Cardiac and renal metabolic syndrome progress prediction model construction system and method based on insulin resistance index

Abstract

The invention discloses a heart and kidney metabolic syndrome progress prediction model construction system and method based on an insulin resistance index, and the system comprises a data processing module which is used for preprocessing clinical CKM population sample data to obtain a training set and a verification set; the index association module is used for acquiring insulin resistance indexes and respectively establishing association between each insulin resistance index and the cardiovascular disease onset risk of people in each stage of the heart and kidney metabolic syndrome; the index determination module is used for drawing ROC curves of various insulin resistance indexes for identifying cardiovascular diseases and determining insulin substitution indexes in the insulin resistance indexes; the model construction module is used for constructing a plurality of Cox regression models; and the model evaluation module is used for carrying out performance evaluation on each Cox regression model to obtain a heart and kidney metabolic syndrome progress prediction model. The method can improve the accuracy of predicting cardiovascular diseases of people suffering from heart and kidney metabolic syndrome in the future, and can be widely applied to the technical field of data processing.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a system and method for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators. Background Art

[0002] In October 2023, the American Heart Association (AHA) released a scientific statement defining cardiovascular-kidney-metabolic syndrome (CKM) for the first time as a systemic disease caused by the pathophysiological interaction between obesity, diabetes, chronic kidney disease, and cardiovascular disease (CVD, which includes heart failure, atrial fibrillation, coronary artery disease, stroke, and peripheral arterial disease). CKM is a complex of cardiovascular and renal diseases centered on dysfunctional adipocytes and encompasses inflammation, oxidative stress, insulin resistance, and endothelial dysfunction. Due to the complex and holistic nature of the disease, comprehensive screening and assessment are essential throughout the diagnosis and treatment pathway for individuals at high risk for CKM. For patients with CKM stages 0 to 3, the focus is on preventing cardiovascular disease (CVD); while stage 4 emphasizes treatment and care for CVD associated with CKM risk factors to reduce the incidence of adverse events such as mortality.

[0003] Insulin resistance plays an important role in the progression of CKM. However, the gold standard for insulin resistance, HEC, requires direct measurement of insulin in the blood, which is cumbersome and expensive, making it difficult to promote in clinical practice. In contrast, insulin resistance indicators such as the triglyceride-glucose (TyG) index have become a simple and inexpensive tool to measure insulin resistance, metabolic syndrome, and the risk of cardiovascular disease. Currently, studies have shown that the insulin resistance index has an important predictive role in the development of cardiovascular disease (CVD) in people with CKM stages 0-3. However, the predictive performance of the insulin resistance index in people at all stages of cardiorenal metabolic syndrome (CKM) is still inconclusive, and the risk threshold has not been determined. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a system and method for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators, which can improve the accuracy of predicting the future occurrence of cardiovascular diseases in people with cardiorenal metabolic syndrome.

[0005] To achieve the above objectives, one aspect of the present invention provides a system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators, comprising:

[0006] A data processing module is used to obtain clinical CKM population sample data, preprocess the clinical CKM population sample data, and obtain a training set and a validation set;

[0007] An indicator association module is used to obtain a plurality of insulin resistance indicators from the training set, and then respectively establish an association between each of the insulin resistance indicators and the risk of cardiovascular disease in people at different stages of cardiorenal metabolic syndrome to obtain an association result;

[0008] An indicator determination module is used to draw the ROC curve of each insulin resistance indicator for identifying the onset of cardiovascular disease based on the correlation result, and calculate the AUC value of the ROC curve to determine the insulin replacement indicator in the insulin resistance indicator;

[0009] A model building module, used to build multiple Cox regression models between predictive factors and the risk of progression of cardiorenal metabolic syndrome at each stage, wherein the predictive factors include the insulin replacement index and preset general characteristic factors;

[0010] A model evaluation module, configured to evaluate the performance of each Cox regression model based on the validation set to obtain a cardiorenal metabolic syndrome progression prediction model;

[0011] Among them, the insulin resistance indicators include triglyceride glucose index, triglyceride glucose-waist circumference index, triglyceride glucose-body mass index and triglyceride glucose index-waist height ratio index.

[0012] In some embodiments, the data processing module includes:

[0013] A data collection module, used to obtain the clinical CKM population sample data;

[0014] A data preprocessing module is used to screen out data of the clinical CKM population sample data that include data with cardiovascular diseases, missing CKM staging information, and missing physical examination and blood biochemical indicators;

[0015] The data partitioning module is used to divide the clinical CKM population sample data after screening according to a preset ratio to obtain the training set and the validation set.

[0016] In some embodiments, the triglyceride glucose index is calculated by the following formula:

[0017] TyG = Ln[triglyceride × fasting blood glucose] / 2;

[0018] Wherein, TyG represents the triglyceride glucose index, and the unit of triglyceride and fasting blood glucose is mg / dl;

[0019] The triglyceride glucose-waist circumference index is calculated by the following formula:

[0020] TyG-WC=TyG×WC;

[0021] Wherein, TyG-WC represents the triglyceride glucose-waist circumference index, and WC represents waist circumference, in cm;

[0022] The triglyceride glucose-body mass index is calculated by the following formula:

[0023] TyG-BMI=TyG×BMI;

[0024] Wherein, TyG-BMI represents the triglyceride glucose-body mass index, and BMI represents body mass index;

[0025] The triglyceride glucose index-waist height ratio index is calculated by the following formula:

[0026] TyG-WHtR=TyG×WHtR;

[0027] Wherein, TyG-WHtR represents the triglyceride glucose index-waist-to-height ratio index, and WHtR represents waist-to-height ratio.

