Medical data management method based on general surgery department big data

Abstract

The invention relates to the technical field of data management, discloses a medical data management method based on general surgery department big data, and remarkably improves the accuracy and interpretability of a prediction result through an innovative method combining a random forest model and an improved Shapley formula. Firstly, an accurate prediction result is generated by using a random forest model. And secondly, the specific contribution value of each pathological index to the prediction result is calculated based on the improved Shapley formula, the importance of each index is quantified in the process, the problem of low calculation efficiency of the traditional Shapley value is solved, and the analysis speed and practicability are greatly improved. By screening out the key indexes with high improvement contribution values, the method can accurately position the core factors influencing the prediction result, and provides a scientific basis for subsequent decision making.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a medical data management method based on general surgery big data. Background Art

[0002] With the rapid development of information technology, the medical industry has gradually achieved a transformation from traditional paper records to electronic and digital records. The widespread application of information systems such as hospital information systems (HIS), electronic medical records (EMR), laboratory information systems (LIS) and picture archiving and communication systems (PACS) has enabled a large amount of medical data to be efficiently stored and managed. However, these systems usually operate independently, resulting in serious data silos and difficulty in cross-system data integration and analysis. Big data technology provides a new solution to the above problems. By integrating and storing scattered data in a unified data warehouse, advanced data analysis tools and technologies (such as machine learning, natural language processing and deep learning) can be used to mine valuable information. This not only helps clinical decision support and personalized treatment plan formulation, but also optimizes the allocation of medical resources. General surgery, as an important department in the hospital, involves a large number of surgeries and diagnosis and treatment work, and has accumulated a wealth of case materials and surgical data. These data include patients' medical history, diagnosis results, surgical procedures and postoperative recovery. Effective management and utilization of these data are crucial to improving the quality and efficiency of medical services. Especially in terms of treatment plan optimization, how to use existing data to improve and optimize treatment plans has become the key.

[0003] In the prior art, the risk probability that affects the disease is predicted and the key factors are obtained through the random forest model, and intervention measures are generated based on the key factors. However, after the random forest model obtains the prediction result, the prediction result is also explained by the Shapley value, that is, the contribution of the model input data to the prediction result is calculated. However, there are certain errors in the prediction process of the model, so that the data with high risk probability may correspond to a lower contribution value, resulting in inaccurate determination of key indicators. The plan generated based on inaccurate key indicators cannot reduce the disease risk to the greatest extent, and thus cannot guarantee that the intervention effect of the plan on the disease risk reaches the ideal. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a medical data management method based on general surgery big data, comprising: Step 1, obtaining patient data and preprocessing; the patient data includes several pathological indicators; Step 2: select a number of training samples from the preprocessed patient data and label each training sample; the label includes the disease type and the risk probability of the pathological index for the disease type; Step 3, construct a random forest model, use all training samples with calibration labels as training sets to train the random forest model, and obtain a trained random forest model; Acquire the patient's real-time data and input it into the trained random forest model to obtain a prediction result; the prediction result includes the risk probability of each pathological indicator for the current disease type; calculate the improved Shapley formula based on the Shapley formula, calculate the improvement contribution value of each pathological indicator in the patient's real-time data to the prediction result through the improved Shapley formula, calculate the comprehensive score according to the improvement contribution value of each pathological indicator in the patient's real-time data to the prediction result and the risk probability of each pathological indicator in the patient's real-time data for the current disease type, and arrange them from high to low, and take the pathological indicators corresponding to the first 2 / 3 of the comprehensive scores as key indicators; Step 4: Generate a preliminary plan based on the prediction results: disease type, patient real-time data, key indicators, risk probability of key indicators for the current disease type, and intervention measures; and execute the preliminary plan to obtain the key indicators for execution; Step 5: Based on the pathological indicators before executing the preliminary plan and each key indicator after executing the preliminary plan, calculate the intervention characteristic value of the key indicator; define an optimization goal, build an optimization function based on the intervention characteristic value, and use the optimization algorithm to solve the optimal solution of the optimization function. The optimal solution is the optimization plan.

