude, calculate the adjustment coefficient of all target factors regarding the breast cancer detection cycle according to the ratio of the decrease amplitude of the target risk factors to the preset amplitude and the weight of the target risk factors on the breast cancer risk value, and then calculate the adjusted breast cancer detection cycle according to the adjustment coefficient and the original breast cancer detection cycle.

[0094] By analyzing the decrease amplitude of the breast cancer risk value caused by each risk factor, we determine the risk factors with a decrease amplitude less than the preset amplitude as target risk factors. For each target risk factor, we calculate the ratio of its actual decrease amplitude to the preset amplitude. This ratio reflects the gap between the risk reduction effect of this risk factor and the expected effect. Then, we use this ratio and the weight of this risk factor on the breast cancer risk value to calculate an adjustment coefficient regarding the breast cancer detection cycle.

[0095] For example: Suppose we have a risk factor of "unhealthy eating habits". After implementing quantitative suggestions for a period of time, we find that the decline in the breast cancer risk value caused by this risk factor does not reach the preset range.

[0096] We first determine "unhealthy eating habits" as the target risk factor. Suppose the preset range is a 20% decline in the risk value, while the actual decline is only 10%. Then the ratio of the decline to the preset range is 0.5. If the weight of "unhealthy eating habits" on the breast cancer risk value is 0.3, then we can calculate an adjustment coefficient. This adjustment coefficient may be the product of the ratio of the decline to the preset range and the risk factor weight, that is, 0.5 * 0.3 = 0.15. This adjustment coefficient means that due to the poor improvement effect of the risk factor of "unhealthy eating habits", we may need to shorten the adjusted breast cancer detection cycle by 15% (or make other corresponding adjustments according to the specific situation) to monitor the patient's health more frequently.

[0097] Step Sb00, update the patient's breast cancer-related detection time schedule according to the finally determined breast cancer detection cycle.

[0098] A breast cancer risk control system further includes steps after step S300, specifically as follows:

[0099] Step S3a0, analyze whether complete data of patients reaching or exceeding the preset number of cases are collected. These data should comprehensively cover patient personalized data (such as family cancer history, gene test results, etc.), real-time physiological data (such as elastography data of breast tissue, levels of tumor markers in blood, etc.), daily activity data (such as daily dietary calorie intake, weekly physical labor duration, etc.), and environmental data (such as electromagnetic radiation intensity of the long-term living environment, air pollutant concentration, etc.).

[0100] Among them, the preset number of cases can be 1200 cases.

[0101] Step S3b0, if the answer is no, then continue with the subsequent steps.

[0102] Step S3c0, if yes, select variables related to breast cancer risk, use stepwise regression method for variable screening, establish a preliminary multiple regression model, divide the preprocessed data into a training set and a validation set, train the multiple regression model on the training set, and adjust the performance of the multiple regression model by adjusting the parameters of the multiple regression model until the accuracy of the multiple regression model on the validation set reaches the preset accuracy within a preset number of consecutive times, determine that the training of the multiple regression model is completed, view the regression coefficients corresponding to each risk factor, calculate the sum of the absolute values of all regression coefficients, and calculate the ratio of the absolute value of the regression coefficient of different risk factors to the sum of the absolute values of all regression coefficients to determine the weight of each risk factor on the breast cancer risk value.

[0103] First, we need to select those variables from the collected and preprocessed data that are considered to be closely related to breast cancer risk. For example, it may include the patient's age, hormone levels (such as estrogen, progesterone), age at menarche, number of pregnancies, duration of breastfeeding, BMI (body mass index), eating habits (whether prefer high-fat foods), exercise habits (number of exercise hours per week), family history (number of breast cancer patients in immediate family members), etc.

[0104] Next, use the stepwise regression method for variable screening. Stepwise regression will introduce or eliminate variables step by step according to certain criteria to find the optimal combination of variables.

[0105] Then, establish a preliminary multiple regression model based on the selected variables. Suppose we have selected three variables: age, hormone level, and family history. The model may be expressed as: Breast cancer risk value = β0 + β1 * age + β2 * hormone level + β3 * family history.

[0106] After that, randomly divide the preprocessed data into a training set and a validation set. For example, if we have data of 100 patients, we may take 70 as the training set and 30 as the validation set. When training the multiple regression model on the training set, we will continuously adjust the parameters of the model, such as the learning rate, regularization parameter, etc., just like adjusting the engine and parts of a car, to make the performance of the model reach the best. When evaluating the model, we will use the validation set to check the accuracy of the model. If the accuracy of the model on the validation set reaches the preset 80% for 3 consecutive times, for example, we consider that the training of this multiple regression model is completed.

[0107] After training is completed, we view the regression coefficients corresponding to each risk factor. Suppose the regression coefficient of age is 0.3, the regression coefficient of hormone level is 0.5, and the regression coefficient of family history is 0.2.

[0108] Then calculate the sum of the absolute values of all regression coefficients, that is, |0.3| + |0.5| + |0.2| = 1.

[0109] Finally, calculate the ratio of the absolute value of the regression coefficient of each risk factor to the sum to determine the weight of each risk factor for the breast cancer risk value. The weight of age is |0.3| / 1 = 0.3, the weight of hormone level is |0.5| / 1 = 0.5, and the weight of family history is |0.2| / 1 = 0.2.

[0110] Step S3d0: Use the risk value weights output by the random forest model and the risk value weights output by the multiple regression model as new features and input them into the trained decision tree fusion model, and output the comprehensive risk weight evaluation result.

[0111] Among them, the decision tree fusion model is a model that combines multiple decision trees to improve prediction performance and stability.

[0112] The construction of the decision tree is as follows: Construct a certain number of decision trees, for example, construct 8 decision trees. When each decision tree is constructed, it grows based on a randomly selected feature subset and a random split point.

[0113] The training is as follows: 1. Train each decision tree with the existing training data. 2. During the training process, by adjusting the split features and split points, make each decision tree able to reasonably classify or predict the input risk value weight features.

[0114] . The fusion mechanism is as follows: When the risk value weights output by the random forest model are RF_weight1, RF_weight2,..., RF_weightn, and the risk value weights output by the multiple regression model are MR_weight1, MR_weight2,..., MR_weightn, calculate their average value as the fused weight. The fused weight is as follows:

[0115] Fusion_weighti=(RF_weighti+MR_weighti) / 2.

[0116] The output of the comprehensive risk weight evaluation result is as follows: Comprehensively calculate the fused weights of all risk factors. Finally, output a comprehensive risk weight evaluation result, which reflects the average performance of the two models.

[0117] First, we have obtained a set of risk value weights through the random forest model, and at the same time calculated another set of risk value weights through the multiple regression model. Next, regard these two sets of weights as new features and input them into the previously trained decision tree fusion model. This decision tree fusion model will comprehensively consider the information of these two sets of weights, and through its internal decision rules and calculation logic, analyze and process the input weight features.

[0118] . Assume that the risk value weights output by the random forest model are: Factor A: 0.4; Factor B: 0.3; Factor C: 0.2.

[0119] The risk value weights output by the multiple regression model are: Factor A: 0.3; Factor B: 0.4; Factor C: 0.3.