[0028] In some embodiments, the indicator association module includes:

[0029] An indicator acquisition module is used to divide the training set into six groups according to the CKM stage of the clinical CKM population and whether cardiovascular disease occurs, and then obtain the insulin resistance indicator in each group;

[0030] The variance analysis module is used to perform t-test and ANOVA variance analysis on the insulin resistance index of each group, and obtain the correlation result based on the analysis result and the preset significant difference threshold.

[0031] In some embodiments, the populations at different stages of cardiorenal metabolic syndrome include a CKM0-1 stage population, a CKM2 stage population, and a CKM3 stage population, and the indicator determination module includes:

[0032] A curve drawing module, for drawing the ROC curve for identifying the onset of cardiovascular disease by each insulin resistance indicator in the CKM0-1 stage population, the CKM2 stage population, and the CKM3 stage population;

[0033] The lower area calculation module is used to calculate the area of ​​the graph formed by each ROC curve and the horizontal and vertical axes to obtain the AUC value corresponding to each ROC curve;

[0034] An indicator screening module, used to screen the insulin resistance indicator corresponding to the highest AUC value among the CKM stage 0-1 population, the CKM stage 2 population, and the CKM stage 3 population, to obtain the insulin replacement index;

[0035] The indicator evaluation module is used to draw a KM survival curve and determine the predictive value of the insulin replacement indicator based on the KM survival curve.

[0036] In some embodiments, the indicator evaluation module includes:

[0037] A quartile division module is used to divide the CKM0-1 stage population, the CKM2 stage population, and the CKM3 stage population into four groups according to the quartiles of the insulin resistance index;

[0038] The prediction value determination module is used to draw the KM survival curve of each group, compare the curve differences of the KM survival curves of each group through the Log-rank test, and determine the prediction value of the insulin replacement index according to the curve differences.

[0039] In some embodiments, the triglyceride glucose index is determined as the insulin replacement indicator in the CKM0-1 stage, the triglyceride glucose index-waist height ratio index is determined as the insulin replacement indicator in the CKM2 stage, and the triglyceride glucose-waist circumference index is determined as the insulin replacement indicator in the CKM3 stage.

[0040] In some embodiments, the model building module includes:

[0041] A preliminary model construction module, used to construct a plurality of Cox regression models according to the insulin replacement index and the general characteristic factors;

[0042] The prediction factor screening module is used to calculate the variance inflation factor of each of the prediction factors, and screen the prediction factors of each of the Cox regression models according to the variance inflation factor and a preset collinearity threshold.

[0043] In some embodiments, the general characteristic factors include lifestyle indicators, demographic characteristics and clinical indicators, the lifestyle indicators include smoking, drinking, physical exercise level and body mass index, the demographic characteristics include gender, age, education level, occupation and marital status, and the clinical indicators include high-density lipoprotein, low-density lipoprotein, blood creatinine and white blood cell count.

[0044] To achieve the above objectives, another aspect of the present invention provides a method for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators, comprising the following steps:

[0045] Obtaining clinical CKM population sample data, and preprocessing the clinical CKM population sample data to obtain a training set and a validation set;

[0046] Obtaining several insulin resistance indicators from the training set, and then establishing associations between each of the insulin resistance indicators and the risk of cardiovascular disease in people at different stages of cardiorenal metabolic syndrome, to obtain association results;

[0047] According to the correlation results, drawing ROC curves for each insulin resistance index to identify the onset of cardiovascular disease, and calculating the AUC value of the ROC curve to determine the insulin replacement index in the insulin resistance index;

[0048] Constructing multiple Cox regression models between predictive factors and the risk of progression of cardiorenal metabolic syndrome at each stage, wherein the predictive factors include the insulin replacement index and pre-set general characteristic factors;

[0049] Performing performance evaluation on each of the Cox regression models based on the validation set to obtain a cardiorenal metabolic syndrome progression prediction model;

[0050] Among them, the insulin resistance indicators include triglyceride glucose index, triglyceride glucose-waist circumference index, triglyceride glucose-body mass index and triglyceride glucose index-waist height ratio index.

[0051] The beneficial effects of the present invention are as follows: the present invention's system and method for constructing a cardiorenal metabolic syndrome progression prediction model based on the insulin resistance index include a data processing module, an index association module, an index determination module, a model construction module, and a model evaluation module. On the one hand, the present invention calculates the triglyceride glucose index and its derivative indicators (i.e., triglyceride glucose-waist circumference index, triglyceride glucose-body mass index, and triglyceride glucose index-waist-height ratio index) using biochemical parameters all from routine laboratory examination items in physical examination items, and the acquisition method is simple, and the index value can be quickly calculated; on the other hand, according to the different CKM stages of people in different stages of cardiorenal metabolic syndrome, insulin replacement indicators and general characteristic factors are respectively constructed to predict the progression of cardiorenal metabolic syndrome, which can improve the accuracy of predicting the future occurrence of cardiovascular disease in people with cardiorenal metabolic syndrome. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0053] Figure 1 A schematic diagram of a system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators provided by one embodiment of the present invention;