[0005] Furthermore, an improved Shapley formula is calculated based on the Shapley formula, which specifically includes the following steps: Step 31, extracting each pathological index from the patient's real-time data, and generating a feature subset that does not include the current pathological index based on each pathological index; obtaining the predicted values ​​of each pathological index and each feature subset at multiple moments through the trained random forest model; Step 32, based on the predicted values ​​of each pathological index and the feature subset excluding the current pathological index at multiple moments, the initial contribution value of the current pathological index and the feature subset excluding the current pathological index is calculated by Shapley's formula; Step 33, determining a combination weight for the current pathological index and the feature subset that does not include the current pathological index; Step 34, calculating the mutual information between the current pathological index at the current moment and the feature subset that does not include the current pathological index; Step 35, obtaining an improved Shapley formula according to the initial contribution value, the combination weight and the mutual information to calculate the improved contribution value.

[0006] Further, determining the combination weight includes the following steps: Step 331, calculating the variance according to the patient data in step 1 and the current pathological index at the current moment; Step 332, determining the initial weight of the current pathological indicator and each pathological indicator in the feature subset that does not include the current pathological indicator; Step 333, calculating the correlation strength value between the current pathological index at the current moment and each pathological index in the feature subset that does not include the current pathological index; Step 334, calculating the combined weight according to the initial weight, the correlation strength value and the variance.

[0007] Furthermore, the calculation formula for the comprehensive score is: ; In the formula, represents the comprehensive score of the i-th pathological index, represents the initial contribution value of the i-th pathological index, represents the risk probability of the i-th pathological indicator for the current disease type, represents the mutual information between the i-th pathological index and the feature subset S that does not contain the current pathological index, represents the maximum mutual information between the i-th pathological index and the feature subset S that does not contain the current pathological index, represents the variance of the i-th pathological index at the current time t, represents the maximum variance of the i-th pathological index at the current time t, represents the combined weight of the i-th pathological index at the current time t and the feature subset that does not include the current pathological index, and F represents the set of feature subsets and / or pathological indexes.

[0008] Furthermore, the calculation formula of the combined weight is: ; In the formula, represents the correlation strength value between the i-th pathological index at the current time t and the j-th pathological index in the feature subset that does not contain the current pathological index, represents the initial weight of the i-th pathological index and the j-th pathological index in the feature subset that does not contain the current pathological index, represents the adjustment factor for the correlation strength value, Represents the adjustment factor for the variance.

[0009] Furthermore, based on the pathological indicators before the implementation of the preliminary plan and the key indicators after the implementation of the preliminary plan, the intervention characteristic values ​​of the key indicators are calculated, which specifically includes the following steps: Step 51, obtaining the characteristic value of each pathological indicator before executing the preliminary plan; Step 52, obtaining characteristic values ​​of the key indicators after the preliminary plan is executed, and calculating characteristic changes of the key indicators based on the characteristic values ​​of the key indicators after the preliminary plan is executed and the characteristic values ​​of the key indicators before the preliminary plan is executed; Step 53, based on the characteristic change amount and the characteristic value of each pathological indicator before executing the preliminary plan, the intervention characteristic value of the key indicator is obtained.

[0010] Furthermore, the optimization function is: ; In the formula, E represents the optimization function, min represents the minimization process, represents the weight of the kth key indicator, Represents the weight of the kth key indicator and the Lth key indicator, represents the eigenvalue of the kth key indicator, Represents the characteristic change of the kth key indicator, represents the eigenvalue of the Lth key indicator, represents the characteristic change of the Lth key indicator, n represents the total number of key indicators, and b is a constant greater than 0.

[0011] Furthermore, the optimization goal is to minimize the health risks of patients.

[0012] Furthermore, the improved Shapley formula is: ; In the formula, represents the improvement contribution value of the i-th pathological index at the current time t, F represents the set of feature subsets and / or pathological indicators, represents the combined weight of the i-th pathological index at the current time t and the feature subset that does not contain the current pathological index, represents the initial contribution value of the i-th pathological index, represents the mutual information between the i-th pathological index and the feature subset S that does not contain the current pathological index, Represents the adjustment factor.

