Insulin resistance prediction method, system, equipment, medium and program product

Abstract

The invention discloses an insulin resistance prediction method, system and device, a medium and a program product, and the method comprises the steps: classifying an original data set into cost feature data and cost-free feature data, obtaining a first prediction model and a second prediction model, the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and the second prediction model is obtained by training based on the cost-free feature data, and determining a first type of users and a second type of users in the to-be-predicted users, and inputting the first type of user data and the second type of user data into the first prediction model and the second prediction model respectively to carry out insulin resistance prediction, so that corresponding prediction models are provided for different user groups, and accurate prediction of insulin resistance is realized in combination with questionnaire data and medical data. High-cost insulin resistance detection is not needed, so that the medical cost is effectively reduced, and the risk screening capability is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an insulin resistance prediction method, system, device, medium and program product. Background Art

[0002] With the change of lifestyle and the increase of chronic diseases, the prevalence of insulin resistance is becoming increasingly serious. Insulin resistance (IR) has become an important challenge facing the field of public health. Insulin resistance refers to the state in which the biological effect of insulin on the body is weakened. It is also the core pathophysiological factor of many diseases such as type 2 diabetes, cardiovascular disease and metabolic syndrome. In this context, the need for early identification and intervention of insulin resistance is becoming increasingly urgent.

[0003] However, traditional insulin resistance detection methods, such as the Insulin Tolerance Test (ITT) and the Euglycemic Hyperinsulinemic Clamp, are difficult to implement on a large scale due to their complexity, invasiveness and high cost, and therefore have limitations. Due to individual differences in physiology and environment between different subjects, the current overly expensive insulin resistance detection methods cannot capture the potential risks of insulin resistance, and therefore cannot identify early signs of insulin resistance, resulting in low early screening capabilities for insulin resistance. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, system, device, medium and program product for predicting insulin resistance, aiming to solve the technical problem that the existing technology uses high-cost insulin resistance detection methods to capture the potential risks of insulin resistance, thereby identifying early signs of insulin resistance, resulting in low early screening capabilities for insulin resistance.

[0005] To achieve the above object, the present invention provides a method for predicting insulin resistance, which comprises the following steps: Acquire an original data set, the original data set including sample data and label data corresponding to the sample data, the sample data including user medical data and user questionnaire data; Performing feature classification on the original data set to obtain data with cost features and data without cost features; Training a pre-built original model based on the cost feature data and the cost-free feature data to obtain a first prediction model and a second prediction model, wherein the original model includes an integrated tree model, the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and the second prediction model is obtained by training based on the cost-free feature data; Classifying the users to be predicted, determining the first type of users and the second type of users among the users to be predicted, and acquiring the first type of user data and the second type of user data, wherein the first type of user data includes the user questionnaire data and the user medical data of the first type of users, and the second type of user data includes the user questionnaire data of the second type of users; The first type of user data is input into the first prediction model for insulin resistance prediction, and the second type of user data is input into the second prediction model for insulin resistance prediction, to obtain prediction results for the first type of users and prediction results for the second type of users.

[0006] Optionally, the training of a pre-built original model based on the cost feature data and the cost-free feature data to obtain a first prediction model and a second prediction model includes: Training a plurality of pre-constructed original models based on the cost feature data and the cost-free feature data to obtain a plurality of first candidate models and a plurality of second candidate models, wherein the first candidate models are obtained by training based on the cost feature data and the cost-free feature data, and the second candidate models are obtained by training based on the cost-free feature data; Evaluate each first candidate model and each second candidate model to obtain a candidate evaluation result; Performing a correlation analysis on the cost feature data and the cost-free feature data, and performing feature screening on the cost feature data and the cost-free feature data based on the correlation analysis result and the candidate evaluation result to obtain first target data and second target data; The first candidate model and the second candidate model are trained according to the first target data and the second target data to obtain a first prediction model and a second prediction model, wherein the first prediction model is obtained by training based on the first target data and the second target data, and the second prediction model is obtained by training based on the second target data.

[0007] Optionally, the correlation analysis result includes a continuous feature analysis result and a discrete feature analysis result; performing correlation analysis on the cost feature data and the cost-free feature data, and performing feature screening on the cost feature data and the cost-free feature data based on the correlation analysis result and the candidate evaluation result to obtain the first target data and the second target data, includes: Determining continuous feature data and discrete feature data in the cost feature data and the cost-free feature data; Determining a linear correlation coefficient between each continuous feature in the continuous feature data, and performing a correlation analysis on the continuous feature data based on the linear correlation coefficient to obtain a continuous feature analysis result; Performing a chi-square test on each discrete feature in the discrete feature data to obtain a discrete feature analysis result; Performing correlation dimension reduction on the cost feature data and the cost-free feature data based on the continuous feature analysis result and the discrete feature analysis result; Performing importance evaluation on each feature in the cost feature data and the cost-free feature data according to the correlation dimension reduction result and the candidate evaluation result; Based on the importance evaluation result, the cost feature data and the cost-free feature data are feature screened to obtain the first target data and the second target data.

[0008] Optionally, the classifying the users to be predicted, determining the first type of users and the second type of users among the users to be predicted, and acquiring the first type of user data and the second type of user data includes: Classifying the users to be predicted, and determining a first type of users and a second type of users among the users to be predicted; Generate a first type of questionnaire text based on the first target data and the second target data, and generate a second type of questionnaire text based on the second target data; Sending the first type of questionnaire text to the first type of users, and sending the second type of questionnaire text to the second type of users; Acquire a first type of answer text fed back by the first type of users based on the first type of questionnaire text and a second type of answer text fed back by the second type of users based on the second type of questionnaire text; Performing semantic analysis on the first type of answer text to obtain first type of user data; Perform semantic analysis on the second type of answer text to obtain second type of user data.

[0009] Optionally, obtaining the original data set includes: Collect user questionnaire data and user medical data; Aggregating the user questionnaire data and the user medical data based on user identities of the user questionnaire data and the user medical data to obtain an initial multidimensional data set; Performing data cleaning on the initial multidimensional data set according to the user identity identifier to obtain a candidate multidimensional data set; Performing dependency analysis on the candidate multidimensional data set to obtain dependency relationship information between features in the candidate multidimensional data set; Filling missing data in the candidate multidimensional data set based on the dependency information; The candidate multidimensional datasets filled with missing data are standardized to obtain the original dataset.