[0054] Figure 2 A schematic diagram of sample inclusion criteria provided for one embodiment of the present invention;

[0055] Figure 3 A schematic diagram of the incidence of CVD in people at different stages of cardiorenal metabolic syndrome at different insulin resistance index levels provided by one embodiment of the present invention;

[0056] FIG4( a ) is a schematic diagram of CVD survival curves for different insulin resistance index levels in a CKM0-1 stage population according to an embodiment of the present invention;

[0057] FIG4( b ) is a schematic diagram of CVD survival curve results for different insulin resistance index levels in a CKM2 stage population according to an embodiment of the present invention;

[0058] FIG4( c ) is a schematic diagram of CVD survival curve results for different insulin resistance index levels in a CKM3 stage population according to an embodiment of the present invention;

[0059] FIG5( a ) is a schematic diagram of an ROC curve of a CVD risk prediction model in a CKM stage 0-1 population constructed based on a training cohort according to an embodiment of the present invention;

[0060] FIG5( b ) is a schematic diagram of an ROC curve of a CVD risk prediction model in a CKM2 stage population constructed based on a training cohort according to an embodiment of the present invention;

[0061] FIG5( c ) is a schematic diagram of an ROC curve of a CVD risk prediction model in a CKM stage 3 population constructed based on a training cohort according to an embodiment of the present invention;

[0062] Figure 6 The present invention provides a flowchart of the steps of a method for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are merely examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0064] It will be understood that the terms "first", "second", etc. used in this application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0065] The terms "at least one", "plurality", "each", "any", etc. used in this application include "at least one", "two" or more, "plurality" or "each", "any" or "any one", "each" or "any one" as used herein.

[0066] In October 2023, the American Heart Association (AHA) released a scientific statement defining cardiovascular-kidney-metabolic syndrome (CKM) for the first time as a systemic disease caused by the pathophysiological interaction between obesity, diabetes, chronic kidney disease, and cardiovascular disease (CVD, which includes heart failure, atrial fibrillation, coronary artery disease, stroke, and peripheral arterial disease). CKM is a complex of cardiovascular and renal diseases centered on dysfunctional adipocytes and encompasses inflammation, oxidative stress, insulin resistance, and endothelial dysfunction. Due to the complex and holistic nature of the disease, comprehensive screening and assessment are essential throughout the diagnosis and treatment pathway for individuals at high risk for CKM. For patients with CKM stages 0 to 3, the focus is on preventing cardiovascular disease (CVD); while stage 4 emphasizes treatment and care for CVD associated with CKM risk factors to reduce the incidence of adverse events such as mortality.

[0067] Insulin resistance plays an important role in the progression of CKM. However, the gold standard for insulin resistance, HEC, requires direct measurement of insulin in the blood, which is cumbersome and expensive, making it difficult to promote in clinical practice. In contrast, insulin resistance indicators such as the triglyceride-glucose (TyG) index have become a simple and inexpensive tool to measure insulin resistance, metabolic syndrome, and the risk of cardiovascular disease. Currently, studies have shown that the insulin resistance index has an important predictive role in the development of cardiovascular disease (CVD) in people with CKM stages 0-3. However, the predictive performance of the insulin resistance index in people at all stages of cardiorenal metabolic syndrome (CKM) is still inconclusive, and the risk threshold has not been determined.

[0068] To this end, an embodiment of the present invention proposes a system for constructing a cardiorenal metabolic syndrome progression prediction model based on the insulin resistance index, including a data processing module, an index association module, an index determination module, a model construction module, and a model evaluation module. On the one hand, the present invention calculates the triglyceride glucose index and its derivative indicators (i.e., triglyceride glucose-waist circumference index, triglyceride glucose-body mass index, and triglyceride glucose index-waist height ratio index) using biochemical parameters that are all derived from routine laboratory examination items in physical examination items. The acquisition method is simple, and the index value can be quickly calculated. On the other hand, according to the different CKM stages of people with cardiorenal metabolic syndrome at different stages, insulin replacement indicators and general characteristic factors are respectively constructed to predict the progression of cardiorenal metabolic syndrome, which can improve the accuracy of predicting the future occurrence of cardiovascular disease in people with cardiorenal metabolic syndrome.

[0069] Reference Figure 1 , Figure 1 This is a schematic diagram of a system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators according to an embodiment of the present invention. The system comprises:

[0070] The data processing module is used to obtain clinical CKM population sample data, pre-process the clinical CKM population sample data, and obtain training sets and validation sets;

[0071] The indicator association module is used to obtain several insulin resistance indicators from the training set, and then establish the association between each insulin resistance indicator and the risk of cardiovascular disease in people at different stages of cardiorenal metabolic syndrome to obtain the association results;

[0072] An indicator determination module is used to draw ROC curves for each insulin resistance indicator to identify the onset of cardiovascular disease based on the correlation results, calculate the AUC value of the ROC curve, and determine the insulin replacement indicator in the insulin resistance indicator;

[0073] A model building module is used to construct multiple Cox regression models that correlate predictors with the risk of progression of cardiorenal metabolic syndrome at each stage. Predictors include insulin replacement markers and pre-set general characteristic factors.