[0013] The embodiments of the present invention have the following technical effects: The present invention significantly improves the accuracy and interpretability of prediction results by combining the innovative method of random forest model and improved Shapley formula. First, accurate prediction results are generated by using random forest model. Secondly, the specific contribution value of each pathological index to the prediction result is calculated based on the improved Shapley formula. This process not only quantifies the importance of each index, but also overcomes the problem of low efficiency of traditional Shapley value calculation, greatly improving the analysis speed and practicality. By screening out key indicators with high improved contribution values, the present invention can accurately locate the core factors affecting the prediction results and provide a scientific basis for subsequent decision-making. Further, the preliminary scheme generated based on key indicators has clear pertinence and feasibility, and through dynamic monitoring and feedback of key indicators after implementation, the optimization function is constructed to iteratively optimize the preliminary scheme to ensure that the final scheme achieves the best effect in practical application. In summary, the present invention shows significant advantages in improving prediction accuracy, enhancing scheme optimization capability and reducing implementation risks, and has important theoretical value and broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 It is a flow chart of a medical data management method based on general surgery big data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0017] Figure 1 Flowchart of a medical data management method based on general surgery big data provided by an embodiment of the present invention. Figure 1 , specifically including: Step 1: Obtain patient data and perform preprocessing; the patient data includes several pathological indicators.

[0018] Acquire patient data from electronic health information systems, laboratory testing equipment, wearable medical devices, medical imaging data, etc. Preprocessing includes: Data cleaning: Deleting or filling missing values: Missing data can be filled by using mean filling, interpolation or model-based prediction methods.

[0019] Remove outliers: Use statistical methods to identify and remove data points that deviate significantly from the normal range.

[0020] Data standardization / normalization: Convert data of different dimensions to the same scale for subsequent modeling and analysis.

[0021] Feature selection and dimensionality reduction: Use methods such as principal component analysis (PCA) or Lasso regression to screen out the features that have the greatest influence on the prediction target.

[0022] Pathological indicators include at least: blood-related indicators: blood routine: white blood cell count (WBC), red blood cell count (RBC), hemoglobin (Hb), platelet count (PLT).

[0023] Biochemical indicators: glucose (Glucose), total cholesterol (TC), triglycerides (TG), high-density lipoprotein (HDL), low-density lipoprotein (LDL).

[0024] Liver function indicators: alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase (ALP), total bilirubin (TBIL).

[0025] Renal function indicators: Creatinine, urea nitrogen (BUN), uric acid (Uric Acid).

[0026] Cardiovascular indicators: heart rate (HR), blood pressure (SBP, DBP), blood lipid levels (TC, TG), C-reactive protein (CRP).

[0027] Immunological indicators: C-reactive protein (CRP), immunoglobulins (IgA, IgG, IgM), complement (C3, C4).

[0028] Tumor markers: carcinoembryonic antigen (CEA), alpha-fetoprotein (AFP), carbohydrate antigens (CA125, CA19-9).

[0029] Other special indicators: Inflammatory factors: interleukin-6 (IL-6), tumor necrosis factor-α (TNF-α).

[0030] Genetic information: gene mutation sites, single nucleotide polymorphism (SNP), etc.

[0031] Step 2: select several training samples from the preprocessed patient data and label each training sample; the label includes the disease type and the risk probability of the pathological indicator for the disease type.

[0032] Divide patient data into different groups according to disease type. For example, for diabetes prediction tasks, patients can be divided into two groups: "diabetic patients" and "non-diabetic patients". Example: Extract patient data diagnosed with diabetes in the past year from the hospital database as positive samples, and randomly extract the same number of healthy people as negative samples. Clearly mark the disease category to which each sample belongs, and mark the risk contribution probability of each pathological indicator to a specific disease type through clinical expert evaluation or statistical analysis methods.

[0033] Step 3: Build a random forest model, use all training samples with calibration labels as training sets to train the random forest model, and obtain a trained random forest model.

[0034] Obtain the patient's real-time data and input it into the trained random forest model to obtain the prediction results; the prediction results include the risk probability of each pathological indicator for the current disease type. Based on the Shapley formula, the improved Shapley formula is calculated, and the improved contribution value of each pathological indicator in the patient's real-time data to the prediction result is calculated by the improved Shapley formula: Step 31, extract each pathological indicator from the patient's real-time data, and generate a feature subset that does not include the current pathological indicator based on each pathological indicator; obtain the predicted values ​​of each pathological indicator and each feature subset at multiple moments through the trained random forest model.