[0010] Optionally, the step of inputting the first type of user data into the first prediction model to predict insulin resistance, and inputting the second type of user data into the second prediction model to predict insulin resistance, and obtaining the prediction results of the first type of users and the second type of users, comprises: Based on the prediction results of the first type of users and the prediction results of the second type of users, the first type of users and the second type of users are classified into risk categories to determine high-risk users and low-risk users; Performing semantic analysis on the answer texts of the high-risk user and the low-risk user to obtain user answer information; Generate a resistance question set according to a pre-constructed insulin resistance knowledge graph, wherein the insulin resistance knowledge graph includes medical knowledge information, symptom information, risk factor information, and diagnostic criteria information of insulin resistance; Determining the degree of text matching between the user answer information of the high-risk user and the low-risk user and the resistance question set based on a deep interactive text matching model; Insulin resistance is determined for the high-risk user and the low-risk user according to the text matching degree.

[0011] In addition, to achieve the above object, the present invention also provides an insulin resistance prediction system, the insulin resistance prediction system comprising: A data acquisition module, used to acquire an original data set, wherein the original data set includes sample data and label data corresponding to the sample data, wherein the sample data includes user medical data and user questionnaire data; A feature classification module, used for performing feature classification on the original data set to obtain cost feature data and cost-free feature data; A model training module, used for training a pre-built original model based on the cost feature data and the cost-free feature data to obtain a first prediction model and a second prediction model, wherein the original model includes an integrated tree model, the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and the second prediction model is obtained by training based on the cost-free feature data; A user classification module, used to classify the users to be predicted, determine the first type of users and the second type of users among the users to be predicted, and obtain the first type of user data and the second type of user data, wherein the first type of user data includes the user questionnaire data and user medical data of the first type of users, and the second type of user data includes the user questionnaire data of the second type of users; The insulin resistance prediction module is used to input the first type of user data into the first prediction model for insulin resistance prediction, and input the second type of user data into the second prediction model for insulin resistance prediction, to obtain the prediction results of the first type of users and the prediction results of the second type of users.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes an insulin resistance prediction device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the insulin resistance prediction method described above.

[0013] In addition, to achieve the above objectives, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the insulin resistance prediction method described above are implemented.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the insulin resistance prediction method described above are implemented.

[0015] The present invention obtains an original data set, wherein the original data set includes sample data and label data corresponding to the sample data, wherein the sample data includes user medical data and user questionnaire data, performs feature classification on the original data set, obtains cost feature data and cost-free feature data, trains a pre-built original model based on the cost feature data and the cost-free feature data, obtains a first prediction model and a second prediction model, wherein the original model includes an integrated tree model, wherein the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and wherein the second prediction model is obtained by training based on the cost-free feature data, classifies users to be predicted, determines a first type of user and a second type of user among the users to be predicted, and obtains first type of user data and second type of user data, wherein the first type of user data includes user questionnaire data and user medical data of the first type of users, and the second type of user data includes user questionnaire data of the second type of users, and wherein the first type of user data includes user questionnaire data of the second type of users. The first type of user data is input into the first prediction model for insulin resistance prediction, and the second type of user data is input into the second prediction model for insulin resistance prediction, to obtain the prediction results of the first type of users and the prediction results of the second type of users; because the present invention classifies the original data set into cost characteristic data and cost-free characteristic data, it can realize training corresponding prediction models for different user groups, thereby providing suitable prediction means for different user groups, ensuring the accuracy of prediction while effectively reducing computing resources, combining questionnaire data and medical data to achieve accurate prediction of insulin resistance, without the need to use high-cost insulin resistance detection means, effectively reducing medical costs, and predicting insulin resistance based on user questionnaire data and user medical data through a prediction model, so as to accurately capture the user's potential risks, effectively identify early signs of insulin resistance, and greatly improve the screening ability of insulin resistance risks, thereby formulating intervention measures for users' health problems in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 It is a structural schematic diagram of an insulin resistance prediction device in a hardware operating environment involved in an embodiment of the present invention; Figure 2 This is a schematic diagram of a flow chart of an embodiment of a method for predicting insulin resistance of the present invention; Figure 3 This is a schematic diagram of the data processing flow of an embodiment of the method for predicting insulin resistance of the present invention; Figure 4 This is a schematic diagram of the model training process in an embodiment of the method for predicting insulin resistance of the present invention; Figure 5 This is a schematic diagram of a data optimization process in an embodiment of a method for predicting insulin resistance of the present invention; Figure 6 This is a schematic diagram of the insulin resistance determination process in an embodiment of the insulin resistance prediction method of the present invention; Figure 7 A schematic diagram of a basic information questionnaire in an embodiment of the method for predicting insulin resistance of the present invention; Figure 8 A schematic diagram of a dietary habit questionnaire in an embodiment of a method for predicting insulin resistance of the present invention; Fig. 9 This is a schematic diagram of a health literacy questionnaire in an embodiment of the method for predicting insulin resistance of the present invention; Fig.10 This is a structural block diagram of an embodiment of the insulin resistance prediction system of the present invention.

[0019] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0021] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of an insulin resistance prediction device in the hardware operating environment involved in an embodiment of the present invention.

[0022] like Figure 1As shown, the insulin resistance prediction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage system independent of the aforementioned processor 1001.

[0023] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the insulin resistance prediction device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0024] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and an insulin resistance prediction program.

[0025] exist Figure 1 In the insulin resistance prediction device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the insulin resistance prediction device of the present invention can be set in the insulin resistance prediction device, and the insulin resistance prediction device calls the insulin resistance prediction program stored in the memory 1005 through the processor 1001, and executes the insulin resistance prediction method provided by the embodiment of the present invention.

[0026] The present invention provides a method for predicting insulin resistance. Figure 2 , Figure 2 Schematic diagram of a flow chart of an embodiment of a method for predicting insulin resistance of the present invention.

[0027] In this embodiment, the insulin resistance prediction method comprises the following steps: Step S10: Obtain the original data set.

[0028] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a terminal electronic device capable of realizing the above functions, etc. The following takes an insulin resistance prediction device (referred to as the prediction device) as an example to illustrate this embodiment and the following embodiments.

[0029] It should be noted that the original data set includes sample data and label data corresponding to the sample data, and the sample data includes user medical data and user questionnaire data.