[0074] The model evaluation module is used to evaluate the performance of each Cox regression model based on the validation set to obtain a cardiorenal metabolic syndrome progression prediction model;

[0075] Among them, insulin resistance indicators include triglyceride glucose index, triglyceride glucose-waist circumference index, triglyceride glucose-body mass index and triglyceride glucose index-waist height ratio index.

[0076] Specifically, the embodiment of the present invention first obtains sample data of a clinical CKM population, preprocesses the sample data of the clinical CKM population, and randomly divides the sample data into a training set and a validation set according to a preset ratio; then, the insulin resistance index is obtained from the sample data, and the association between each insulin resistance index and the risk of CVD in the population at each stage of cardiorenal metabolic syndrome is established, wherein the insulin resistance index includes the triglyceride glucose (TyG) index and its derivative index, and the derivative index is constructed by the triglyceride glucose (TyG) index and height, weight, and waist circumference data; then, the ROC curve of each insulin resistance index for identifying the onset of CVD is drawn, and the area under the ROC curve (AUC) is calculated to further determine the insulin replacement index included in the model construction of each stage; and then the Cox regression model is used in the training set to construct a prediction model for the insulin replacement index and general characteristic factors and the risk of progression of cardiorenal metabolic syndrome (CKM) at each stage, and finally, the model effectiveness is verified in the validation set to obtain a constructed cardiorenal metabolic syndrome progression prediction model.

[0077] As an optional embodiment, the data processing module includes:

[0078] Data collection module, used to obtain clinical CKM population sample data;

[0079] The data preprocessing module is used to screen out data from clinical CKM population samples that include patients with cardiovascular diseases, missing CKM staging information, and missing physical examination and blood biochemical indicators;

[0080] The data partitioning module is used to divide the sample data of the screened clinical CKM population according to a preset ratio to obtain a training set and a validation set.

[0081] Specifically, the clinical CKM population sample data obtained in the embodiment of the present invention comes from a longitudinal dynamic health cohort of the elderly population in a certain region. The baseline survey time of the cohort is 2018-2020, and the existing follow-up information is as of December 31, 2023. Participants aged 65 years or above at baseline were selected, and those with cardiovascular disease (CVD) at baseline, missing CKM stage-related information, physical examination and blood biochemical indicators were excluded. Finally, 453,533 participants were included. The sample inclusion criteria are as follows: Figure 2 As shown in the figure, the sample data is randomly divided into a training set and a validation set according to a preset ratio (e.g., 7:3). The validation set is used to evaluate the performance of the constructed model, and the consistency and stability of the prediction accuracy of the prediction model in the training set and the validation set are compared.

[0082] As a further optional embodiment, the triglyceride glucose index is calculated by the following formula:

[0083] TyG = Ln[triglyceride × fasting blood glucose] / 2;

[0084] Wherein, TyG represents triglyceride glucose index, and the unit of triglyceride and fasting blood glucose is mg / dl;

[0085] The triglyceride-glucose waist circumference index was calculated using the following formula:

[0086] TyG-WC=TyG×WC;

[0087] Wherein, TyG-WC represents triglyceride glucose-waist circumference index, WC represents waist circumference, and the unit is cm;

[0088] Triglyceride-glucose body mass index was calculated using the following formula:

[0089] TyG-BMI=TyG×BMI;

[0090] Wherein, TyG-BMI represents triglyceride glucose-body mass index, and BMI represents body mass index;

[0091] The triglyceride glucose index-waist height ratio index was calculated using the following formula:

[0092] TyG-WHtR=TyG×WHtR;

[0093] TyG-WHtR represents triglyceride glucose index-waist-to-height ratio index, and WHtR represents waist-to-height ratio.

[0094] Specifically, BMI is body mass index, which is calculated by dividing weight by height squared, and WHtR is waist-to-height ratio, which is calculated by dividing waist circumference by height.

[0095] As an optional implementation, the indicator association module includes:

[0096] The indicator acquisition module is used to divide the training set into six groups based on the CKM stage of the clinical CKM population and whether cardiovascular disease occurs, and then obtain the insulin resistance index in each group;

[0097] The variance analysis module is used to perform t-test and ANOVA variance analysis on the insulin resistance index of each group, and obtain the correlation results based on the analysis results and the preset significant difference threshold.

[0098] Specifically, participants were divided into groups according to their CKM stage, based on the statement released by the American Heart Association (AHA). The groups are as follows:

[0099] (1) Stage 0: no CKM risk factors, i.e., normal BMI, waist circumference, blood sugar, blood pressure, and blood lipids, and no CKD or subclinical / clinical CVD;

[0100] (2) Stage 1: excessive or abnormal fat accumulation, i.e., overweight / obesity, abdominal obesity, or adipose tissue dysfunction, but without other metabolic risk factors or CKD;

[0101] (3) Stage 2: presence of metabolic risk factors and CKD, i.e., combined metabolic risk factors (hypertriglyceridemia ≥135 mg / dL, hypertension, diabetes, metabolic syndrome) or moderate to high-risk CKD;

[0102] (4) Stage 3: subclinical CVD (including Framingham-10-year CVD risk score results of high risk and CKD stage G4 or G5);

[0103] (5) Stage 4: CVD occurs.