[0035] Step 32, based on the predicted values ​​of each pathological index and the feature subset excluding the current pathological index at multiple moments, the initial contribution value of the current pathological index and the feature subset excluding the current pathological index is calculated by Shapley formula.

[0036] This embodiment obtains the real-time data of the patient at multiple moments for prediction, which can not only capture the changing trend of pathological indicators over time, but also provide more comprehensive and dynamic data support for the calculation of improved Shapley values. Compared with the data at a single moment, the multi-moment data can reflect the volatility and stability of the indicators in different time periods, thereby generating more accurate initial contribution values. These initial contribution values, as the basis for improving the calculation of Shapley values, can significantly improve the accuracy and reliability of subsequent analysis. The initial contribution values ​​generated based on multi-moment data can better reflect the long-term impact of each pathological indicator on the disease prediction results, and avoid the deviation caused by the randomness or noise of single-time point data. In addition, this dynamic analysis method helps to identify the time-dependent characteristics of key indicators, for example, some indicators may only have a significant contribution to the disease risk at a specific stage. Therefore, the calculation of the initial contribution value is optimized using multi-moment data to improve the calculation efficiency of the improved Shapley value.

[0037] The Shapley formula is: ; in, represents the initial contribution value of the i-th pathological index, represents the number of pathological indicators in the feature subset, F represents the set of feature subsets and / or pathological indicators, represents the number of pathological indicators contained in the set representing feature subsets and / or pathological indicators, Represents the predicted value of all pathological indicators, Represents the predicted value of the feature subset that does not contain the current pathological index i.

[0038] Step 33, determining a combined weight for the current pathological index and the feature subset that does not include the current pathological index: Step 331, calculating the variance according to the patient data in step 1 and the current pathological index at the current moment.

[0039] The variance is used to quantify the degree of change of each pathological index. All data of each pathological index are collected from the patient data in step 1 and the real-time data of the patient at the current moment, and the variance is calculated.

[0040] Step 332: determine the initial weight of the current pathological indicator and each pathological indicator in the feature subset that does not include the current pathological indicator.

[0041] The initial weight is obtained based on the variance normalization in the above steps. The variance contribution rate of each indicator is obtained by normalization. The larger the variance, the wider the variation range of the indicator, and the more important it may be for disease prediction. Therefore, this embodiment assigns the initial weight based on the variance contribution rate.

[0042] Step 333: Calculate the correlation strength value between the current pathological index and each pathological index in the feature subset that does not include the current pathological index at the current moment.

[0043] The correlation strength values ​​were calculated by Pearson's correlation coefficient.

[0044] Step 334, calculate the combined weight according to the initial weight, the correlation strength value and the variance ; ; In the formula, represents the correlation strength value between the i-th pathological index at the current time t and the j-th pathological index in the feature subset that does not contain the current pathological index, represents the initial weight of the i-th pathological index and the j-th pathological index in the feature subset that does not contain the current pathological index, represents the adjustment factor for the correlation strength value, Represents the adjustment factor for the variance.

[0045] in, , this part represents the exponential decay of the correlation strength value between the current pathological index i and other pathological indexes j in the feature subset. In machine learning, overfitting is a common problem, that is, the model fits the training data too well, so that it performs poorly when faced with new data. Indicators with high correlation may cause the model to rely too much on certain specific data patterns or noise rather than real potential relationships. By reducing the weights of indicators with strong correlation, the model can be prompted to consider more relatively independent indicators that can provide additional information, thereby enhancing the generalization ability of the model and making it perform better on unseen data. Therefore, this embodiment reduces the weights of pathological indicators with strong correlation strength through exponential decay.

[0046] , which partly represents the variance of the current pathological index i at the current moment, and the influence of on the weight. An indicator with a larger variance indicates that its values ​​are more dispersed in the data set, rather than concentrated around a specific value. This dispersion may reflect the contribution of the indicator to the diversity and complexity of the target variable. Therefore, from the perspective of information content, a larger variance often means that the indicator contains more information about the predicted target, and therefore should be given a higher weight.

[0047] Step 34, calculating the mutual information between the current pathological index at the current moment and the feature subset that does not include the current pathological index.