[0120] Take these weights as new features and input them into the decision tree fusion model. After calculation and analysis by the decision tree fusion model, the possible output comprehensive risk weights may be: Factor A: 0.35; Factor B: 0.38; Factor C: 0.27.

[0121] Step S3e0, according to the correspondence between the comprehensive risk weights output by the decision tree fusion model, the risk value evaluation range in which the breast cancer risk value falls, and the detection cycle, analyze and determine the breast cancer detection cycle.

[0122] The comprehensive risk weights output by the decision tree fusion model will be divided into different intervals, and each interval corresponds to a specific breast cancer risk value evaluation range.

[0123] Suppose we set the following intervals and corresponding risk assessment ranges and detection cycles:

[0124] Low-risk interval: Comprehensive risk weight < 0.3; Risk value evaluation range: 0 - 0.2; Detection cycle: once every 3 years;

[0125] Medium-risk interval: 0.3 <= Comprehensive risk weight < 0.7; Risk value evaluation range: 0.2 - 0.6;

[0126] Detection cycle: once every 2 years;

[0127] High-risk interval: Comprehensive risk weight >= 0.7; Risk value evaluation range: 0.6 - 1; Detection cycle: once a year.

[0128] For example, if the comprehensive risk weight output by the decision tree fusion model is 0.25, then it is in the low-risk interval. The corresponding breast cancer risk value evaluation range is 0 - 0.2, and the recommended detection cycle is once every 3 years. Another example, if the comprehensive risk weight is 0.8, it is in the high-risk interval. The corresponding breast cancer risk value evaluation range is 0.6 - 1, and the detection cycle should be set to once a year.

[0129] Refer to Figure 2 , A breast cancer risk control system further includes steps located after collecting patient-related data and performing data preprocessing, and before using a pre-set and trained random forest algorithm training model, specifically as follows:

[0130] Step SA00: Divide the patients into different age groups, including the young group, the middle-aged group, and the elderly group.

[0131] First, it is necessary to clarify the specific criteria for dividing age groups. Generally, the young group can be defined as those aged between 18 - 40 years old, the middle-aged group as those aged between 41 - 60 years old, and the elderly group as those aged 61 and above. Then, obtain the age information of the patients. This can be obtained through the patients' medical records, questionnaires, or direct inquiries, etc. According to the obtained age information, classify the patients into the corresponding age groups.

[0132] Step SB00: If the patient is in the young group or the middle-aged group, maintain the original settings.

[0133] Among them, the original setting is to continue to execute Step S300, that is, to train the model using a pre-set and already trained random forest algorithm.

[0134] Step SC00: If the patient is in the elderly group, select variables related to breast cancer risk, use the stepwise regression method for variable screening, and establish a preliminary multiple regression model.

[0135] Variables related to breast cancer risk include but are not limited to the following aspects: 1. Physiological indicators, such as changes in hormone levels (estrogen, progesterone, etc.) and breast tissue density. 2. Health status, such as whether suffering from chronic diseases like diabetes and hypertension. 3. Lifestyle factors, such as diet structure (whether high in oil and fat) and exercise habits (whether exercising regularly and the intensity of exercise). 4. Genetic factors, details of specific gene mutations or family medical history.

[0136] The process of using the stepwise regression method for variable screening is as follows: First, include all possible variables in the model. Then, according to a certain statistical criterion (such as AIC, BIC, etc.), gradually eliminate variables that do not contribute significantly to the model. Finally, leave the variables that have a significant impact on predicting breast cancer risk. Based on the selected variables, establish a preliminary multiple regression model. The general form of the multiple regression model is: Breast cancer risk value = β0 + β1X1 + β2X2 + … + βn*Xn, where X1, X2, etc. are the selected variables, β0 is the intercept, and β1, β2, etc. are the regression coefficients.

[0137] Suppose we have the following data for an elderly patient: Patient D: Age: 75 years old; Estrogen level: 25 pg / mL; Progesterone level: 10 pg / mL; Suffering from diabetes (yes / no): yes; Diet structure (healthy / unhealthy): unhealthy; Weekly exercise duration: 2 hours; There is 1 relative in the family with breast cancer.

[0138] First, select variables that may be related to breast cancer risk, such as estrogen level, progesterone level, whether having diabetes, diet structure, weekly exercise duration, and family history.

[0139] Using the stepwise regression method, it may be found that the contributions of diet structure and weekly exercise duration to the model are not significant and are excluded.

[0140] The finally established multiple regression model may be: Breast cancer risk value = β0 + β1 Estrogen level + β2 Progesterone level + β3 Whether having diabetes + β4 Family history.

[0141] Through such a process, a preliminary multiple regression model is established for elderly patients for subsequent further analysis and determination of risk weights and detection cycles.

[0142] Step SD00: Divide the preprocessed data into a training set and a validation set. Train the multiple regression model on the training set and adjust the performance of the multiple regression model by adjusting the parameters of the multiple regression model until the accuracy of the multiple regression model on the validation set reaches the preset accuracy within a preset number of consecutive times. Determine that the training of the multiple regression model is completed and view the regression coefficients corresponding to each risk factor.

[0143] First, randomly divide the preprocessed data. Usually, it can be divided according to a certain ratio. For example, 70% of the data is used as the training set and 30% of the data is used as the validation set. Then, use the training set to train the multiple regression model. During the training process, optimize the performance of the model by adjusting the parameters of the model, such as the learning rate, regularization parameter, etc. After each round of training, use the validation set to evaluate the accuracy of the model. If the accuracy of the model on the validation set reaches the preset accuracy (such as 80%) within a preset number of consecutive times (such as 5 times), it is considered that the training of the multiple regression model is completed.

[0144] Next, view the regression coefficients corresponding to each risk factor in the trained model. These regression coefficients reflect the degree of influence of each risk factor on the breast cancer risk value.

[0145] Step SE00: According to the regression coefficients corresponding to each risk factor, calculate the sum of the absolute values of all regression coefficients, and calculate the ratio of the absolute value of the regression coefficient of different risk factors to the sum of the absolute values of all regression coefficients to determine the weight of each risk factor on the breast cancer risk value.

[0146] After obtaining the regression coefficients corresponding to each risk factor in the multiple regression model, first calculate the sum of the absolute values of all regression coefficients. Suppose we have three risk factors, and their regression coefficients are: β1 = 0.2, β2 = -0.3, β3 = 0.4. Then calculate their absolute values first: |β1| = 0.2, |β2| = 0.3, |β3| = 0.4.

[0147] Then calculate the sum of the absolute values: |β1| + |β2| + |β3| = 0.2 + 0.3 + 0.4 = 0.9.

[0148] Next, calculate the ratio of the absolute value of each risk factor's regression coefficient to the sum of the absolute values of all regression coefficients.

[0149] For risk factor 1: Ratio = |β1| / (|β1| + |β2| + |β3|) = 0.2 / 0.9 ≈ 0.22.

[0150] For risk factor 2: Ratio = |β2| / (|β1| + |β2| + |β3|) = 0.3 / 0.9 ≈ 0.33.

[0151] For risk factor 3: Ratio = |β3| / (|β1| + |β2| + |β3|) = 0.4 / 0.9 ≈ 0.44.

[0152] The ratios obtained through such calculations determine the weights of each risk factor on the breast cancer risk value.