[0104] Participants were divided into six groups based on their CKM stage and whether they had experienced CVD (i.e., cardiovascular disease). Data were statistically analyzed using R language software. ANOVA analysis of variance was performed using the aov() function in the R environment. Insulin resistance indices were expressed as mean ± standard deviation. A t-test was used for comparisons between two groups, and ANOVA analysis of variance was used for comparisons between multiple groups. A P value < 0.05 (i.e., the threshold for significant difference) was considered significant between at least two groups. Table 1 summarizes the insulin resistance levels of patients with and without CVD across various stages of CKM. Significant differences in insulin resistance were observed between the CVD-developing and non-CVD-developing groups.

[0105] Table 1

[0106]

[0107] As a further optional embodiment, the populations at different stages of cardiorenal metabolic syndrome include a CKM0-1 stage population, a CKM2 stage population, and a CKM3 stage population, and the indicator determination module includes:

[0108] The curve drawing module is used to draw ROC curves for identifying the incidence of cardiovascular disease using various insulin resistance indicators in the CKM0-1 stage population, the CKM2 stage population, and the CKM3 stage population;

[0109] The lower area calculation module is used to calculate the area of ​​the graph formed by each ROC curve and the horizontal and vertical axes to obtain the AUC value corresponding to each ROC curve;

[0110] An indicator screening module is used to screen the insulin resistance index corresponding to the highest AUC value among the CKM0-1 stage population, the CKM2 stage population, and the CKM3 stage population to obtain an insulin replacement index;

[0111] The indicator evaluation module is used to draw the KM survival curve and determine the predictive value of the insulin replacement indicator based on the KM survival curve.

[0112] In some optional embodiments, KM survival curves and Cox regression models are used to analyze the association between the triglyceride glucose (TyG) index and its derivatives and disease progression in CKM0-1, CKM2, and CKM3 stages, respectively. P<0.05 indicates statistical significance. ROC curves are drawn for the triglyceride glucose (TyG) index and its derivatives in identifying the occurrence of cardiovascular disease (CVD) in populations at each stage of cardiorenal metabolic syndrome (CKM), and the area under the ROC curve (AUC) is calculated to evaluate the predictive efficacy of various insulin resistance indicators in identifying the occurrence of CVD in populations at each stage of cardiorenal metabolic syndrome.

[0113] Specifically, in order to screen out the insulin replacement index with the best predictive performance in the population of each stage of cardiorenal metabolic syndrome, the ROC curves for identifying the occurrence of CVD were drawn for the triglyceride glucose (TyG) index, triglyceride glucose-physique (TyG-BMI) index, triglyceride glucose-waist circumference (TyG-WC) index, and triglyceride glucose index-waist height ratio (TyG-WHtR) index in the population of each stage of cardiorenal metabolic syndrome, and the AUC was calculated. For example, taking the triglyceride glucose (TyG) index of CKM0-1 stage as an example, the triglyceride glucose (TyG) index was sorted from small to large, and each value was used as a cutoff point. The false positive rate (false positive number / total number of non-events) was used as the horizontal coordinate, and the true positive rate (true positive number / total number of events) was used as the vertical coordinate. All cutoff points were connected to form a curve, the ROC curve was drawn, and the trapezoidal method formula was used to calculate the area of ​​the graph composed of the curve and the horizontal and vertical axes, i.e., the AUC. The AUC comprehensively considers the model's classification performance at different thresholds and reflects its ability to distinguish between positive and negative examples. Higher values ​​indicate better model performance. This can be performed using the timeROC package in the R environment. A summary of the AUCs for the ROC curves of the various insulin resistance indices is shown in Table 2. The TyG index had the highest AUC in patients with CKM stage 0-1, the TyG-WHtR index had the highest AUC in patients with CKM stage 2, and the TyG-WC index had the highest AUC in patients with CKM stage 3.

[0114] Table 2

[0115]

[0116] As a further optional embodiment, the triglyceride glucose index is determined as an insulin replacement indicator in the CKM0-1 stage, the triglyceride glucose index-waist height ratio index is determined as an insulin replacement indicator in the CKM2 stage, and the triglyceride glucose-waist circumference index is determined as an insulin replacement indicator in the CKM3 stage.

[0117] As an optional implementation, the indicator evaluation module includes:

[0118] The quartile division module is used to divide the CKM0-1 stage population, the CKM2 stage population, and the CKM3 stage population into four groups according to the quartiles of the insulin resistance index;

[0119] The predictive value determination module is used to draw the KM survival curve of each group, compare the curve differences of the KM survival curves of each group through the Log-rank test, and determine the predictive value of the insulin replacement index based on the curve differences.