[0030] It should be noted that the questionnaire data can be the questionnaire data answered by the user collected by the prediction device through a pre-built questionnaire system. The above questionnaire system focuses on the comprehensive collection of multi-dimensional data, covering key areas such as physiological characteristics, lifestyle and psychological state, so as to reveal the potential risk factors of insulin resistance. The questionnaire content includes basic physiological information such as age, gender, body mass index, lifestyle information such as eating habits, exercise frequency, smoking and drinking history, as well as the assessment of psychological states such as mood swings and sleep quality.

[0031] In some embodiments, the questionnaire system can generate corresponding questionnaire questions for the user based on the user's initial answers, such as user identity, user type, etc., so as to adjust the content and order of subsequent questions, thereby optimizing data collection efficiency without increasing the burden on the user.

[0032] In some embodiments, users can fill out questionnaires online through a self-service platform, and the system will process the user's answers in real time and generate preliminary health risk assessment results after submission. This convenience not only lowers the threshold for filling out questionnaires, but also enables users to obtain health feedback anytime and anywhere, improving the overall user experience.

[0033] In some embodiments, in order to ensure the integrity and reliability of the questionnaire data, the system introduces multiple optimization strategies in the data processing link. First, for the missing data in the questionnaire, the system uses methods such as mean filling, mode filling or logical inference to reduce the impact of missing data on model performance. Secondly, standardize all collected data and unify the data into a standard format and range to facilitate the subsequent use of machine learning models. In addition, to further improve the efficiency of the model, the system will screen the questionnaire data and eliminate features that are irrelevant to or have low contribution to the prediction of insulin resistance, thereby optimizing the data input structure.

[0034] It should be noted that the above user medical data may include two key dimensions: blood biochemical indicators and physical examination data. Blood biochemical indicators include fasting blood sugar, triglycerides, high-density lipoprotein and low-density lipoprotein, which are important biomarkers reflecting metabolism. Physical examination data include basic physiological information such as blood pressure, waist circumference and BMI. The introduction of the above data is intended to capture the complexity and diversity of insulin resistance, so that the system can perform more detailed assessments in high-risk individuals.

[0035] In some embodiments, the prediction device can collect user medical data and user questionnaire data, match the user questionnaire data with the medical data using individual identifiers (such as ID numbers), and integrate the data based on the matching results to form an overall view of multi-dimensional data fusion. The model reasonably classifies and optimizes data from different sources through hierarchical modeling, and processes easy-to-obtain and difficult-to-obtain data separately to avoid potential problems caused by data inconsistency.

[0036] In some embodiments, user questionnaire data may refer to the following Table 1, which is a questionnaire characteristic data table; user medical data may refer to Table 2, which is a medical characteristic data table: Further, refer to Figure 3 , Figure 3 This is a schematic diagram of a data processing flow according to an embodiment of the present invention. In order to improve the data quality of the original data set and thus improve the prediction efficiency, the above step S10 may include: Step S101: Collecting user questionnaire data and user medical data; Step S102: aggregating the user questionnaire data and the user medical data based on the user identity identifiers of the user questionnaire data and the user medical data to obtain an initial multidimensional data set; Step S103: performing data cleaning on the initial multidimensional data set according to the user identity to obtain a candidate multidimensional data set; Step S104: performing a dependency analysis on the candidate multidimensional data set to obtain dependency relationship information between features in the candidate multidimensional data set; Step S105: filling missing data in the candidate multidimensional data set based on the subordinate relationship information; Step S106: Standardize the candidate multidimensional data set filled with missing data to obtain the original data set.

[0037] In some embodiments, the prediction device can collect individual physiological and biochemical characteristic data through questionnaire data. After the data is collected, the questionnaire data and blood data collected at different times are merged and integrated into a unified data set according to the physical examination number and ID number, and then the duplicate data is randomly deduplicated according to the ID number, and some data that is difficult to encode is deleted.

[0038] In some embodiments, for missing data, the prediction device may view the missing values ​​of each feature from the feature dimension and perform visualization processing, and delete features with missing values ​​exceeding 30% of the total data.

[0039] It should be noted that features with a subordinate relationship cannot be treated as ordinary missing values, for example, features with a subordinate relationship: "Do you smoke?" The subordinate feature [how many cigarettes do you smoke every day, how many years have you continued to smoke, how long have you quit smoking]; the subordinate feature of "Do you drink alcohol": [what kind of alcohol do you drink, how many times a week, how much each time, how many years have you continued to drink, how long have you quit drinking]; the subordinate feature of "Do you take part in sports and exercise?" [exercise method, how many times a week, each exercise time, how many years have you persisted in exercising]; the subordinate feature of how you sleep: [main manifestations, reasons that affect sleep], among the features with a subordinate relationship, the number of missing values ​​of the [how long have you quit smoking, how long have you quit drinking] feature is too large, so it will be deleted directly, and the missing values ​​of other subordinate features with fewer missing values ​​are assigned to 0.

[0040] In some embodiments, for features that have no subordinate relationship and whose missing values ​​are less than 30%, continuous features are filled with the average value, and discrete features are filled with the mode; for features with a small number of missing values, rows with missing values ​​are directly deleted.

[0041] In some embodiments, considering the accuracy of medical data testing, the prediction device may check and replace the average values ​​of the four features [age, height, weight, waist circumference].

[0042] Step S20: performing feature classification on the original data set to obtain data with cost features and data without cost features.

[0043] It should be noted that the cost-based characteristic data can be characteristic data that is difficult to obtain in the original data set, such as biochemical index data, blood lipid index data, blood sugar index data, etc. The above-mentioned cost-free acquisition data can be data that is easy to obtain in the original data set, such as eating habits, smoking characteristics, drinking characteristics, etc.

[0044] In some embodiments, the prediction device can divide the features in the data set into costless features feature1 and costly features feature2, and further divide the costless features feature1 into physiological characteristics, disease history, dietary habits, smoking, drinking, exercise, work, psychological state, sleep and health monitoring, health habits and prevention, and health indicators; the costly features feature2 are divided into biochemical indicators, blood lipid indicators, blood sugar indicators, and protein tables. According to the difficulty of acquisition, the data is divided into two levels: easy-to-acquire data: feature1, and easy-to-acquire data + difficult-to-acquire data: feature1 + feature2.

[0045] Step S30: training the pre-built original model based on the cost feature data and the cost-free feature data to obtain a first prediction model and a second prediction model.

