Method and apparatus for analyzing mortality and cardiovascular disease in diabetic patients

Abstract

The application discloses a method and device for analyzing mortality and cardiovascular disease of diabetes patients, and relates to the field of medical data processing, which comprises the following steps: acquiring metabolic and inflammatory indexes related to diabetes, performing binary logistic regression analysis on the outcome of diabetes patients according to covariates and independent variables, screening analysis indexes from the independent variables, and taking the outcome as survival or death due to cardiovascular and cerebrovascular diseases; constructing a full-cause death risk prediction model based on a Cox regression model and training the model to obtain a trained full-cause death risk prediction model; inputting data of analysis indexes and covariates corresponding to diabetes patients to be analyzed into the trained full-cause death risk prediction model to obtain an intermediate calculated risk score as an inflammatory metabolic index; and analyzing the mortality and cardiovascular disease of the diabetes patients to be analyzed based on the inflammatory metabolic index to obtain an analysis result. The application solves the problem of low prediction accuracy of existing indexes.

Description

Technical Field

[0001] This invention relates to the field of medical data analysis, specifically to a method and apparatus for analyzing the mortality rate and cardiovascular disease status of diabetic patients. Background Technology

[0002] Diabetes mellitus is a common chronic metabolic disease, especially type 2 diabetes, which is closely related to metabolic disorders and inflammatory immune responses, significantly increasing the risk of all-cause mortality and cardiovascular death. The incidence of cardiovascular disease (CVD) in diabetic patients is 2-4 times higher than in non-diabetic individuals, and approximately 70-80% of diabetic patients eventually die from CVD (coronary heart disease accounts for 45%). Commonly used clinical scores (such as the Framingham score) rely on routine metabolic indicators (blood pressure, blood lipids) but neglect the contribution of inflammatory immune pathways. Traditional models rely on single inflammatory markers (such as CRP) or metabolic indicators (such as HbA1c), which, while associated with cardiovascular mortality, cannot capture the dynamic network effects reflecting metabolic-inflammatory interactions. CVD in diabetic patients is highly heterogeneous, and existing indicators have insufficient predictive accuracy for specific subgroups (such as patients with immune metabolic disorders), resulting in limited effectiveness of early intervention. Summary of the Invention

[0003] The purpose of this application is to provide a method and apparatus for analyzing the mortality rate and cardiovascular disease status of diabetic patients in response to the aforementioned technical problems.

[0004] In a first aspect, the present invention provides a method for analyzing the mortality rate and cardiovascular disease status of diabetic patients, comprising the following steps:

[0005] We obtained metabolic and inflammatory indicators related to diabetes, selected covariates and independent variables from these indicators, and performed binary logistic regression analysis on the outcomes of diabetic patients based on the covariates and independent variables. We then selected analytical indicators from the independent variables, with the outcomes being survival or death due to cardiovascular and cerebrovascular diseases.

[0006] A Cox regression-based all-cause mortality risk prediction model was constructed and trained to obtain the trained all-cause mortality risk prediction model.

[0007] The data of analytical indicators and covariates corresponding to the diabetic patients to be analyzed are input into the trained all-cause mortality risk prediction model to obtain the intermediate calculated risk score as the inflammatory metabolic index.

[0008] The mortality rate and cardiovascular disease status of the diabetic patients under analysis were analyzed based on the inflammatory metabolic index, and the analysis results were obtained.