[0120] Specifically, if Figure 3Shown is a schematic diagram of the incidence of cardiovascular disease (CVD) at different insulin resistance levels in individuals with various stages of the cardiorenal metabolic syndrome. Within each stage of the cardiorenal metabolic syndrome, the incidence of CVD significantly increased with increasing levels of specific insulin markers. Kaplan-Meier survival curves (KM survival curves) were used to determine the predictive value of selected insulin surrogate markers for insulin resistance in individuals with various stages of the cardiorenal metabolic syndrome. Individuals with various stages of the cardiorenal metabolic syndrome were divided into Q1-Q4 groups according to quartiles of insulin resistance. CVD events were used as the endpoint, and follow-up time was recorded. Each time point and its corresponding cumulative survival probability were plotted on a coordinate system with time as the horizontal axis and cumulative survival probability as the vertical axis. These points were then connected with broken lines to generate Kaplan-Meier survival curves for each group. The curves were compared using the Log-rank test (P < 0.05 was considered significant). Kaplan-Meier survival curves can visually demonstrate changes in survival probability or cumulative survival rate, allowing comparison of survival outcomes between groups with different insulin resistance levels to assess the predictive value of insulin resistance levels for CVD events. As shown in Figure 4(a), the results of the CVD survival curves at different levels of insulin resistance indicators in the CKM0-1 stage population are shown in Figure 4(b), the results of the CVD survival curves at different levels of insulin resistance indicators in the CKM2 stage population are shown in Figure 4(c), and the results of the CVD survival curves at different levels of insulin resistance indicators in the CKM3 stage population are shown in Figure 4(c). It can be seen that the cumulative incidence of CVD in the high-level insulin resistance index group was significantly higher than that in the low-level group.

[0121] Table 3 shows the survival regression analysis of various insulin resistance indicators and the progression to CVD syndrome in people at different stages of cardiorenal metabolic syndrome. It can be seen that in the CKM0-1 stage population, only the triglyceride glucose (TyG) index was positively correlated with the risk of cardiovascular disease (CVD); in the CKM2 and CKM3 stages population, the triglyceride glucose (TyG) index, triglyceride glucose-body mass index (TyG-BMI) index, triglyceride glucose-waist circumference (TyG-WC) index, and triglyceride glucose index-waist height ratio (TyG-WHtR) index were all positively correlated with the risk of CVD.

[0122] Table 3

[0123]

[0124] As an optional embodiment, the model building module includes:

[0125] The preliminary model building module is used to construct multiple Cox regression models based on insulin replacement indicators and general characteristic factors;

[0126] The predictor screening module is used to calculate the variance inflation factor of each predictor and screen the predictors of each Cox regression model based on the variance inflation factor and the preset collinearity threshold.

[0127] As a further optional embodiment, general characteristic factors include lifestyle indicators, demographic characteristics and clinical indicators. Lifestyle indicators include smoking, drinking, physical exercise level and body mass index. Demographic characteristics include gender, age, education level, occupation and marital status. Clinical indicators include high-density lipoprotein, low-density lipoprotein, blood creatinine and white blood cell count display.

[0128] Specifically, based on the selected insulin replacement indicators, combined with general characteristic factors, multiple Cox regression models were preliminarily constructed, and the variance inflation factor (VIF) was calculated. The Cox proportional hazard regression model mainly consists of time variables, state variables and predictor variables, and the hazard function is defined as h(t|X)=h0(t)exp(β1X1+β2X2+...+β p X p ), where h0(t) is the baseline risk function and β is the regression coefficient. The formula for calculating the variance inflation factor is VIF = 1 / (1-R 2 ), where R 2 The VIF represents the goodness-of-fit of the linear regression of a variable with respect to other variables. A VIF ≥ 10 indicates severe multicollinearity, so only factors with a VIF < 5 (the threshold for collinearity) were retained. The results of the Cox regression models are shown in Table 4. Model 1 did not adjust for covariates; Model 2 adjusted for age and sex; and Model 3 adjusted for smoking, alcohol consumption, physical activity, BMI, low-density lipoprotein (LDL-c), high-density lipoprotein (HDL-c), serum creatinine, and white blood cell count. In all models, the triglyceride-glucose (TyG) index, the triglyceride-glucose index-waist-to-height ratio (TyG-WHtR) index, and the triglyceride-glucose-waist circumference (TyG-WC) index quartiles were significantly positively correlated with the incidence of CVD.

[0129] Table 4

[0130]

[0131] Finally, analysis and verification were performed on the validation set to ensure the consistency and reliability of the prediction efficiency. The corresponding risk prediction values ​​for CKM0-1, CKM2, and CKM3 were calculated according to each model. The risk prediction value calculation formula is: risk_score=β1X1+β2X2+...+β p X pThe ROC curve of the risk prediction value was drawn and the AUC was calculated to evaluate the discrimination of the prediction model. The ROC curve of the CVD risk prediction model in the CKM0-1 stage population constructed based on the training cohort is shown in Figure 5(a). It can be seen that the optimal risk prediction value of the TyG prediction model in the CKM0-1 stage population is 0.589, and the AUC is 0.722. The ROC curve of the CVD risk prediction model in the CKM2 stage population constructed based on the training cohort is shown in Figure 5(b). It can be seen that the optimal risk prediction value of the TyG-WHtR prediction model in the CKM2 stage population is 0.489, and the AUC is 0.717. The ROC curve of the CVD risk prediction model in the CKM3 stage population constructed based on the training cohort is shown in Figure 5(c). It can be seen that the optimal risk prediction value of the TyG-WC prediction model in the CKM3 stage population is 0.573, and the AUC is 0.756, reflecting good prediction performance and good fitting results.