[0046] It should be noted that the original model includes an integrated tree model, the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and the second prediction model is obtained by training based on the cost-free feature data.

[0047] In some embodiments, the prediction device may construct multiple original integrated tree models, generate a training set and a test set based on the cost feature data and the cost-free feature data, train each original integrated data model based on the training set, test and evaluate each trained original integrated tree model based on the test set, and select the model with the best performance from the multiple original integrated tree models as the prediction model based on the test and evaluation results.

[0048] Further, refer to Figure 4 , Figure 4 This is a schematic diagram of a model training process in an embodiment of the present invention. In order to improve the model performance, the above step S30 may include: Step S301: training a plurality of pre-built original models based on the cost feature data and the cost-free feature data to obtain a plurality of first candidate models and a plurality of second candidate models; Step S302: Evaluate each first candidate model and each second candidate model to obtain a candidate evaluation result; Step S303: performing a correlation analysis on the cost feature data and the cost-free feature data, and performing feature screening on the cost feature data and the cost-free feature data based on the correlation analysis result and the candidate evaluation result to obtain first target data and second target data; Step S304: training the first candidate model and the second candidate model according to the first target data and the second target data to obtain a first prediction model and a second prediction model.

[0049] It should be noted that the first candidate model is obtained by training based on the cost feature data and the cost-free feature data, and the second candidate model is obtained by training based on the cost-free feature data. The first prediction model is obtained by training based on the first target data and the second target data, and the second prediction model is obtained by training based on the second target data.

[0050] In some embodiments, the prediction device can construct five ensemble tree models respectively, including, for example, catboost, RandomForest (RF), lightgbm, xgboost, and GradientBoostingCart (GBC). The ensemble tree model is an ensemble learning method that improves the overall performance and generalization ability of the model by constructing multiple base decision trees and integrating their prediction results. The key advantage of the ensemble tree model is that it can reduce the overfitting problem that a single decision tree may encounter, and by integrating the views of multiple models, it enhances the model's generalization ability for new data.

[0051] In some embodiments, the prediction device may use 80% of the data set as a training set and 20% as a test set for model training and evaluation. Through grid search, the optimal hyperparameter combination in the machine learning model is determined. The F1 score, accuracy, recall rate, precision and area under the curve (AUC) are calculated to evaluate the performance of these models. The above indicators can be used to evaluate the overall performance of the models and determine their applicability in clinical decision-making.

[0052] In some embodiments, the prediction device may first train multiple pre-built original models based on the cost-free feature data to obtain an initial model, then evaluate the initial model, train the initial model based on the initial evaluation result and the cost feature data to obtain a candidate model, then evaluate the candidate model, optimize and screen the cost feature data and the cost-free feature data based on the candidate evaluation result, remove data with lower importance and relevance, retain data with higher importance and relevance, obtain first target data and second target data, and train the candidate model based on the first target data and the second target data, wherein the first target data is obtained by optimizing and screening the cost feature data, and the second target data is obtained by optimizing and screening the cost-free feature data.

[0053] In some embodiments, based on data integration, the system trains and optimizes multi-source data through advanced machine learning algorithms to ensure the efficiency and reliability of the prediction model. To cope with the complexity and diversity of nonlinear feature relationships and high-dimensional data, the system uses a variety of integrated tree models (such as CatBoost and LightGBM) for modeling. Through a hierarchical data training strategy, the system models easily accessible questionnaire data and difficult-to-obtain medical data separately, and integrates them into a unified prediction framework to effectively reduce the impact of data differences on model performance, while ensuring the scientificity and stability of the overall prediction results.

[0054] Then, through the Bayesian optimization method, the system automatically finds the best combination of model hyperparameters, thereby significantly improving the accuracy and efficiency of the model. In addition, the system conducts in-depth feature importance analysis on the fused data to identify the key features that contribute most to the prediction of insulin resistance, such as fasting blood sugar, BMI and triglycerides, providing a reliable scientific basis for further clinical analysis.

[0055] Further, refer to Figure 5 , Figure 5 This is a schematic diagram of a data optimization process in an embodiment of the present invention. In order to improve data quality and thus improve model performance, the correlation analysis results include continuous feature analysis results and discrete feature analysis results. The above step S303 may include: Step S3031: determining continuous feature data and discrete feature data in the feature data with cost and the feature data without cost; Step S3032: determining a linear correlation coefficient between each continuous feature in the continuous feature data, and performing a correlation analysis on the continuous feature data based on the linear correlation coefficient to obtain a continuous feature analysis result; Step S3033: performing a chi-square test on each discrete feature in the discrete feature data to obtain a discrete feature analysis result; Step S3034: performing correlation dimension reduction on the cost feature data and the cost-free feature data based on the continuous feature analysis result and the discrete feature analysis result; Step S3035: performing importance evaluation on each feature in the feature data with cost and the feature data without cost according to the correlation dimension reduction result and the candidate evaluation result; Step S3036: Based on the importance evaluation result, feature screening is performed on the cost feature data and the cost-free feature data to obtain the first target data and the second target data.

[0056] It should be noted that the prediction device can reduce the overfitting problem of the model through sampling training, balance the category distribution, and improve the model's recognition ability for minority classes. The accuracy of the model after oversampling in the training set is improved.

[0057] In some embodiments, the prediction device can classify the cost feature data and the non-cost feature data to determine the continuous feature data and the discrete feature data, and use Pearson to perform correlation analysis on the continuous feature data and chi-square test to perform correlation analysis on the discrete data. Through the heat map, it is observed that there are strong correlation features in the modules of eating habits, smoking, exercise, drinking, biochemical indicators, blood lipid indicators, blood sugar indicators, and protein indicators.

[0058] For example, in the chi-square test, self-measurement of blood pressure and heart rate, eating animal offal, drinking several times a week, and actively acquiring medical knowledge are significantly correlated with the training data, while repression, depression, tension, difficulty in relaxing, anxiety, and restlessness are significantly unrelated to the training data.