[0153] Step SF00, based on the correspondence between the weight range in which the weight of a specific risk factor on the breast cancer risk value falls, the risk value assessment range in which the breast cancer risk value falls, and the detection cycle, analyze and determine the breast cancer detection cycle.

[0154] First, it is necessary to clarify the different ranges of the weights of specific risk factors on the breast cancer risk value. For example, the low weight range can be set as 0 - 0.2, the medium weight range as 0.2 - 0.5, and the high weight range as 0.5 - 1.

[0155] At the same time, it is also necessary to determine the assessment range of the breast cancer risk value. For example, the low risk range is 0 - 0.3, the medium risk range is 0.3 - 0.7, and the high risk range is 0.7 - 1.

[0156] Then, obtain the weight of the specific risk factor on the breast cancer risk value and the breast cancer risk value calculated through the previous steps.

[0157] According to the range where the weight is located and the range where the risk value is located, look up the pre-set correspondence to determine the breast cancer detection cycle.

[0158] For example, if the weight is in the low weight range and the risk value is in the low risk range, the corresponding detection period may be once every three years; if the weight is in the medium weight range and the risk value is in the medium risk range, the corresponding detection period may be once every two years; if the weight is in the high weight range and the risk value is in the high risk range, the corresponding detection period may be once a year.

[0159] Refer to Figure 3 , a breast cancer risk management and control system further includes other steps parallel to the step of "if the answer is no, then analyze and obtain risk factors with a decrease amplitude less than the preset amplitude as target risk factors", specifically as follows:

[0160] Step Sh00: Regard patients whose decrease amplitude of the breast cancer risk value generated by a single risk factor does not reach the preset amplitude as patients to be followed up.

[0161] First, the system analyzes the decrease amplitude of the breast cancer risk value caused by each risk factor. This is determined by comparing with the risk value of the previous assessment. If the decrease amplitude of the risk value caused by a certain risk factor does not reach the preset amplitude, then this risk factor is regarded as a target that needs to be focused on. For patients with risk factors whose decrease amplitude does not reach the preset amplitude, the system will mark them as personnel to be followed up.

[0162] Suppose we have a patient with a too high BMI (Body Mass Index), which is an important breast cancer risk factor. After implementing quantitative suggestions for a period of time, we find that the decrease amplitude of the breast cancer risk value caused by her BMI does not reach the preset amplitude. We first determine that BMI is the target risk factor for this patient. Since the decrease amplitude of BMI does not reach the preset amplitude, we mark this patient as a person to be followed up.

[0163] For this patient, we can give specific quantitative suggestions to help her more effectively reduce her BMI and breast cancer risk. For example: Suggest that she do at least 150 minutes of moderate-intensity aerobic exercise per week, such as brisk walking, swimming or cycling. Adjust the diet structure, reduce the intake of high-calorie and high-fat foods, and increase the intake of vegetables, fruits and whole grains. Regularly monitor the change of BMI and record it for observing the progress.

[0164] Step Si00: Initiate the follow-up process, contact the patient through the intelligent voice method, and obtain the implementation results of the patient's information on quantitative suggestions. The implementation results include exercise duration and diet adjustment.

[0165] After identifying the patients to be followed up, the system will automatically activate the intelligent voice follow-up function. This function utilizes advanced speech recognition and speech synthesis technologies to conduct natural and fluent voice communication with patients. The system will first send an intelligent voice greeting to the patient, such as "Hello, this is the breast cancer risk management follow-up system. Are you [patient's name]?" After the patient confirms their identity, the follow-up process will continue.

[0166] Next, the system will ask the patient about the implementation of the previously sent quantitative advice information, especially the specific data regarding exercise duration and dietary adjustments. For example, the system may ask, "May I ask how long you exercised on average each day in the past week?" or "Have you adjusted your diet structure as recommended and reduced your intake of high-fat foods?"

[0167] The patient's answers will be automatically recorded by the system and converted into an analyzable data format. These data will be used to evaluate the patient's implementation and for adjusted risk assessment and advice adjustment.

[0168] Step Sj00, if the implementation result of the patient regarding the quantitative advice information does not conform to the quantitative content mentioned in the quantitative advice information, then advise the patient to execute again according to the quantitative content mentioned in the quantitative advice information.

[0169] Compare the implementation result provided by the patient with the original quantitative advice to check whether the patient has made corresponding health behavior adjustments as recommended. If the patient's implementation result does not match the quantitative advice content, it indicates that the patient has not met the recommended standards in some aspects. For patients who do not meet the quantitative advice standards, we will emphasize the importance of the quantitative advice again and advise the patient to execute strictly according to the content of the quantitative advice again.

[0170] Step Sk00, if the implementation result of the patient regarding the quantitative advice information conforms to the quantitative content mentioned in the quantitative advice information, then analyze the quantitative content related to health not mentioned in the quantitative advice information and provide suggestions for other quantitative content to be added to the quantitative advice information to form new quantitative advice information and send it to the patient's terminal again.

[0171] If the patient has well implemented the previous quantitative advice, the system will further analyze other possible health-related risk factors that may not have been covered by the previous quantitative advice. Based on the above analysis, the system will generate new quantitative advice aimed at further optimizing the patient's health behavior and reducing the breast cancer risk.

[0172] Taking the new risk factor of "sleep deprivation" as an example, the corresponding quantitative suggestions could be: Ensure 7 - 9 hours of high-quality sleep every night. Avoid using electronic devices before bedtime to reduce the impact of blue light on sleep quality. Create a comfortable sleep environment and ensure that the mattress and pillow fit your body curves and sleep habits. Record your sleep time and quality every night for self-monitoring and continuous improvement. By implementing these new quantitative suggestions, patients can further reduce the risk of breast cancer and improve their overall health level.

[0173] Update the patient's breast cancer-related detection time schedule according to the finally determined breast cancer detection cycle, including:

[0174] Step S410, obtain the relevant information of the patient's electronic medical record and extract the key factors affecting the breast cancer detection results. Among them, the key factors affecting the breast cancer detection results include the ongoing treatment plans for other diseases, the specific drugs used, the recent surgical history, and the severity of the patient's underlying diseases.

[0175] Extract the key factors affecting the breast cancer detection results from the collected electronic medical record information. These key factors include but are not limited to: 1. The ongoing treatment plans for other diseases: Some treatment plans may affect the breast cancer detection results, especially those involving hormone therapy or immunotherapy. 2. The specific drugs used: Some drugs, such as hormonal drugs, may interfere with the breast cancer detection. 3. The recent surgical history: Surgery may cause changes in the internal physiological environment of the body, thus affecting the detection results. 4. The severity of the patient's underlying diseases: The severity of the underlying diseases may affect the patient's physiological state and thus have an impact on the detection results.

[0176] Step S420, analyze and determine the overall delay time caused by the key factors affecting the breast cancer detection results according to the corresponding relationship between the range of the influence degree values of the key factors affecting the breast cancer detection results falling into the range of influence degree values and the delay time.

[0177] First, different ranges of influence degree values and the corresponding delay times will be preset. For example, the influence degree values are divided into three ranges: mild (0 - 0.3), moderate (0.3 - 0.6), and severe (0.6 - 1).