[0048] Step 35, based on the initial contribution value, the combination weight and the mutual information, an improved Shapley formula is obtained to calculate the improved contribution value. The specific formula is as follows: ; In the formula, represents the improvement contribution value of the i-th pathological index at the current time t, F represents the set of feature subsets and / or pathological indicators, represents the combined weight of the i-th pathological index at the current time t and the feature subset that does not contain the current pathological index, represents the initial contribution value of the i-th pathological index, represents the mutual information between the i-th pathological index and the feature subset S that does not contain the current pathological index, Represents the adjustment factor.

[0049] The combined weight reflects the correlation and variance between the current pathological index and other indexes in the feature subset, ensuring that the importance of each index is dynamically adjusted at different time points; the introduction of time series data enables the model to capture the trend of pathological indexes changing over time, enhancing the timeliness and accuracy of the prediction results; mutual information quantifies the dependency between the current pathological index and the feature subset, further optimizing the model's ability to handle complex interactions. This comprehensive consideration improves the prediction accuracy of the model.

[0050] Based on the improvement contribution value of each pathological indicator in the patient's real-time data to the prediction result and the risk probability of each pathological indicator in the patient's real-time data for the current disease type, a comprehensive score is calculated and arranged from high to low, and the pathological indicators corresponding to the first 2 / 3 of the comprehensive scores are used as key indicators.

[0051] The formula for calculating the comprehensive score is as follows: ; In the formula, represents the comprehensive score of the i-th pathological index, represents the initial contribution value of the i-th pathological index, represents the risk probability of the i-th pathological indicator for the current disease type, represents the mutual information between the i-th pathological index and the feature subset S that does not contain the current pathological index, represents the maximum mutual information between the i-th pathological index and the feature subset S that does not contain the current pathological index, represents the variance of the i-th pathological index at the current time t, represents the maximum variance of the i-th pathological index at the current time t, represents the combined weight of the i-th pathological index at the current time t and the feature subset that does not include the current pathological index, and F represents the set of feature subsets and / or pathological indexes.

[0052] in, , combining the initial contribution value and risk probability to ensure a balance between basic importance and disease relevance. ,Through the exponential function adjustment of the mutual information, the ,dependency between the current pathological index and other indexes is reflected, and the ,comparability among different indexes is ensured through normalization ,processing. ,The variance is introduced and the weight of the high variance indicators is enhanced through standardization,,ensuring the reflection of the importance of dynamic changes.

[0053] Step 4, based on the prediction results, generate a preliminary plan: disease type, patient real-time data, key indicators, risk probability of key indicators for the current disease type, and intervention measures; and execute the preliminary plan to obtain the execution key indicators.

[0054] Exemplarily, the corresponding intervention measures generated for diabetes are: Interventions targeting fasting blood sugar Dietary control: Patients are advised to reduce the intake of high-sugar, high-carbohydrate foods and increase the proportion of dietary fiber and high-quality protein.

[0055] Exercise plan: Develop a personalized exercise plan, such as 30 minutes of moderate-intensity aerobic exercise every day.

[0056] Drug treatment: Use hypoglycemic drugs as recommended by your doctor and monitor blood sugar levels regularly.

[0057] Health education: popularize diabetes management knowledge to patients and improve their self-management capabilities.

[0058] Interventions targeting glycated hemoglobin Long-term blood sugar control: A combination of diet, exercise, and medications to keep fasting blood sugar within the target range.

[0059] Regular monitoring: Test the glycated hemoglobin level every 3 months to evaluate the effectiveness of blood sugar control.

[0060] Psychological support: Providing counseling or support groups to help patients cope with the stress of chronic illness.

[0061] Interventions targeting insulin levels Insulin therapy: For patients with insufficient insulin secretion, exogenous insulin can be injected to supplement it.

[0062] Weight management: Lose weight and improve insulin sensitivity through proper diet and exercise.

[0063] Lifestyle adjustments: Avoid staying up late and overwork, and maintain a regular life and work schedule.

[0064] Interventions targeting C-reactive protein Anti-inflammatory diet: Foods rich in antioxidants are recommended to reduce the level of inflammation in the body.

[0065] Quit smoking and limit alcohol intake: Encourage patients to quit smoking and limit alcohol intake to reduce additional burden on the body.

[0066] Drug assistance: Use anti-inflammatory drugs to lower C-reactive protein levels when necessary.