[0059] For example, serum albumin, age, total bile acid, and low-density lipoprotein cholesterol are significantly unrelated to the training data, while creatinine, aspartate aminotransferase, and albumin ratio are significantly correlated with the training data. By observing the first four columns, it can be seen that the distribution of age, serum albumin, and other indicators is relatively concentrated, while the distribution range of creatinine, aspartate aminotransferase, and other characteristics is relatively wide. From the group mean and group standard deviation, it can be seen that as the training data increases, the mean values ​​of creatinine, total bile acid, aspartate aminotransferase, and total cholesterol are also increasing, that is, the training data is positively correlated with these characteristics, while the mean values ​​of serum albumin, albumin ratio, direct bilirubin, and total bilirubin decrease, indicating that the training data is negatively correlated with age.

[0060] In some embodiments, the prediction device can delete features that fail the statistical test, delete data with low relevance, and retain data with high relevance. In some embodiments, the features that pass the correlation test are analyzed, and the performance of each model is improved after the irrelevant features are removed from the observation model.

[0061] In some embodiments, the prediction device may perform correlation dimensionality reduction on the cost feature data and the cost-free feature data, for example, perform dimensionality reduction on three types of features with strong correlation in the "physiological characteristics": [body mass index BMI, height, weight, waist circumference], select the body mass index BMI, reduce the dimensionality of the two features with strong correlation [right upper arm systolic blood pressure, right upper arm diastolic blood pressure], and select "right upper arm systolic blood pressure".

[0062] In some embodiments, the prediction device can perform importance analysis on the feature data to quantify the importance of the feature data, screen the features based on the quantification results, and screen the best performing machine learning model based on the results of the model evaluation. The selected model is subjected to feature importance analysis to determine the impact of the feature on the prediction, and the importance of each feature is calculated based on the internal mechanism of the model.

[0063] For example, the feature data retained in the cost-free feature data may include: body mass index BMI, right upper arm systolic blood pressure, age, physical intensity at work, length of time sitting outside of work, staple food structure, how often to have a physical examination, do you eat fruit, do you drink milk, sleep time, self-measurement of blood pressure and heart rate, how many years of exercise, salt, gender, how much meat you eat on average per day, do you drink coffee, observe urination and defecation, beans and bean products, dietary tastes, carrying first aid medicines when going out, eating three meals on time, duration of each exercise, drinking sugary drinks, normal pulse, do you eat fatty meat, how many vegetables you eat on average per day, how many times you exercise per week, seat belts, and sun exposure.

[0064] The characteristic data retained in the cost characteristic data may include: fasting blood glucose (GLU), high-density lipoprotein cholesterol, triglycerides, creatinine, blood uric acid, alanine aminotransferase, total bilirubin, urea nitrogen, total bile acid, low-density lipoprotein cholesterol, serum albumin, aspartate aminotransferase, serum total protein, total cholesterol, albumin-globulin ratio, serum globulin, and direct bilirubin.

[0065] In some embodiments, the prediction device may find the optimal model hyperparameters through Bayesian optimization.

[0066] In some embodiments, the prediction device can provide feature importance analysis within the model, and use methods such as SHAP value to interpret the model. For example, the top five features of model feature importance and SHAP analysis are BMI (Body Mass Index, body mass index), SBP (Systolic Blood Pressure, systolic blood pressure), Saltintake (salt intake), Exercisetype (exercise type), Family history medicine (family medical history).

[0067] In some embodiments, the top five features ranked by model feature importance and SHAP analysis are BMI (Body Mass Index), FBG (Fasting Blood Glucose), HDL-C (High-Density Lipoprotein Cholesterol), TG (Triglycerides), and Cr (Creatinine).

[0068] In certain embodiments, for each prediction result, local explanation is provided to help understand the logic behind the specific prediction. When the BMI value is certain and less than -0.3 and the gender is female, at this moment, the contribution of BMI to the model is positive, and the insulin prediction value can increase accordingly. When the BMI value is certain and greater than -0.3, the SHAP value of BMI can gradually decrease, indicating that the negative effect of BMI on the model increases, and the insulin prediction value can decrease accordingly. When the SBP value is certain and less than -0.4, from the vertical point of view, the SHAP value of SBP increases gradually, indicating that people under the same SBP situation, along with the rise of BMI, SBP gradually increases for the positive effect of the model, and the insulin prediction value can increase accordingly. And when the SBP value is certain and greater than -0.4, the contribution of the SBP value to the model is negative.

[0069] Step S40: Classifying the users to be predicted, determining the first type of users and the second type of users among the users to be predicted, and acquiring the first type of user data and the second type of user data.

[0070] It should be noted that the first type of user data includes user questionnaire data and user medical data of the first type of users, and the second type of user data includes user questionnaire data of the second type of users.

[0071] It should be noted that the first type of user may be a user with medical data and questionnaire data such as fasting blood sugar and blood oxygen value, for example, the first type of user may be a medical staff. The second type of user is an ordinary user who only has daily data and questionnaire data such as height and weight.

[0072] It is understandable that, in this embodiment, the users to be predicted may be classified based on the identity type of the users and / or the type of data the users possess, and the user type of each user to be predicted may be determined, thereby determining the first type of users and the second type of users therein.

[0073] It should be understood that since different types of users have different types of data, this embodiment classifies the users to be predicted, thereby dividing the user groups and providing corresponding prediction methods for different types of users, thereby ensuring that the prediction accuracy is improved while reducing the computing load.

[0074] Furthermore, in order to accurately collect user data of the user to be predicted, the above step S40 may include: Step S401: Classifying the users to be predicted, and determining the first type of users and the second type of users among the users to be predicted; Step S402: Generate a first type of questionnaire text based on the first target data and the second target data, and generate a second type of questionnaire text based on the second target data; Step S403: sending the first type of questionnaire text to the first type of users, and sending the second type of questionnaire text to the second type of users; Step S404: obtaining a first type of answer text fed back by the first type of users based on the first type of questionnaire text and a second type of answer text fed back by the second type of users based on the second type of questionnaire text; Step S405: performing semantic analysis on the first type of answer text to obtain first type of user data; Step S406: Perform semantic analysis on the second type of answer text to obtain second type of user data.

[0075] It should be noted that the first type of user may be a user with medical data and questionnaire data such as fasting blood sugar and blood oxygen value, for example, the first type of user may be a medical staff. The second type of user is an ordinary user who only has daily data and questionnaire data such as height and weight.

[0076] It can be understood that this embodiment can classify the users to be predicted based on the user's identity type and / or the type of data the user possesses, determine the user type of each user to be predicted, thereby determining the first type of users and the second type of users therein, and generate corresponding questionnaire texts for different types of users.