[0178] For the key factor of "the ongoing treatment plans for other diseases", if the degree of influence of the treatment plan on the body is evaluated as mild, the corresponding delay time may be set to 1 month; if it is a moderate influence, the delay time may be 2 months; and if it is a severe influence, it may be 3 months.

[0179] Suppose a patient is receiving a treatment plan for another disease that has a moderate impact on the body. Then, in this step, according to the preset corresponding relationship, the delay time caused by this treatment plan is determined to be 2 months.

[0180] For another example, regarding the key factor of "specific drug used", if the impact degree of the drug is evaluated as mild, the delay time may be half a month; for moderate impact, it is 1 month; and for severe impact, it is 1.5 months.

[0181] If a patient is using a specific drug that is evaluated as having a severe impact, then the resulting delay time is determined to be 1.5 months.

[0182] Step S430, based on the overall delay time caused by the key factors affecting the breast cancer detection results and the analyzed and determined breast cancer detection cycle, re-analyze to obtain the breast cancer detection cycle and re-formulate the patient's breast cancer-related detection time schedule.

[0183] In this step, first, the overall delay time caused by the key factors determined in the previous step (S420) and the originally analyzed and determined breast cancer detection cycle are obtained. For example, the originally determined breast cancer detection cycle is to conduct a detection every 8 months, but through step S420, the calculated overall delay time caused by the key factors is 2 months. Next, the delay time is added to the original detection cycle for re-analysis. Taking the above example, the re-calculated detection cycle becomes to conduct a detection every 10 months. Then, based on this re-determined detection cycle, a detailed breast cancer-related detection time schedule is formulated for the patient.

[0184] A breast cancer risk control system also includes steps after updating the patient's breast cancer-related detection time schedule according to the finally determined breast cancer detection cycle, which are as follows:

[0185] Step Sd00, collect the specific information of the patient's breast cancer-related detections and perform data preprocessing.

[0186] Among them, the specific information of the breast cancer-related detections includes but is not limited to breast cancer pathological data, physical condition information, underlying disease information, and breast cancer risk assessment results. Data preprocessing work. This may include the following operations: 1. Data cleaning, removing duplicate, incorrect, or incomplete data. 2.

[0187] Data standardization, uniformly converting data from different sources and formats into a comparable and analyzable standard format. 3. Data encoding, encoding some non-numerical data for adjusted analysis and calculation.

[0188] Step Se00: Select features related to adjuvant therapy decision-making from the specific information collected on the patient's breast cancer-related tests.

[0189] Features related to adjuvant therapy decision-making include tumor size, grade, patient age, and severity of underlying diseases.

[0190] In this step, a large amount of specific information collected on the patient's breast cancer-related tests will be carefully screened and analyzed to extract the key features most relevant to adjuvant therapy decision-making.

[0191] First, attention will be paid to the characteristics of the tumor itself, such as the size of the tumor. If the tumor is large, it may mean that more aggressive treatment measures are necessary; if the tumor is small, different treatment considerations may apply. The grade of the tumor is also one of the important features.

[0192] High-grade tumors usually have a higher degree of malignancy and invasiveness, which will affect the choice of treatment plan.

[0193] The patient's age is another key factor. Younger patients may have better tolerance to treatment, while older patients may require a more gentle or comprehensive treatment approach considering the overall physical condition.

[0194] The severity of underlying diseases cannot be ignored. If the patient has severe underlying diseases such as heart disease and diabetes, this will limit the application of certain treatment methods or require special attention to the prevention and management of complications during the treatment process.

[0195] Step Sf00: Input the features related to adjuvant therapy decision-making into a pre-trained adjuvant therapy decision model, and output the result of whether adjuvant therapy is needed and the treatment plan under the condition of needing adjuvant therapy. The treatment plan under the condition of needing adjuvant therapy includes surgical and drug supply plans.

[0196] In this step, the screened features related to adjuvant therapy decision-making, such as tumor size, grade, patient age, and severity of underlying diseases, will be input into a pre-trained adjuvant therapy decision model with a large amount of data.

[0197] This model will use complex algorithms and machine learning techniques to comprehensively analyze and calculate the input features. For example, the model may evaluate the patient's tolerance to surgery based on the patient's age and the severity of underlying diseases, and combine the size and grade of the tumor to judge the malignancy and progression risk of the tumor.

[0198] Then, the model will output two key results. One is the judgment on whether adjuvant treatment is needed. If the model believes that the patient's condition is relatively severe and simple initial treatment is not sufficient to control the condition, it will output the result that adjuvant treatment is needed; conversely, if the patient's condition is relatively good, it may output the conclusion that adjuvant treatment is not needed. The second is that if adjuvant treatment is needed, the model will give a specific treatment plan, including the surgical plan and the drug supply plan. The surgical plan may detail the type of surgery (such as breast-conserving surgery or total mastectomy), the scope and difficulty of the surgery, etc. The drug supply plan will list the types of drugs suitable for the patient (such as chemotherapy drugs, targeted drugs, etc.) and the corresponding dosages and usage frequencies.

[0199] In step Sg00, if the output is the result that adjuvant treatment is needed and the treatment plan under adjuvant treatment is surgery, obtain the patient's medical imaging data, use an image segmentation algorithm to extract the contours of the tumor and surrounding tissues, and based on the extracted contours of the tumor and surrounding tissues, use a path planning algorithm to simulate the entry path and operation range of the surgical instrument, and determine the surgical path and resection range, thereby forming a surgical planning plan.

[0200] First, obtain the patient's medical imaging data, which may include the results of various imaging examinations such as magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound.

[0201] Then, use an advanced image segmentation algorithm, such as a convolutional neural network (CNN) in deep learning, to process the medical images. Through the trained model, automatically identify and segment the tumor and its surrounding key tissue structures, such as blood vessels, nerves, and other important organs.

[0202] Based on the results of image segmentation, accurately extract the contours of the tumor and surrounding tissues. Use this contour data to construct a three-dimensional (3D) model to more intuitively display the tumor location and its relative relationship with the surrounding tissues.

[0203] Next, according to the extracted contour information, use a path planning algorithm such as the ant colony algorithm or the A* algorithm, aiming to minimize surgical trauma and maximize tumor resection effect, to simulate the possible entry paths of the surgical instrument. According to the tumor characteristics and the path planning results, combined with the size and operation requirements of the surgical instrument, determine the operation range of the surgical instrument in the tumor area. Considering both path planning and operation range, determine the final surgical path and resection range to ensure that while completely removing the tumor, the surrounding normal tissues are protected to the greatest extent.

[0204] Based on the above simulation results, the specific surgical path and resection scope are finally determined. For example, it is determined which part to cut into to minimize the damage to surrounding normal tissues while ensuring the complete resection of the tumor; it is determined how far from the tumor edge the resection boundary should be to ensure the complete removal of cancer cells without over-resecting healthy tissues.

[0205] For example, if the patient's tumor is located deep in the breast and close to important blood vessels and nerves, through image segmentation and path planning, a surgical path that enters from the side and bypasses important structures may be determined, and a resection scope that is relatively conservative but can ensure tumor removal is determined.

[0206] For another example, for a tumor with a relatively clear boundary and a shallow location, the surgical path may be selected to cut directly from above, and the resection scope can also be relatively small to maximize the preservation of normal breast tissue and function.