[0009] Preferably, metabolic and inflammatory markers include demographic, laboratory, and questionnaire indicators. Demographic indicators include age, sex, height, weight, race, marital status, and education level. Laboratory indicators include BMI, waist circumference, C-reactive protein, triglycerides, LDL cholesterol, HDL cholesterol, total cholesterol, glycated hemoglobin, fasting blood glucose, insulin, systolic blood pressure, diastolic blood pressure, triglyceride-glucose index, white blood cell count, basophil count, basophil percentage, eosinophil count, eosinophil percentage, lymphocyte count, lymphocyte percentage, neutrophil count, neutrophil percentage, and monocyte count. The questionnaire included the following parameters: percentage of monocytes, mean corpuscular hemoglobin (MCH), mean corpuscular volume (MCV), red blood cell count, hematocrit, hemoglobin, red blood cell distribution width (RDW), platelet count, mean platelet volume (MCV), neutrophil-to-lymphocyte ratio, albumin, alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase (ALP), blood urea nitrogen (BUN), calcium, bicarbonate, gamma-glutamyl transferase (GGT), iron, lactate dehydrogenase (LDH), phosphorus, total protein, total bilirubin, uric acid, creatinine, sodium, potassium, chloride, osmolarity, globulin, creatine kinase, and hematocrit. Questionnaire indicators included the presence of hypertension, hyperlipidemia, hypercholesterolemia, ischemic heart failure, heart attack, coronary artery disease, angina pectoris, stroke, smoking and alcohol consumption, and physical activity index.

[0010] Preferred analytical indicators include: lymphocyte percentage, monocyte percentage, neutrophil percentage, eosinophil percentage, eosinophil count, basophil count, white blood cell count, basophil percentage, neutrophil count, lymphocyte count, monocyte count, platelet count, red blood cell count, albumin, C-reactive protein, hemoglobin, mean corpuscular volume, mean corpuscular hemoglobin content, red blood cell distribution width, mean platelet volume, hematocrit, triglyceride-glucose index, body weight, presence of hypertension, presence of hyperlipidemia, height, BMI, and total cholesterol.

[0011] As a preferred approach, covariates include age, gender, race, marital status, education level, smoking and drinking habits, hypertension, and hyperlipidemia; the remaining indicators of metabolic and inflammatory markers, excluding covariates, are used as independent variables in binary logistic regression analysis.

[0012] As a preferred approach, the mortality rate and cardiovascular disease status of the diabetic patients to be analyzed are based on the inflammatory metabolic index, and the analysis results include:

[0013] The optimal cutoff value of the inflammatory metabolic index most significantly associated with survival was determined by Youden index analysis; based on the optimal cutoff value, the diabetic patients to be analyzed were divided into a high inflammatory metabolic index group and a low inflammatory metabolic index group.

[0014] Kaplan-Meier survival analysis was used to analyze the survival of individuals in the high-inflammatory metabolic index group and the low-inflammatory metabolic index group, and survival curves for the two groups were obtained. The unit of the survival curves is months, and the outcome events are all-cause mortality or death from cardiovascular and cerebrovascular diseases.

[0015] The inflammatory metabolic index of the diabetic patients to be analyzed was used to assess mortality and disease status.

[0016] Preferably, a logistic regression classification model is used to analyze the inflammatory metabolic index of the diabetic patients to be analyzed, including mortality and disease status, specifically:

[0017] The inflammatory metabolic index was analyzed using the time-dependent ROC curve in the logistic regression classification model to predict the all-cause mortality rate of the diabetic patients under analysis at 1, 3, 5, and 10 years.

[0018] The nonlinear relationship between the inflammatory metabolic index and the mortality rate of diabetic patients was analyzed by using restricted cubic spline curves in a logistic regression classification model, and it was determined that there is a nonlinear relationship between the inflammatory metabolic index and the mortality rate of diabetic patients.

[0019] The inflammatory metabolic index was analyzed using the receiver operating characteristic curve in a logistic regression classification model to determine the relationship between the inflammatory metabolic index and cardiovascular disease events, including total cardiovascular disease, congestive heart failure, coronary heart disease, heart attack, stroke, angina pectoris, and stroke. The inflammatory metabolic index was found to have the best predictive effect on congestive heart failure.

[0020] The nonlinear relationship between the inflammatory metabolic index and cardiovascular disease events was analyzed using restricted cubic spline curves in a logistic regression classification model. This analysis revealed a linear relationship between the inflammatory metabolic index and total cardiovascular disease, congestive heart failure, heart attack, angina pectoris, stroke, and coronary heart disease.