[0077] In a specific implementation, the prediction device may send a first type of questionnaire text containing cost characteristic data and no cost characteristic data to a first type of user, and send a second type of questionnaire text containing only no cost characteristic data to a second type of user.

[0078] In some embodiments, the prediction device may generate a questionnaire text in combination with the first target data and the second target data obtained after optimizing the training data during the model training process. Because the first target data and the second target data are obtained after screening and cleaning the cost feature data and the cost-free feature data, generating the questionnaire text based on the first target data and the second target data can improve the accuracy of the questionnaire text and avoid generating unnecessary, unimportant features in the questionnaire text that have little help in the accuracy of the prediction results.

[0079] For example, the cost-effective features in the first type of questionnaire text may include: fasting blood glucose (GLU), high-density lipoprotein cholesterol, triglycerides, creatinine, blood uric acid, alanine aminotransferase, total bilirubin, urea nitrogen, total bile acid, low-density lipoprotein cholesterol, serum albumin, aspartate aminotransferase, serum total protein, total cholesterol, albumin-globulin ratio, serum globulin, direct bilirubin, etc.; the cost-free features in the first type of questionnaire text may include: body mass index BMI, right upper arm systolic blood pressure, age, physical intensity at work, length of time sitting outside of work, staple food structure, how often to do physical examinations, whether to eat fruits, drink milk, sleep time, self-measured blood pressure and heart rate, etc.

[0080] Step S50: input the first type of user data into the first prediction model to predict insulin resistance, and input the second type of user data into the second prediction model to predict insulin resistance, to obtain the prediction results of the first type of users and the prediction results of the second type of users.

[0081] It should be noted that the first prediction model is obtained by training based on cost feature data and cost-free feature data, and the first type of users are users to be predicted with cost-free feature data and cost feature data, so the user data of the first type of users are input into the first prediction model for insulin resistance prediction. The second prediction model is obtained by training based on cost-free feature data, and the second type of users are users to be predicted with cost-free feature data, so the user data of the second type of users are input into the second prediction model for insulin resistance prediction, thereby providing corresponding prediction means for different types of users, reducing the amount of calculation and improving the prediction accuracy.

[0082] It can be understood that this embodiment trains a deep learning model based on user questionnaire data and user medical data, thereby effectively reducing detection costs and reducing the invasiveness of detection, greatly improving the accessibility and efficiency of screening. This embodiment adopts non-invasive technology and low-cost detection methods to make the prediction of insulin resistance more convenient and economical, thereby providing a popular basis for early screening of insulin resistance.

[0083] In some embodiments, the prediction device can study and demonstrate the relationship between insulin resistance and diabetes incidence through cohort analysis to observe the risk of individuals developing diabetes under different insulin resistance states.

[0084] Further, refer to Figure 6 , Figure 6 This is a schematic diagram of the insulin resistance determination process in an embodiment of the present invention. In order to accurately identify the risk of insulin resistance, after the above step S50, the following may be included: Step S501: Based on the prediction results of the first type of users and the prediction results of the second type of users, the first type of users and the second type of users are classified into risk categories to determine high-risk users and low-risk users; Step S502: performing semantic analysis on the answer texts of the high-risk user and the low-risk user to obtain user answer information; Step S503: generating a resistance question set according to a pre-constructed insulin resistance knowledge graph; Step S504: determining the degree of text matching between the user answer information of the high-risk user and the low-risk user and the resistance question set based on the deep interactive text matching model; Step S505: determining insulin resistance of the high-risk user and the low-risk user according to the text matching degree.

[0085] It should be noted that the insulin resistance knowledge graph includes medical knowledge information, symptom information, risk factor information and diagnostic criteria information of insulin resistance.

[0086] In some embodiment sets, the prediction device identifies key information and biomarkers related to insulin resistance by performing detailed semantic analysis on the user's answer text.

[0087] Next, the prediction device can generate a set of resistance questions based on a pre-built insulin resistance knowledge graph, which contains medical knowledge, symptoms, risk factors, and diagnostic criteria related to insulin resistance, to generate a series of possible questions that will be used to further confirm the user's health status.

[0088] In some embodiments, the prediction device may pre-build a question similarity detection model, namely a deep interactive text matching model, for calculating the similarity between the user's answer and the question generated by the system. This model can evaluate the degree of matching between the user's answer and the set of questions related to insulin resistance, thereby determining whether the user's answer indicates the possibility of insulin resistance.

[0089] In some embodiments, if the prediction device determines that the user's answer indicates a risk of insulin resistance, it will push relevant analysis and suggestions to help the user understand their health status and may recommend further medical consultation or examination. If the user's answer is not related to insulin resistance, the prediction device will provide corresponding feedback, indicating that the answer is not relevant to the insulin resistance issue, thereby guiding the user to ask more specific questions.

[0090] In some embodiments, the prediction device can construct an automatic analysis system, which consists of two core subsystems: a question generation and similarity detection system and an analysis push system. The question generation and similarity detection system includes a question generation model based on medical knowledge and a deep interactive text matching model; the analysis push system includes an analysis model based on customer answers and a model that sorts the analysis results according to the matching score. Through the collaborative work of these two subsystems, the system can provide efficient and accurate automatic analysis services for insulin resistance problems.

[0091] In some embodiments, in order to achieve early screening of insulin resistance risk, the present invention has designed an efficient and scientific questionnaire system to collect basic health data of individuals in a non-invasive, economical and convenient manner. Through carefully designed questionnaire content, multi-dimensional data collection, and real-time processing technology, the system can quickly identify potential high-risk individuals and lay a solid foundation for subsequent medical data analysis. The questionnaire system focuses on the comprehensive collection of multi-dimensional data, covering key areas such as physiological characteristics, lifestyle, and psychological state to reveal potential risk factors for insulin resistance. The questionnaire content includes basic physiological information such as age, gender, body mass index, lifestyle information such as eating habits, exercise frequency, smoking and drinking history, and assessment of psychological states such as mood swings and sleep quality, with reference to Figure 7 , Figure 8 and Fig. 9 ,in, Figure 7 This is a diagram of the basic information questionnaire. Figure 8 This is a diagram of the dietary habits questionnaire. Fig. 9 Schematic diagram of the health literacy questionnaire.