[0207] In step Sh00, if the output is a result that requires adjuvant therapy and the treatment plan under adjuvant therapy is medication, obtain the patient's gene test results, drug sensitivity data, and surgical plan, and based on the patient's gene test results, drug sensitivity data, and surgical plan, use a preset drug matching algorithm to screen out suitable drug types and dosages as the drug provision plan.

[0208] Description of the drug matching algorithm: Based on big data analysis and machine learning techniques, by integrating the patient's gene test results, drug sensitivity data, and surgical plan, it intelligently matches the most suitable drug types and dosages. The algorithm first analyzes the gene test results, identifies gene mutations related to drug responses, and predicts the patient's metabolic rate and efficiency of different drugs. Then, combined with the drug sensitivity data, it evaluates the patient's tolerance and response to different drugs to avoid selecting drugs that may cause serious side effects or are ineffective. At the same time, it considers the impact of the surgical plan on drug use, such as drug adjustment during the postoperative recovery period. Finally, the algorithm will comprehensively consider all the above information and perform intelligent matching through preset rules and models to recommend the most suitable drug types and dosages for the patient.

[0209] According to the output results of the drug matching algorithm, formulate a personalized drug provision plan. The plan will detail key information such as the name, dosage, frequency of medication, and time of medication of the drug. At the same time, the plan will also consider the patient's actual situation, such as economic status and medication convenience, to ensure the feasibility of the plan and the patient's compliance.

[0210] Suppose the genetic test results of patient B show that they have a high reactivity to a certain new targeted drug, and the drug sensitivity test also supports the use of this drug. Considering that patient B has just had surgery and the drug dosage needs to be adjusted to reduce the physical burden, the drug matching algorithm will recommend this targeted drug and give specific medication guidance.

[0211] The breast cancer risk management and control system also includes steps after providing the formation of the surgical planning plan, specifically as follows:

[0212] Step Sg01, classify and organize the collected physiological data, rehabilitation data, lifestyle data, and psychological state data respectively.

[0213] Specifically, classify the collected physiological data (such as heart rate, blood pressure, body temperature, blood test results, etc.), rehabilitation data (wound healing situation, progress of recovery of mobility, etc.), lifestyle data (diet structure, exercise duration and type, etc.), and psychological state data (assessment results of anxiety and depression levels, etc.) respectively for subsequent analysis.

[0214] Step Sg02, analyze the trend of each type of data within a preset future time range according to each type of data, and determine the scoring ratio of different types of data based on the data range into which different types of data fall, the trend range into which different types of data fall within the preset future time range, and the scoring ratio.

[0215] Specifically, for each type of data, use the existing data and appropriate analysis methods (such as time series analysis, etc.) to predict its trend within the preset future time range. For example, whether the heart rate in physiological data may remain stable, increase, or decrease; whether the wound healing speed in rehabilitation data will accelerate, remain unchanged, or slow down, etc.

[0216] Step Sg03, determine the scoring ratio of this type of data according to the data range into which different types of data currently fall and the future trend range, in combination with the preset corresponding relationship. For example, if the physiological data is currently within the normal range and the future trend is favorable, a relatively high scoring ratio may be given, such as 80% of the total score of this type; if the rehabilitation data currently shows slow recovery and the future trend is uncertain, a relatively low scoring ratio may be given, such as 60% of the total score of this type, etc.

[0217] Step Sg04, analyze and determine the overall score according to the preset scores corresponding to different types of data and the scoring ratios of different types of data.

[0218] The scores corresponding to different types of data are obtained as follows: Obtain the surgical level and the overall surgical success rate; analyze and determine the scores corresponding to different types of data based on the surgical level, the overall surgical success rate, and the scores corresponding to different types of data.

[0219] Specifically, the scores corresponding to different categories of data are initially determined according to the surgical level and the overall surgical success rate. For example, when the surgical level is high and the success rate is low, the initial scores of various types of data may be relatively low; when the surgical level is low and the success rate is high, the initial scores of various types of data may be relatively high.

[0220] Combined with the score proportion of different categories of data and the preset scores corresponding to various categories of data, the actual score of each category of data is calculated. For example, if the preset score for physiological data is 40 points and the score proportion is 80%, the actual score is 32 points. The actual scores of all categories are added together to obtain the overall score.

[0221] Step Sg05: Analyze and determine the postoperative breast cancer detection cycle according to the corresponding relationship between the score range in which the overall score falls and the postoperative breast cancer detection cycle.

[0222] Suppose a patient has undergone breast cancer surgery and is in the postoperative rehabilitation stage.

[0223] The data is classified and sorted as follows: Physiological data: The current heart rate, blood pressure, and body temperature are basically normal, and some indicators in the blood test fluctuate slightly. Rehabilitation status data: The wound heals slowly, and the progress of the recovery of motor ability is average. Lifestyle data: The diet structure is relatively reasonable, and there is a certain amount of exercise but it is irregular.

[0224] Mental state data: There is mild anxiety.

[0225] Analyze the future trends of each category of data and determine the score proportions as follows: Physiological data: Through analysis, it is expected that the heart rate, blood pressure, etc. may remain stable in the future, and the blood test indicators are also expected to gradually return to normal. The score proportion given to this category of data is 75%. Rehabilitation status data: Due to the slow wound healing and the uncertainty of the recovery of motor ability, the score proportion given is 60%. Lifestyle data: Considering that the patient has room for improvement and it may have a positive impact on rehabilitation, the score proportion given is 70%. Mental state data: Given that the mild anxiety may last for some time, the score proportion given is 65%.

[0226] Determine the scores of different categories of data and the overall score as follows: The obtained surgical level is medium, and the overall surgical success rate is 75%. Initially determine that the preset score for physiological data is 40 points, the preset score for rehabilitation status data is 30 points, the preset score for lifestyle data is 20 points, and the preset score for mental state data is 10 points.

[0227] Actual score of physiological data: 40 × 75% = 30 points.

[0228] Actual score of rehabilitation status data: 30 × 60% = 18 points.

[0229] Actual score of lifestyle data: 20 × 70% = 14 points.

[0230] Actual score of mental state data: 10 × 65% = 6.5 points.

[0231] The overall score is 30 + 18 + 14 + 6.5 = 68.5 points.

[0232] Determine the postoperative breast cancer detection cycle as follows: According to the corresponding relationship between the preset score range and the detection cycle, 68.5 points is between 60 - 80 points, and it can be determined that the postoperative detection cycle is once every three months.

[0233] Furthermore, the breast cancer risk management and control system also includes steps after providing the formation of the surgical planning scheme, specifically as follows:

[0234] Step Sg06, use the SHAP analysis method to analyze the contribution degree of various postoperative data in risk prediction. Adopt the Holt-Winters triple exponential smoothing time series analysis method to analyze the change trend of postoperative data, and obtain the trend stability score of the data. According to the surgical level and the patient's physiological indicators, evaluate the matching degree between the postoperative data and the clinical standard rehabilitation path, and obtain the clinical path correlation score.

[0235] Among them, the Holt-Winters triple exponential smoothing method is used to analyze the trend, seasonality and irregular fluctuations of time series data, and predict future data changes. Output: Trend stability score (0 - 1), the higher the score, the smaller the data fluctuation.