[0132] The above describes a system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators according to an embodiment of the present invention. It can be appreciated that the embodiment of the present invention includes a data processing module, an indicator association module, an indicator determination module, a model construction module, and a model evaluation module, and has the following advantages:

[0133] 1. The biochemical parameters used to calculate the triglyceride-glucose index and its derivatives (i.e., triglyceride-glucose-waist circumference index, triglyceride-glucose-body mass index, and triglyceride-glucose-waist-height ratio index) are all derived from routine laboratory tests in physical examinations. They are easy to obtain and can be quickly calculated.

[0134] Second, based on the different CKM stages of people with cardiorenal metabolic syndrome, prediction models for the progression of cardiorenal metabolic syndrome were constructed using insulin replacement indicators and general characteristic factors, respectively. These models can improve the accuracy of predicting the future development of cardiovascular disease in people with cardiorenal metabolic syndrome.

[0135] 3. It is simple to operate and applicable to a wide range of people, especially for the prediction and early warning of CVD events in patients with cardiorenal metabolic syndrome (CKM) among the basic public health service population. It can identify whether patients with cardiorenal metabolic syndrome will develop cardiovascular disease (CVD) at an early stage.

[0136] Reference Figure 6 The embodiment of the present invention further provides a method for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators, comprising the following steps S101 to S105:

[0137] S101, obtaining clinical CKM population sample data, preprocessing the clinical CKM population sample data, and obtaining a training set and a validation set;

[0138] S102. Obtaining several insulin resistance indicators from the training set, and then establishing associations between each insulin resistance indicator and the risk of cardiovascular disease in people at different stages of cardiorenal metabolic syndrome, to obtain association results;

[0139] S103. Based on the correlation results, draw the ROC curve for each insulin resistance index to identify the onset of cardiovascular disease, calculate the AUC value of the ROC curve, and determine the insulin replacement index in the insulin resistance index;

[0140] S104. Construct multiple Cox regression models to assess the risk of progression to cardiorenal metabolic syndrome at each stage, with predictors including insulin replacement markers and pre-defined general characteristics.

[0141] S105. Evaluate the performance of each Cox regression model based on the validation set to obtain a cardiorenal metabolic syndrome progression prediction model;

[0142] Among them, insulin resistance indicators include triglyceride glucose index, triglyceride glucose-waist circumference index, triglyceride glucose-body mass index and triglyceride glucose index-waist height ratio index.

[0143] The contents of the above-mentioned embodiments of the cardiorenal metabolic syndrome progress prediction model construction system based on insulin resistance indicators are all applicable to the present embodiments of the cardiorenal metabolic syndrome progress prediction model construction method based on insulin resistance indicators. The functions specifically implemented by the present embodiments of the cardiorenal metabolic syndrome progress prediction model construction method based on insulin resistance indicators are the same as those of the above-mentioned embodiments of the cardiorenal metabolic syndrome progress prediction model construction system based on insulin resistance indicators, and the beneficial effects achieved are also the same as those achieved by the above-mentioned embodiments of the cardiorenal metabolic syndrome progress prediction model construction system based on insulin resistance indicators.

[0144] An embodiment of the present invention further provides an electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for enabling communication between the processor and the memory. When the program is executed by the processor, the system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators is implemented. The electronic device can be any intelligent terminal, including a tablet computer and an in-vehicle computer.

[0145] An embodiment of the present invention also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to realize the above-mentioned cardiorenal metabolic syndrome progression prediction model construction system based on insulin resistance indicators.

[0146] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0147] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0148] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art can implement the present invention set forth in the claims using ordinary skills without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0149] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0150] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0151] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0152] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0153] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators, characterized in that: include: A data processing module is used to obtain clinical CKM population sample data, preprocess the clinical CKM population sample data, and obtain a training set and a validation set; An indicator association module is used to obtain a plurality of insulin resistance indicators from the training set, and then respectively establish an association between each of the insulin resistance indicators and the risk of cardiovascular disease in people at different stages of cardiorenal metabolic syndrome to obtain an association result; An indicator determination module is used to draw the ROC curve of each insulin resistance indicator for identifying the onset of cardiovascular disease based on the correlation result, and calculate the AUC value of the ROC curve to determine the insulin replacement indicator in the insulin resistance indicator; A model building module, used to build multiple Cox regression models between predictive factors and the risk of progression of cardiorenal metabolic syndrome at each stage, wherein the predictive factors include the insulin replacement index and preset general characteristic factors; A model evaluation module, configured to evaluate the performance of each Cox regression model based on the validation set to obtain a cardiorenal metabolic syndrome progression prediction model; Among them, the insulin resistance indicators include triglyceride glucose index, triglyceride glucose-waist circumference index, triglyceride glucose-body mass index and triglyceride glucose index-waist height ratio index.

2. A cardiorenal metabolic syndrome progression prediction model construction system based on insulin resistance indicators according to claim 1, characterized in that: The data processing module includes: A data collection module, used to obtain the clinical CKM population sample data; A data preprocessing module is used to screen out data of the clinical CKM population sample data that include data with cardiovascular diseases, missing CKM staging information, and missing physical examination and blood biochemical indicators; The data partitioning module is used to divide the clinical CKM population sample data after screening according to a preset ratio to obtain the training set and the validation set.