[0092] This embodiment obtains an original data set, wherein the original data set includes sample data and label data corresponding to the sample data, wherein the sample data includes user medical data and user questionnaire data, performs feature classification on the original data set, obtains cost feature data and cost-free feature data, trains a pre-built original model based on the cost feature data and the cost-free feature data, obtains a first prediction model and a second prediction model, wherein the original model includes an integrated tree model, wherein the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and the second prediction model is obtained by training based on the cost-free feature data, classifies users to be predicted, determines a first type of user and a second type of user among the users to be predicted, and obtains first type of user data and second type of user data, wherein the first type of user data includes user questionnaire data and user medical data of the first type of users, and the second type of user data includes user questionnaire data of the second type of users, and the The first type of user data is input into the first prediction model for insulin resistance prediction, and the second type of user data is input into the second prediction model for insulin resistance prediction, to obtain the prediction results of the first type of users and the prediction results of the second type of users; because this implementation classifies the original data set into cost characteristic data and cost-free characteristic data, and realizes training corresponding prediction models for different user groups, thereby providing suitable prediction means for different user groups, ensuring the accuracy of prediction while effectively reducing computing resources, combining questionnaire data and medical data to achieve accurate prediction of insulin resistance, without the need to use high-cost insulin resistance detection methods, effectively reducing medical costs, and predicting insulin resistance based on user questionnaire data and user medical data through prediction models, so as to accurately capture the user's potential risks, effectively identify early signs of insulin resistance, and greatly improve the screening ability of insulin resistance risks, so as to formulate intervention measures for users' health problems in advance.

[0093] In addition, an embodiment of the present invention further proposes a computer-readable storage medium, on which an insulin resistance prediction program is stored. When the insulin resistance prediction program is executed by a processor, the steps of the insulin resistance prediction method described above are implemented.

[0094] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0095] The computer-readable storage medium may be included in the insulin resistance prediction device; or may exist independently without being assembled into the insulin resistance prediction device.

[0096] In addition, an embodiment of the present invention further provides a computer program product, including an insulin resistance prediction program, which implements the steps of the insulin resistance prediction method described above when executed by a processor.

[0097] The specific implementation of the computer program product of the present invention is basically the same as the embodiments of the above-mentioned insulin resistance prediction method, and will not be repeated here.

[0098] Reference Fig.10 , Fig.10 This is a structural block diagram of an embodiment of the insulin resistance prediction system of the present invention.

[0099] like Fig.10 As shown, the insulin resistance prediction system proposed in the embodiment of the present invention includes: A data acquisition module 10 is used to acquire an original data set, wherein the original data set includes sample data and label data corresponding to the sample data, wherein the sample data includes user medical data and user questionnaire data; A feature classification module 20 is used to perform feature classification on the original data set to obtain cost feature data and cost-free feature data; A model training module 30 is used to train a pre-built original model based on the cost feature data and the cost-free feature data to obtain a first prediction model and a second prediction model, wherein the original model includes an integrated tree model, the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and the second prediction model is obtained by training based on the cost-free feature data; A user classification module 40, configured to classify users to be predicted, determine first-type users and second-type users among the users to be predicted, and obtain first-type user data and second-type user data, wherein the first-type user data includes user questionnaire data and user medical data of the first-type users, and the second-type user data includes user questionnaire data of the second-type users; The insulin resistance prediction module 50 is used to input the first type of user data into the first prediction model for insulin resistance prediction, and input the second type of user data into the second prediction model for insulin resistance prediction, to obtain the prediction results of the first type of users and the prediction results of the second type of users.

[0100] This embodiment obtains an original data set, wherein the original data set includes sample data and label data corresponding to the sample data, wherein the sample data includes user medical data and user questionnaire data, performs feature classification on the original data set, obtains cost feature data and cost-free feature data, trains a pre-built original model based on the cost feature data and the cost-free feature data, obtains a first prediction model and a second prediction model, wherein the original model includes an integrated tree model, wherein the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and the second prediction model is obtained by training based on the cost-free feature data, classifies users to be predicted, determines a first type of user and a second type of user among the users to be predicted, and obtains first type of user data and second type of user data, wherein the first type of user data includes user questionnaire data and user medical data of the first type of users, and the second type of user data includes user questionnaire data of the second type of users, and the The first type of user data is input into the first prediction model for insulin resistance prediction, and the second type of user data is input into the second prediction model for insulin resistance prediction, to obtain the prediction results of the first type of users and the prediction results of the second type of users; because this implementation classifies the original data set into cost characteristic data and cost-free characteristic data, and realizes training corresponding prediction models for different user groups, thereby providing suitable prediction means for different user groups, ensuring the accuracy of prediction while effectively reducing computing resources, combining questionnaire data and medical data to achieve accurate prediction of insulin resistance, without the need to use high-cost insulin resistance detection methods, effectively reducing medical costs, and predicting insulin resistance based on user questionnaire data and user medical data through prediction models, so as to accurately capture the user's potential risks, effectively identify early signs of insulin resistance, and greatly improve the screening ability of insulin resistance risks, so as to formulate intervention measures for users' health problems in advance.

[0101] The insulin resistance prediction system provided by the present application adopts the insulin resistance prediction method in the above embodiment, which can solve the technical problem of insulin resistance prediction. Compared with the prior art, the beneficial effects of the insulin resistance prediction system provided by the present application are the same as the beneficial effects of the insulin resistance prediction method provided by the above embodiment, and other technical features in the insulin resistance prediction system are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0102] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0103] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0104] In addition, for technical details not fully described in this embodiment, reference can be made to the insulin resistance prediction method provided in any embodiment of the present invention, and will not be repeated here.

[0105] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0106] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0108] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for predicting insulin resistance, characterized in that: The insulin resistance prediction method comprises: Acquire an original data set, the original data set including sample data and label data corresponding to the sample data, the sample data including user medical data and user questionnaire data; Performing feature classification on the original data set to obtain data with cost features and data without cost features; Training a pre-built original model based on the cost feature data and the cost-free feature data to obtain a first prediction model and a second prediction model, wherein the original model includes an integrated tree model, the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and the second prediction model is obtained by training based on the cost-free feature data; Classifying the users to be predicted, determining the first type of users and the second type of users among the users to be predicted, and acquiring the first type of user data and the second type of user data, wherein the first type of user data includes the user questionnaire data and the user medical data of the first type of users, and the second type of user data includes the user questionnaire data of the second type of users; The first type of user data is input into the first prediction model for insulin resistance prediction, and the second type of user data is input into the second prediction model for insulin resistance prediction, to obtain prediction results for the first type of users and prediction results for the second type of users.