[0236] The method for obtaining the trend stability score is as follows: 1. Collect multiple observation values of a certain postoperative data (such as the patient's blood pressure value) within a period of time to form time series data. 2. Use the Holt-Winters triple exponential smoothing method to analyze this time series, and this method will consider factors such as the level, trend and seasonality of the data. 3. According to the analysis results, calculate the trend stability score of the data. For example, determine the score by calculating indicators such as the deviation degree between the predicted value and the actual value.

[0237] Clinical path correlation: The matching degree between postoperative data and the standardized rehabilitation path (such as the NCCN guidelines). Range: 0 (completely unmatched) to 1 (completely matched).

[0238] The method for obtaining the clinical pathway correlation score is as follows: 1. Establish a clinical standard rehabilitation pathway database, which contains the standard rehabilitation data range and change trend under different surgical levels and combinations of patient physiological indicators. 2. Compare the actual postoperative data of the patient with the clinical standard rehabilitation pathway corresponding to the corresponding surgical level and physiological indicators. 3. According to the comparison results, calculate the clinical pathway correlation score through a preset clinical pathway correlation score algorithm. For example, if a certain indicator of the patient is within the standard pathway range, a higher score is given; if it deviates greatly from the range, the score is lower.

[0239] The steps involved in the preset clinical pathway correlation score algorithm are as follows:

[0240] 1. Data standardization processing: Perform Z-score standardization on the postoperative data (such as body temperature, heart rate, wound healing degree, etc.), and perform the same standardization processing on the corresponding indicators of the clinical standard rehabilitation pathway.

[0241] 2. Dynamic time warping (DTW) alignment: Use the DTW algorithm to solve the problem of misalignment of the time axis between the postoperative data and the standard pathway, and calculate the optimal matching path between time series. Example: The time points of the postoperative body temperature data are [the 1st day, the 3rd day, the 5th day], and the standard pathway is [the 2nd day, the 4th day, the 6th day]. DTW will find the time warping path between the two for matching.

[0242] 3. Cosine similarity calculation: Calculate the cosine similarity between the aligned postoperative data sequence and the standard pathway.

[0243] 4. Surgical level weighted adjustment: Set the weight coefficient α ∈ [0.7, 1.3] according to the surgical type (such as breast-conserving surgery / mastectomy). Example: The weight coefficient for mastectomy is set to 1.2, and the weight coefficient for breast-conserving surgery is set to 0.9.

[0244] 5. Physiological index correction: Introduce physiological indicators such as BMI and age as correction factors β.

[0245] The specific formula is as follows: .

[0246] 6. Comprehensive score calculation: Clinical pathway correlation score = sim × α × β.

[0247] Example: Similarity 0.85, surgical weight 1.2, physiological correction coefficient 0.95, and the final score is 0.85 × 1.2 × 0.95 = 0.969.

[0248] Step Sg07: According to the preset weight coefficients, combine the SHAP contribution, trend stability score, and clinical pathway relevance score to assign dynamic weights to each type of postoperative data. The formula is as follows: Weight = α × (SHAP contribution / total SHAP contribution) + β × trend stability score + γ × clinical pathway relevance score.

[0249] The preset weight coefficients are defined as follows: Three coefficients preset in the breast cancer risk control system, represented by α, β, and γ respectively, are used to balance the relative importance of the SHAP contribution, trend stability score, and clinical pathway relevance score when determining the weights of postoperative data.

[0250] The acquisition method of the preset weight coefficients is as follows: Usually determined jointly by medical experts and data scientists based on clinical experience, research results, and statistical analysis of a large amount of historical data. For example, in some studies, through the analysis of postoperative rehabilitation data of multiple groups of breast cancer patients, it is found that the SHAP contribution has a greater impact on risk prediction, and the value of α can be appropriately increased.

[0251] Step Sg08: Standardize various types of postoperative indicator data, determine the expected recovery curve of each indicator at different postoperative stages, calculate the score of each indicator according to the comparison between the standardized value of the indicator and the expected recovery curve, and assign corresponding weights to the scores of each indicator according to the importance of different indicators to calculate the comprehensive rehabilitation score.

[0252] Various types of postoperative indicator data: Include physiological data (such as heart rate, blood pressure, body temperature, etc.), rehabilitation situation data (such as wound healing situation, progress of activity ability recovery, etc.), lifestyle data (such as diet structure, exercise duration and type, etc.), and psychological state data (such as evaluation results of anxiety and depression levels, etc.).

[0253] Standardization processing: Perform Z-score standardization on various types of postoperative indicator data to make its mean 0 and standard deviation 1, so as to eliminate the influence of the dimension and dimension between different indicator data.

[0254] Expected recovery curve: An ideal recovery trajectory set for each postoperative indicator at different stages based on a large amount of clinical data and medical research. It reflects the numerical change trend that the indicator should reach over time under normal rehabilitation conditions.

[0255] Indicator score calculation: Compare the standardized indicator data with the expected recovery curve, and calculate the score of each indicator according to the comparison situation. The scoring rules can be set according to the clinical significance and recovery progress of the indicator. For example, if the actual value of an indicator deviates less from the expected value, a higher score is given; otherwise, a lower score is given.

[0256] Weight Allocation: According to the importance of different indicators in the rehabilitation process, corresponding weights are assigned to the scores of each indicator. For example, heart rate and blood pressure in physiological indicators may have higher weights than dietary structure in lifestyle indicators. Comprehensive Rehabilitation Score Calculation: Multiply the score of each indicator by its corresponding weight, and then sum up all the weighted scores to obtain the comprehensive rehabilitation score. This score can comprehensively reflect the postoperative rehabilitation status of the patient.

[0257] For example, assume we have the following three indicators and their weights: Physiological Indicator A (weight 0.5): The standardized value is 0.8, the expected recovery curve value is 0.7, and the scoring rule is that a deviation within ±0.2 gets 80 points, and 10 points are deducted for every 0.1 exceeded.

[0258] Then the score S1 of Physiological Indicator A is: S1 = 80 - 10×(0.8 - 0.7) / 0.1 = 80 - 10×1 = 70. Rehabilitation Indicator B (weight 0.3): The standardized value is 0.6, the expected recovery curve value is 0.5, and the scoring rule is that a deviation within ±0.2 gets 100 points, and 10 points are deducted for every 0.1 exceeded. Then the score S2 of Rehabilitation Indicator B is: S2 = 100 - 10×(0.6 - 0.5) / 0.1 = 100 - 10×1 = 90.

[0259] Lifestyle Indicator C (weight 0.2): The standardized value is 0.9, the expected recovery curve value is 0.8, and the scoring rule is that a deviation within ±0.2 gets 90 points, and 10 points are deducted for every 0.1 exceeded. Then the score S3 of Lifestyle Indicator C is: S3 = 90 - 10×(0.9 - 0.8) / 0.1 = 90 - 10×1 = 80. The calculation of the comprehensive rehabilitation score S is as follows:

[0260] S = S1×0.5 + S2×0.3 + S3×0.2 = 70×0.5 + 90×0.3 + 80×0.2 = 35 + 27 + 16 = 78.