3. The system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators according to claim 1, characterized in that: The triglyceride glucose index is calculated by the following formula: TyG = Ln[triglyceride × fasting blood glucose] / 2; Wherein, TyG represents the triglyceride glucose index, and the unit of triglyceride and fasting blood glucose is mg / dl; The triglyceride glucose-waist circumference index is calculated by the following formula: TyG-WC=TyG×WC; Wherein, TyG-WC represents the triglyceride glucose-waist circumference index, and WC represents waist circumference, in cm; The triglyceride glucose-body mass index is calculated by the following formula: TyG-BMI=TyG×BMI; Wherein, TyG-BMI represents the triglyceride glucose-body mass index, and BMI represents body mass index; The triglyceride glucose index-waist height ratio index is calculated by the following formula: TyG-WHtR=TyG×WHtR; Wherein, TyG-WHtR represents the triglyceride glucose index-waist-to-height ratio index, and WHtR represents waist-to-height ratio.

4. A cardiorenal metabolic syndrome progression prediction model construction system based on insulin resistance indicators according to claim 1, characterized in that: The indicator association module includes: An indicator acquisition module is used to divide the training set into six groups according to the CKM stage of the clinical CKM population and whether cardiovascular disease occurs, and then obtain the insulin resistance indicator in each group; The variance analysis module is used to perform t-test and ANOVA variance analysis on the insulin resistance index of each group, and obtain the correlation result based on the analysis result and the preset significant difference threshold.

5. The system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators according to claim 1, characterized in that: The populations at different stages of cardiorenal metabolic syndrome include CKM0-1 stage population, CKM2 stage population, and CKM3 stage population, and the indicator determination module includes: A curve drawing module, for drawing the ROC curve for identifying the onset of cardiovascular disease by each insulin resistance indicator in the CKM0-1 stage population, the CKM2 stage population, and the CKM3 stage population; The lower area calculation module is used to calculate the area of ​​the graph formed by each ROC curve and the horizontal and vertical axes to obtain the AUC value corresponding to each ROC curve; An indicator screening module, used to screen the insulin resistance indicator corresponding to the highest AUC value among the CKM stage 0-1 population, the CKM stage 2 population, and the CKM stage 3 population, to obtain the insulin replacement index; The indicator evaluation module is used to draw a KM survival curve and determine the predictive value of the insulin replacement indicator based on the KM survival curve.

6. A cardiorenal metabolic syndrome progression prediction model construction system based on insulin resistance indicators according to claim 5, characterized in that: The indicator evaluation module includes: A quartile division module is used to divide the CKM0-1 stage population, the CKM2 stage population, and the CKM3 stage population into four groups according to the quartiles of the insulin resistance index; The prediction value determination module is used to draw the KM survival curve of each group, compare the curve differences of the KM survival curves of each group through the Log-rank test, and determine the prediction value of the insulin replacement index according to the curve differences.

7. The system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators according to claim 5, characterized in that: The triglyceride glucose index is determined as the insulin replacement index in the CKM0-1 stage, the triglyceride glucose index-waist height ratio index is determined as the insulin replacement index in the CKM2 stage, and the triglyceride glucose-waist circumference index is determined as the insulin replacement index in the CKM3 stage.

8. The system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators according to claim 1, characterized in that: The model building module includes: A preliminary model construction module, used to construct a plurality of Cox regression models according to the insulin replacement index and the general characteristic factors; The prediction factor screening module is used to calculate the variance inflation factor of each of the prediction factors, and screen the prediction factors of each of the Cox regression models according to the variance inflation factor and a preset collinearity threshold.

9. The system for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators according to claim 1, characterized in that: The general characteristic factors include lifestyle indicators, demographic characteristics and clinical indicators. The lifestyle indicators include smoking, drinking, physical exercise level and body mass index. The demographic characteristics include gender, age, education level, occupation and marital status. The clinical indicators include high-density lipoprotein, low-density lipoprotein, blood creatinine and white blood cell count.

10. A method for constructing a cardiorenal metabolic syndrome progression prediction model based on insulin resistance indicators, for constructing a cardiorenal metabolic syndrome progression prediction model construction system based on insulin resistance indicators according to any one of claims 1 to 9, characterized in that: The following steps are involved: Obtaining clinical CKM population sample data, and preprocessing the clinical CKM population sample data to obtain a training set and a validation set; Obtaining several insulin resistance indicators from the training set, and then establishing associations between each of the insulin resistance indicators and the risk of cardiovascular disease in people at different stages of cardiorenal metabolic syndrome, to obtain association results; According to the correlation results, drawing the ROC curve of each insulin resistance index for identifying the onset of cardiovascular disease, and calculating the AUC value of the ROC curve to determine the insulin replacement index in the insulin resistance index; Constructing multiple Cox regression models between predictive factors and the risk of progression of cardiorenal metabolic syndrome at each stage, wherein the predictive factors include the insulin replacement index and pre-set general characteristic factors; Performing performance evaluation on each of the Cox regression models based on the validation set to obtain a cardiorenal metabolic syndrome progression prediction model; Among them, the insulin resistance indicators include triglyceride glucose index, triglyceride glucose-waist circumference index, triglyceride glucose-body mass index and triglyceride glucose index-waist height ratio index.

Images