2. The method for predicting insulin resistance according to claim 1, wherein: The pre-built original model is trained based on the cost feature data and the cost-free feature data to obtain a first prediction model and a second prediction model, including: Training a plurality of pre-constructed original models based on the cost feature data and the cost-free feature data to obtain a plurality of first candidate models and a plurality of second candidate models, wherein the first candidate models are obtained by training based on the cost feature data and the cost-free feature data, and the second candidate models are obtained by training based on the cost-free feature data; Evaluate each first candidate model and each second candidate model to obtain a candidate evaluation result; Performing a correlation analysis on the cost feature data and the cost-free feature data, and performing feature screening on the cost feature data and the cost-free feature data based on the correlation analysis result and the candidate evaluation result to obtain first target data and second target data; The first candidate model and the second candidate model are trained according to the first target data and the second target data to obtain a first prediction model and a second prediction model, wherein the first prediction model is obtained by training based on the first target data and the second target data, and the second prediction model is obtained by training based on the second target data.

3. The method for predicting insulin resistance according to claim 2, wherein: The correlation analysis result includes a continuous feature analysis result and a discrete feature analysis result; performing correlation analysis on the cost feature data and the cost-free feature data, and performing feature screening on the cost feature data and the cost-free feature data based on the correlation analysis result and the candidate evaluation result to obtain the first target data and the second target data, including: Determining continuous feature data and discrete feature data in the cost feature data and the cost-free feature data; Determining a linear correlation coefficient between each continuous feature in the continuous feature data, and performing a correlation analysis on the continuous feature data based on the linear correlation coefficient to obtain a continuous feature analysis result; Performing a chi-square test on each discrete feature in the discrete feature data to obtain a discrete feature analysis result; Performing correlation dimension reduction on the cost feature data and the cost-free feature data based on the continuous feature analysis result and the discrete feature analysis result; Performing importance evaluation on each feature in the cost feature data and the cost-free feature data according to the correlation dimension reduction result and the candidate evaluation result; Based on the importance evaluation result, the cost feature data and the cost-free feature data are feature screened to obtain the first target data and the second target data.

4. The method for predicting insulin resistance according to claim 3, wherein: The classifying the users to be predicted, determining the first type of users and the second type of users among the users to be predicted, and acquiring the first type of user data and the second type of user data, includes: Classifying the users to be predicted, and determining a first type of users and a second type of users among the users to be predicted; Generate a first type of questionnaire text based on the first target data and the second target data, and generate a second type of questionnaire text based on the second target data; Sending the first type of questionnaire text to the first type of users, and sending the second type of questionnaire text to the second type of users; Acquire a first type of answer text fed back by the first type of users based on the first type of questionnaire text and a second type of answer text fed back by the second type of users based on the second type of questionnaire text; Performing semantic analysis on the first type of answer text to obtain first type of user data; Perform semantic analysis on the second type of answer text to obtain second type of user data.

5. The method for predicting insulin resistance according to any one of claims 1 to 4, characterized in that: The obtaining of the original data set comprises: Collect user questionnaire data and user medical data; Aggregating the user questionnaire data and the user medical data based on user identities of the user questionnaire data and the user medical data to obtain an initial multidimensional data set; Performing data cleaning on the initial multidimensional data set according to the user identity identifier to obtain a candidate multidimensional data set; Performing dependency analysis on the candidate multidimensional data set to obtain dependency relationship information between features in the candidate multidimensional data set; Filling missing data in the candidate multidimensional data set based on the dependency information; The candidate multidimensional datasets filled with missing data are standardized to obtain the original dataset.

6. The method for predicting insulin resistance according to any one of claims 1 to 4, characterized in that: After inputting the first type of user data into the first prediction model to predict insulin resistance, and inputting the second type of user data into the second prediction model to predict insulin resistance, and obtaining the prediction results of the first type of users and the prediction results of the second type of users, the method comprises: Based on the prediction results of the first type of users and the prediction results of the second type of users, the first type of users and the second type of users are classified by risk to determine high-risk users and low-risk users; Performing semantic analysis on the answer texts of the high-risk user and the low-risk user to obtain user answer information; Generate a resistance question set according to a pre-constructed insulin resistance knowledge graph, wherein the insulin resistance knowledge graph includes medical knowledge information, symptom information, risk factor information, and diagnostic criteria information of insulin resistance; Determining the degree of text matching between the user answer information of the high-risk user and the low-risk user and the resistance question set based on a deep interactive text matching model; Insulin resistance is determined for the high-risk user and the low-risk user according to the text matching degree.

7. An insulin resistance prediction system, characterized in that: The insulin resistance prediction system comprises: A data acquisition module, used to acquire an original data set, wherein the original data set includes sample data and label data corresponding to the sample data, wherein the sample data includes user medical data and user questionnaire data; A feature classification module, used for performing feature classification on the original data set to obtain cost feature data and cost-free feature data; A model training module, used for training a pre-built original model based on the cost feature data and the cost-free feature data to obtain a first prediction model and a second prediction model, wherein the original model includes an integrated tree model, the first prediction model is obtained by training based on the cost feature data and the cost-free feature data, and the second prediction model is obtained by training based on the cost-free feature data; A user classification module, used to classify the users to be predicted, determine the first type of users and the second type of users among the users to be predicted, and obtain the first type of user data and the second type of user data, wherein the first type of user data includes the user questionnaire data and user medical data of the first type of users, and the second type of user data includes the user questionnaire data of the second type of users; The insulin resistance prediction module is used to input the first type of user data into the first prediction model for insulin resistance prediction, and input the second type of user data into the second prediction model for insulin resistance prediction, to obtain the prediction results of the first type of users and the prediction results of the second type of users.

8. An insulin resistance prediction device, characterized in that: The insulin resistance prediction device comprises: a memory, a processor, and an insulin resistance prediction program stored in the memory and executable on the processor, wherein the insulin resistance prediction program is configured to implement the insulin resistance prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an insulin resistance prediction program, and when the insulin resistance prediction program is executed by a processor, the insulin resistance prediction method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises an insulin resistance prediction program, which, when executed by a processor, implements the steps of the insulin resistance prediction method according to any one of claims 1 to 6.

Images