[0261] Step Sg09, based on the data of various postoperative indicators after standardized processing and the weight values of dynamic weight allocation, calculate the current risk value through weighted calculation, and calculate the change rate of the current risk value relative to the baseline risk value to reflect the dynamic change of the risk level. Formula: Risk Change Rate = (Current Risk Value - Baseline Risk Value) / Baseline Risk Value. Compare the actual rehabilitation score of the patient with the expected rehabilitation score, and calculate the rehabilitation deviation degree. The rehabilitation score can be constructed based on the adaptive scoring matrix, comprehensively considering the current situation of the indicators, the change rate and the acceleration. Formula: Rehabilitation Deviation Degree = (Actual Rehabilitation Score - Expected Rehabilitation Score) / (Full Score of Rehabilitation - Minimum Score of Rehabilitation).

[0262] Current risk value: Obtained by multiplying the standardized postoperative index data by the corresponding dynamic weights and then summing all the weighted data. It is a quantitative indicator comprehensively reflecting the current risk status of the patient.

[0263] Baseline risk value: The initial risk value at the first postoperative assessment of the patient, serving as a reference benchmark for subsequent risk changes. Usually output by the preoperative risk prediction model, reflecting the basic risk level of the patient immediately after surgery.

[0264] Risk change rate: Calculated by the formula (Current risk value - Baseline risk value) / Baseline risk value, used to reflect the dynamic change of the risk level. A negative value indicates a risk reduction, and a positive value indicates a risk increase.

[0265] Actual rehabilitation score: Constructed based on the adaptive scoring matrix, comprehensively considering the current status of the indicators, the change rate, and the acceleration. It reflects the actual rehabilitation status of the patient.

[0266] Expected rehabilitation score: The ideal rehabilitation score set for each postoperative indicator at different stages according to a large amount of clinical data and medical research. It reflects the rehabilitation level that the patient should reach under normal rehabilitation conditions.

[0267] Step Sg0a: Take the risk change rate and the rehabilitation deviation as the input variables of the fuzzy inference system. Define different fuzzy sets and membership functions for each input variable. For example, divide the risk change rate into three fuzzy sets: "low", "medium", and "high", and determine the membership function for each set.

[0268] Definition of fuzzy inference system: An intelligent system based on fuzzy logic theory that maps input variables (such as risk change rate, rehabilitation deviation) to fuzzy sets and conducts reasoning through fuzzy rules. Function: Process uncertain data and simulate the decision-making process of human experts.

[0269] Definition of input variables: The input parameters of the fuzzy inference system, which are the risk change rate and the rehabilitation deviation in this step.

[0270] Value range: Risk change rate: [-100%, +∞) (negative value indicates risk reduction, positive value indicates risk increase); Rehabilitation deviation: [-100%, +100%) (negative value indicates rehabilitation lag, positive value indicates rehabilitation advance)

[0271] Definition of fuzzy sets: The discretized classification of continuous input variables, such as dividing the risk change rate into "low", "medium", and "high". Characteristics: The boundaries are fuzzy, allowing partial membership (for example, a risk change rate of 25% may belong to both "medium" and "high" at the same time).

[0272] Definition of membership function: Describes the degree to which an input value belongs to a certain fuzzy set, with a value range of [0, 1]. Common types: triangular, trapezoidal, Gaussian, etc.

[0273] Step Sg0b: According to the membership degree of the input variable, use fuzzy rules for reasoning to obtain a fuzzy output result, and use a defuzzification method (such as the centroid method) to convert the fuzzy output result into a specific detection period adjustment value.

[0274] Definition of fuzzy rules: Based on clinical experience and medical knowledge, a conditional statement that maps fuzzy input variables (such as "high" risk change rate, "large" rehabilitation deviation) to output results (such as "shortened" detection period).

[0275] Definition of fuzzy inference: The process of deriving the fuzzy set of the output result according to the fuzzy rules and combining the membership degree of the input variable. Method: Mamdani inference method (based on max-min composition).

[0276] Definition of defuzzification method: The process of converting the fuzzy output result into a specific value (such as shortening by 2 weeks). Common methods: Centroid method: Calculate the centroid position of the fuzzy set. Maximum membership degree method: Take the point with the maximum membership degree.

[0277] Definition of detection period adjustment value: According to the fuzzy inference result, determine the adjustment amplitude of the detection period (such as shortening by 15%). Range: Usually between -50% (shortening) and +50% (lengthening).

[0278] Step Sg0c: Dynamically adjust the current detection period according to the detection period adjustment value output by the fuzzy inference system.

[0279] Based on the same inventive concept, an embodiment of the present invention provides a computer storage medium, including a memory and a processor, and a program that can be run on the processor to implement any one of the Figures 1 to 3 methods.

[0280] The embodiments of the present specific implementation manners are all preferred embodiments of the present application, and do not limit the protection scope of the present application accordingly. Therefore, all equivalent changes made according to the structure, shape, and principle of the present application should be covered within the protection scope of the present application.

Claims

1. A breast cancer risk management system, characterized in that: include: Breast monitoring equipment; at least one processor; At least one memory storing a computer program, and at least one processor configured to implement a breast cancer risk management method when executing the computer program, the specific steps are as follows: Obtain patient-related data collected by breast monitoring equipment and perform data preprocessing; Inputting the patient-related data that has completed data preprocessing into the trained breast cancer risk value assessment model that considers the patient's personalized data, and outputting the breast cancer risk value; Use the preset and trained random forest algorithm to train the model and calculate the weight of each risk factor for breast cancer risk value; Analyze and determine the breast cancer detection cycle based on the corresponding relationship between the weight range of the breast cancer risk value of the specific risk factor, the risk value assessment range of the breast cancer risk value, and the detection cycle; Form a time schedule for breast cancer related testing for the patient based on the breast cancer testing cycle determined by the analysis; According to the corresponding relationship between the weight interval of each risk factor for the breast cancer risk value and the quantitative suggestion, quantitative suggestion information is formed, and the formed quantitative suggestion information is sent to the terminal held by the patient; Collect the latest data of the patient within the preset period after the quantitative recommendation is sent, and re-analyze the breast cancer risk value and the weight of each risk factor to the breast cancer risk value based on the latest data; Analyze whether the reduction in breast cancer risk value produced by each risk factor alone reaches or exceeds the preset range; If yes, the original breast cancer detection cycle is maintained unchanged, and the original breast cancer detection cycle is determined according to the corresponding relationship between the weight range of the breast cancer risk value of the specific risk factor, the risk value assessment range of the breast cancer risk value, and the detection cycle; If not, then analyze and obtain the risk factors whose decline is less than the preset range as the target risk factors, and calculate the ratio of the decline of the target risk factor to the preset range. According to the ratio of the decline of the target risk factor to the preset range and the weight of the target risk factor to the breast cancer risk value, calculate the adjustment coefficient of all target factors with respect to the breast cancer detection cycle, and then calculate the adjusted breast cancer detection cycle according to the adjustment coefficient and the original breast cancer detection cycle; Update the patient's breast cancer related testing schedule based on the finalized breast cancer testing cycle; Update the patient's breast cancer related testing schedule based on the finalized breast cancer testing cycle, including: Obtain relevant information from the patient's electronic medical records and extract key factors that affect breast cancer test results, including ongoing treatment plans for other diseases, specific drugs used, recent surgical history, and the severity of the patient's underlying disease; According to the correspondence between the influence degree value range of the preset key factors affecting the breast cancer detection results and the delay time, the overall delay time caused by the key factors affecting the breast cancer detection results is analyzed and determined; According to the overall delay time caused by the key factors affecting the breast cancer detection results and the breast cancer detection cycle determined by analysis, the breast cancer detection cycle is re-analyzed and the patient's breast cancer-related detection time planning table is re-formed.