[0067] Apply the intervention measures in the preliminary plan to the patient and guide them to implement them according to the plan. After the intervention measures have been implemented for a period of time, re-collect the patient's pathological index data as the key execution indicators. For example: fasting blood sugar: from 126mg / dL to 110 mg / dL; glycosylated hemoglobin: from 7.5% to 6.8%; insulin level: from 10 µIU / mL to 12 µIU / mL; C-reactive protein: from 5 mg / L to 3 mg / L.

[0068] Step 5: Based on the pathological indicators before the implementation of the preliminary plan and each key indicator after the implementation of the preliminary plan, calculate the intervention characteristic value of the key indicator; define an optimization goal, build an optimization function based on the intervention characteristic value, and use the optimization algorithm to solve the optimal solution of the optimization function. The optimal solution is the optimization plan. The optimization goal is to minimize the health risk of patients.

[0069] Among them, the intervention characteristic value of the key indicator is calculated by each key indicator after the implementation of the preliminary plan and the pathological indicator corresponding to the key indicator before the implementation of the preliminary plan, not all pathological indicators.

[0070] Further: Step 51, obtaining the characteristic value of each pathological indicator before executing the preliminary plan; The pathological index of this step refers to the pathological index corresponding to the key index.

[0071] Step 52, obtaining characteristic values ​​of the key indicators after the preliminary plan is executed, and calculating characteristic changes of the key indicators based on the characteristic values ​​of the key indicators after the preliminary plan is executed and the characteristic values ​​of the key indicators before the preliminary plan is executed; Step 53, based on the characteristic change amount and the characteristic value of each pathological indicator before executing the preliminary plan, the intervention characteristic value of the key indicator is obtained.

[0072] The optimization function is: ; In the formula, E represents the optimization function, min represents the minimization process, represents the weight of the kth key indicator, Represents the weight of the kth key indicator and the Lth key indicator, represents the eigenvalue of the kth key indicator, Represents the characteristic change of the kth key indicator, represents the eigenvalue of the Lth key indicator, represents the characteristic change of the Lth key indicator, n represents the total number of key indicators, and b is a constant greater than 0.

[0073] , which partly reflects the individual contribution of each key indicator, This part reflects the interaction between all key indicators and minimizes the objective function to seek the optimal solution and obtain the optimization plan. The implementation of the optimization plan can minimize the risk of patients' illness.

[0074] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A medical data management method based on general surgery big data, characterized in that: include: Step 1: Obtain patient data and perform preprocessing; Patient data include several pathological indicators; Step 2: select a number of training samples from the preprocessed patient data and label each training sample; the label includes the disease type and the risk probability of the pathological index for the disease type; Step 3, construct a random forest model, use all training samples with calibration labels as training sets to train the random forest model, and obtain a trained random forest model; Obtaining real-time patient data and inputting it into a trained random forest model to obtain prediction results; the prediction results include the risk probability of each pathological indicator for the current disease type; An improved Shapley formula is calculated based on the Shapley formula. The improved Shapley formula is used to calculate the improvement contribution value of each pathological indicator in the patient's real-time data to the prediction result. According to the improvement contribution value of each pathological indicator in the patient's real-time data to the prediction result and the risk probability of each pathological indicator in the patient's real-time data for the current disease type, a comprehensive score is calculated and arranged from high to low, and the pathological indicators corresponding to the first 2 / 3 of the comprehensive scores are used as key indicators; Step 4: Generate a preliminary plan based on the prediction results: disease type, patient real-time data, key indicators, risk probability of key indicators for the current disease type, and intervention measures; And implement the preliminary plan and obtain key execution indicators; Step 5, based on the pathological indicators before the implementation of the preliminary plan and each key indicator after the implementation of the preliminary plan, the intervention characteristic value of the key indicator is calculated; Define an optimization objective, build an optimization function based on the intervention eigenvalue, and use the optimization algorithm to solve the optimal solution of the optimization function. The optimal solution is the optimization plan.