[0021] Secondly, the present invention provides a device for analyzing the mortality rate and cardiovascular disease status of diabetic patients, comprising:

[0022] The analysis indicator screening module is configured to acquire metabolic and inflammatory indicators related to diabetes, select covariates and independent variables from the metabolic and inflammatory indicators, perform binary logistic regression analysis on the outcomes of diabetic patients based on the covariates and independent variables, and screen the analysis indicators from the independent variables. The outcome is survival or death due to cardiovascular and cerebrovascular diseases.

[0023] The model building module is configured to build and train an all-cause mortality risk prediction model based on the Cox regression model, resulting in a trained all-cause mortality risk prediction model.

[0024] The prediction module is configured to input the data of the analysis indicators and covariates corresponding to the diabetic patients to be analyzed into the trained all-cause mortality risk prediction model, and obtain the intermediate calculated risk score as the inflammatory metabolic index.

[0025] The analysis module is configured to analyze the mortality rate and cardiovascular disease status of the diabetic patients to be analyzed based on the inflammatory metabolic index, and obtain the analysis results.

[0026] Thirdly, the present invention provides an electronic device including one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0027] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any of the implementations of the first aspect.

[0028] Fifthly, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the method as described in any of the implementations in the first aspect.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] (1) The method for analyzing the mortality rate and cardiovascular disease status of diabetic patients proposed in this invention uses binary logistic regression to screen out analytical indicators related to the outcome of death due to cardiovascular and cerebrovascular diseases, thereby achieving dynamic prediction of metabolic and inflammatory dual-dimensional indicators.

[0031] (2) The method for analyzing the mortality rate and cardiovascular disease status of diabetic patients proposed in this invention processes the analysis indicators through the Cox regression model, quantifies the synergistic effect of inflammation and metabolism, breaks through the prediction bottleneck of existing models for cardiovascular mortality risk in diabetic patients, can identify high-risk groups, and improves the prediction accuracy compared with single indicator models.

[0032] (3) The method for analyzing the mortality rate and cardiovascular disease status of diabetic patients proposed in this invention can automatically analyze the inflammatory metabolic index to predict cardiovascular disease and death in diabetic patients, which can help promote the development of precision medicine, as well as to pay close attention to the characteristics of the population in the early stage, intervene in a timely manner, and improve the survival status. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart illustrating the method for analyzing the mortality rate and cardiovascular disease status of diabetic patients according to an embodiment of this application.

[0035] Figure 2 The graph shows the relationship between high and low IMCI and all-cause mortality in diabetic patients in the NHANES database, which is an embodiment of the present application for analyzing the mortality rate and cardiovascular disease status of diabetic patients.

[0036] Figure 3 The graph shows the relationship between high and low IMCI of diabetic patients and mortality from cardiovascular disease in the NHANES database, which is an embodiment of the present application for analyzing the mortality rate and cardiovascular disease status of diabetic patients.

[0037] Figure 4 The time-dependent ROC curves of all-cause mortality predicted by IMCI for 1, 3, 5, and 10 years in the NHANES database for the analysis method of mortality and cardiovascular disease status of diabetic patients in embodiments of this application.

[0038] Figure 5 The time-dependent ROC curves of cardiovascular disease mortality predicted by IMCI in the NHANES database for 1, 3, 5, and 10 years are used to analyze the mortality rate and cardiovascular disease status of diabetic patients according to the embodiments of this application.

[0039] Figure 6 The relationship between IMCI and all-cause mortality of diabetic patients in the NHANES database, as described in the embodiments of this application, is plotted using a restricted cubic spline curve.

[0040] Figure 7 The relationship between IMCI and cardiovascular disease mortality of diabetic patients in the NHANES database, as described in the embodiments of this application, is plotted using a restricted cubic spline curve.

[0041] Figure 8The NHANES database shows the receiver operating characteristic (ROC) curves between IMCI and cardiovascular disease in the method for analyzing mortality and cardiovascular disease in diabetic patients according to embodiments of this application.

[0042] Figure 9 The method for analyzing mortality and cardiovascular disease status of diabetic patients in this application, after adjusting the covariates in the database, uses RCS to evaluate the association diagram between IMCI and various cardiovascular diseases, where (a) corresponds to total cardiovascular disease, (b) corresponds to stroke, (c) corresponds to heart attack, (d) corresponds to angina pectoris, (e) corresponds to coronary heart disease, and (f) corresponds to congestive heart failure.