2. A breast cancer risk management and control system according to claim 1, characterized in that: It also includes steps after collecting patient-related data and preprocessing the data, and before using the preset and trained random forest algorithm to train the model, as follows: The patients were divided into different age groups, including young, middle-aged and elderly groups; If the patient is in the young or middle-aged group, the original settings are maintained; If the patient was in the elderly group, variables associated with breast cancer risk were selected, and the stepwise regression method was used for variable screening to establish a preliminary multivariate regression model; The preprocessed data is divided into a training set and a validation set, and the multivariate regression model is trained on the training set. The performance of the multivariate regression model is adjusted by adjusting the parameters of the multivariate regression model until the accuracy of the multivariate regression model on the validation set reaches the preset accuracy within a preset number of consecutive times, and the training of the multivariate regression model is determined to be completed, and the regression coefficient corresponding to each risk factor is checked; According to the regression coefficient corresponding to each risk factor, the sum of the absolute values ​​of all regression coefficients is calculated, and the ratio of the absolute value of the regression coefficient of different risk factors to the sum of the absolute values ​​of all regression coefficients is calculated to determine the weight of each risk factor for breast cancer risk value; The breast cancer detection cycle is determined by analysis based on the correspondence between the weight range of the breast cancer risk value for the specific risk factors, the risk value assessment range within which the breast cancer risk value falls, and the detection cycle.

3. A breast cancer risk management and control system according to claim 1, characterized in that: The steps of analyzing and obtaining the risk factors with a decrease range less than a preset range as target risk factors are also included, which are as follows: Patients whose breast cancer risk values ​​resulting from risk factors alone do not decrease by the preset range are considered to be patients who need to be followed up; Start the follow-up process, contact the patient through intelligent voice methods, and obtain the patient's implementation results of quantitative advice information, including exercise duration and dietary adjustments; If the patient's execution result of the quantitative suggestion information does not match the quantitative content mentioned in the quantitative suggestion information, the patient is advised to execute it again according to the quantitative content mentioned in the quantitative suggestion information; If the patient's execution result on the quantitative advice information is consistent with the quantitative content mentioned in the quantitative advice information, the quantitative advice information is analyzed for health-related quantitative content not mentioned, and suggestions for other quantitative content are provided to be added to the quantitative advice information to form new quantitative advice information, which is then sent to the patient's terminal again.

4. A breast cancer risk management and control system according to claim 1, characterized in that: The method also includes the following steps after updating the patient's breast cancer related testing schedule according to the finalized breast cancer testing cycle: Collect specific information about patients' breast cancer-related tests and perform data preprocessing; Select features relevant to adjuvant treatment decisions from specific information collected on patients' breast cancer-related tests; Input the features related to adjuvant therapy decision-making into a pre-trained adjuvant therapy decision-making model, and output the result of whether adjuvant therapy is required and the treatment plan if adjuvant therapy is required, and the treatment plan if adjuvant therapy is required includes surgery and drug provision plan; If the result of adjuvant therapy is required and the treatment plan under adjuvant therapy is surgery, the patient's medical imaging data is obtained, and the contours of the tumor and surrounding tissues are extracted using an image segmentation algorithm; Based on the extracted contours of the tumor and surrounding tissues, a path planning algorithm is used to simulate the entry path and operating range of the surgical instrument, determine the surgical path and resection range, and thus form a surgical planning plan; If the output is a result that adjuvant therapy is needed and the treatment plan under adjuvant therapy is medication, the patient's genetic test results, drug sensitivity data and surgical plan are obtained, and based on the patient's genetic test results, drug sensitivity data and surgical plan, a preset drug matching algorithm is used to screen out suitable drug types and dosages as a drug provision plan.

5. A breast cancer risk management and control system according to claim 4, characterized in that: The breast cancer risk management system also includes steps after providing a surgical planning solution, as follows: The SHAP analysis method was used to analyze the contribution of various postoperative data in risk prediction; According to the preset weight coefficient, a dynamic weight is assigned to each postoperative data in combination with the SHAP contribution, trend stability score, and clinical pathway relevance score; Standardize the data of various indicators after surgery, and determine the expected recovery curve of each indicator at different stages after surgery. Calculate the score of each indicator based on the comparison between the standardized value of the indicator and the expected recovery curve. According to the importance of different indicators, assign corresponding weights to the scores of each indicator to calculate the comprehensive rehabilitation score. According to the standardized postoperative index data and the weight values ​​of dynamic weight allocation, the current risk value is obtained by weighted calculation, and the change rate of the current risk value relative to the baseline risk value is calculated to reflect the dynamic changes in the risk level; The risk change rate and recovery deviation are used as input variables of the fuzzy inference system, different fuzzy sets and membership functions are defined for each input variable, and the membership function of each set is determined; According to the membership degree of input variables, fuzzy rules are used for reasoning to obtain fuzzy output results, and defuzzification methods are used to convert the fuzzy output results into specific detection cycle adjustment values; According to the detection cycle adjustment value output by the fuzzy inference system, the current detection cycle is dynamically adjusted.

6. A breast cancer risk management and control system according to claim 1, characterized in that: Also included are steps after calculating the weight of each risk factor for breast cancer risk, as follows: Analyze whether complete data of patients reaching or exceeding the preset number of cases have been collected; If no, continue with the next steps; If yes, then select variables related to breast cancer risk, use stepwise regression method to screen variables, establish a preliminary multiple regression model, divide the preprocessed data into a training set and a validation set, train the multiple regression model on the training set, adjust the performance of the multiple regression model by adjusting the parameters of the multiple regression model, until the accuracy of the multiple regression model on the validation set reaches the preset accuracy within a preset number of consecutive times, determine that the multiple regression model training is completed, check the regression coefficient corresponding to each risk factor, calculate the sum of the absolute values ​​of all regression coefficients, and calculate the ratio of the absolute value of the regression coefficient of different risk factors to the sum of the absolute values ​​of all regression coefficients, and determine the weight of each risk factor for the breast cancer risk value; The risk value weights output by the random forest model and the risk value weights output by the multivariate regression model are input as new features into the trained decision tree fusion model, and the comprehensive risk weight assessment results are output; According to the correspondence between the comprehensive risk weight output by the decision tree fusion model, the risk value assessment range into which the breast cancer risk value falls, and the detection cycle, the breast cancer detection cycle is analyzed and determined.

7. A breast cancer risk management and control system according to claim 1, characterized in that: Data preprocessing includes the following steps: Clean the collected raw data, which are patient-related data; Standardize the data to eliminate the dimensional differences between different data types; The processed data were integrated into a format suitable for input into the breast cancer risk assessment model.

8. A computer storage medium, characterized in that: The method comprises a program that can be loaded and executed by a processor to implement a breast cancer risk management method in a breast cancer risk management system according to any one of claims 1 to 7.

Images