2. A medical data management method based on general surgery big data according to claim 1, characterized in that: The improved Shapley formula is calculated based on the Shapley formula, which specifically includes the following steps: Step 31, extracting each pathological index from the patient's real-time data, and generating a feature subset that does not include the current pathological index based on each pathological index; obtaining the predicted values ​​of each pathological index and each feature subset at multiple moments through the trained random forest model; Step 32, based on the predicted values ​​of each pathological index and the feature subset excluding the current pathological index at multiple moments, the initial contribution value of the current pathological index and the feature subset excluding the current pathological index is calculated by Shapley's formula; Step 33, determining a combination weight for the current pathological index and the feature subset that does not include the current pathological index; Step 34, calculating the mutual information between the current pathological index at the current moment and the feature subset that does not include the current pathological index; Step 35, obtaining an improved Shapley formula according to the initial contribution value, the combination weight and the mutual information to calculate the improved contribution value.

3. A medical data management method based on general surgery big data according to claim 2, characterized in that: Determining the combination weights includes the following steps: Step 331, calculating the variance according to the patient data in step 1 and the current pathological index at the current moment; Step 332, determining the initial weight of the current pathological indicator and each pathological indicator in the feature subset that does not include the current pathological indicator; Step 333, calculating the correlation strength value between the current pathological index at the current moment and each pathological index in the feature subset that does not include the current pathological index; Step 334, calculating the combined weight according to the initial weight, the correlation strength value and the variance.

4. The medical data management method based on general surgery big data according to claim 3 is characterized in that: The formula for calculating the comprehensive score is: ； In the formula, represents the comprehensive score of the i-th pathological index, represents the initial contribution value of the i-th pathological index, represents the risk probability of the i-th pathological indicator for the current disease type, represents the mutual information between the i-th pathological index and the feature subset S that does not contain the current pathological index, represents the maximum mutual information between the i-th pathological index and the feature subset S that does not contain the current pathological index, represents the variance of the i-th pathological index at the current time t, represents the maximum variance of the i-th pathological index at the current time t, represents the combined weight of the i-th pathological index at the current time t and the feature subset that does not include the current pathological index, and F represents the set of feature subsets and / or pathological indexes.

5. The medical data management method based on general surgery big data according to claim 4 is characterized in that: The formula for calculating the combined weight is: ； In the formula, represents the correlation strength value between the i-th pathological index at the current time t and the j-th pathological index in the feature subset that does not contain the current pathological index, represents the initial weight of the i-th pathological index and the j-th pathological index in the feature subset that does not contain the current pathological index, represents the adjustment factor for the correlation strength value, Represents the adjustment factor for the variance.

6. The medical data management method based on general surgery big data according to claim 1 is characterized in that: Based on the pathological indicators before the implementation of the preliminary plan and the key indicators after the implementation of the preliminary plan, the intervention characteristic values ​​of the key indicators are calculated, which specifically includes the following steps: Step 51, obtaining the characteristic value of each pathological indicator before executing the preliminary plan; Step 52, obtaining characteristic values ​​of the key indicators after the preliminary plan is executed, and calculating characteristic changes of the key indicators based on the characteristic values ​​of the key indicators after the preliminary plan is executed and the characteristic values ​​of the key indicators before the preliminary plan is executed; Step 53, based on the characteristic change amount and the characteristic value of each pathological indicator before executing the preliminary plan, the intervention characteristic value of the key indicator is obtained.

7. The medical data management method based on general surgery big data according to claim 1 is characterized in that: The optimization function is: ； In the formula, E represents the optimization function, min represents the minimization process, represents the weight of the kth key indicator, represents the weight of the kth key indicator and the Lth key indicator, represents the eigenvalue of the kth key indicator, Represents the characteristic change of the kth key indicator, represents the eigenvalue of the Lth key indicator, represents the characteristic change of the Lth key indicator, n represents the total number of key indicators, and b is a constant greater than 0.

8. The medical data management method based on general surgery big data according to claim 1 is characterized in that: The optimization goal is to minimize the health risks to patients.

9. The medical data management method based on general surgery big data according to claim 1 is characterized in that: The improved Shapley formula is: ； In the formula, represents the improvement contribution value of the i-th pathological index at the current time t, F represents the set of feature subsets and / or pathological indicators, represents the combined weight of the i-th pathological index at the current time t and the feature subset that does not contain the current pathological index, represents the initial contribution value of the i-th pathological index, represents the mutual information between the i-th pathological index and the feature subset S that does not contain the current pathological index, Represents the adjustment factor.

Images