[0043] Figure 10 This is a schematic diagram of an apparatus for analyzing the mortality rate and cardiovascular disease status of diabetic patients according to an embodiment of this application;

[0044] Figure 11 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0046] Figure 1 An embodiment of this application illustrates a method for analyzing mortality and cardiovascular disease status in diabetic patients, comprising the following steps:

[0047] S1. Obtain metabolic and inflammatory indicators related to diabetes. Select covariates and independent variables from the metabolic and inflammatory indicators. Perform binary logistic regression analysis on the outcomes of diabetic patients based on the covariates and independent variables. Select analysis indicators from the independent variables. The outcomes are survival or death due to cardiovascular and cerebrovascular diseases.

[0048] In a specific embodiment, metabolic and inflammatory indicators include demographic indicators, laboratory indicators, and questionnaire indicators. Demographic indicators include age, sex, height, weight, race, marital status, and education level. Laboratory indicators include BMI, waist circumference, C-reactive protein, triglycerides, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, total cholesterol, glycated hemoglobin, fasting blood glucose, insulin, systolic blood pressure, diastolic blood pressure, triglyceride-glucose index, white blood cell count, basophil count, basophil percentage, eosinophil count, eosinophil percentage, lymphocyte count, lymphocyte percentage, neutrophil count, neutrophil percentage, and monocyte count. The questionnaire included the following parameters: number of cells, percentage of monocytes, mean corpuscular hemoglobin, mean corpuscular volume, red blood cell count, hematocrit, hemoglobin, red blood cell distribution width, platelet count, mean platelet volume, neutrophil-to-lymphocyte ratio, albumin, alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase, blood urea nitrogen, calcium, bicarbonate, gamma-glutamyl transferase (GGT), iron, lactate dehydrogenase (LDH), phosphorus, total protein, total bilirubin, uric acid, creatinine, sodium, potassium, chloride, osmolarity, globulin, creatine kinase, and hematocrit. Questionnaire indicators included the presence of hypertension, hyperlipidemia, hypercholesterolemia, ischemic heart failure, heart attack, coronary heart disease, angina pectoris, stroke, smoking and alcohol consumption, and physical activity index.

[0049] In specific embodiments, the analytical indicators include: lymphocyte percentage, monocyte percentage, neutrophil percentage, eosinophil percentage, eosinophil count, basophil count, white blood cell count, basophil percentage, neutrophil count, lymphocyte count, monocyte count, platelet count, red blood cell count, albumin, C-reactive protein, hemoglobin, mean corpuscular volume, mean corpuscular hemoglobin content, red blood cell distribution width, mean platelet volume, hematocrit, triglyceride-glucose index, body weight, presence of hypertension, presence of hyperlipidemia, height, BMI, and total cholesterol.

[0050] In a specific implementation, covariates include age, gender, race, marital status, education level, smoking and drinking habits, hypertension, and hyperlipidemia; the remaining indicators of metabolic and inflammatory markers other than the covariates are used as independent variables for binary logistic regression analysis.

[0051] Specifically, in the embodiments of this application, indicators for screening are first obtained. These indicators are related to cardiovascular and cerebrovascular diseases and mortality outcomes, including demographic indicators, laboratory indicators, and questionnaire indicators. Covariates and independent variables are selected from these indicators. Binary logistic regression is then performed using the covariates and independent variables to screen out the analytical indicators, which are related to inflammation, immunity, and metabolism.

[0052] Specifically, data were obtained from the National Health and Nutrition Examination Survey (NHANES) public database, including demographic, laboratory, and questionnaire indicators. After excluding indicators with too many missing values, a total of 28 immune metabolism-related indicators were identified. The NHANES follow-up date ended on December 31, 2019. Among them, the triglyceride-glucose index TyG = Ln [TG (mg / dL) × FPG (mg / dL) / 2]; mean corpuscular volume (MCV) = [HCT (hematocrit) / RBC (red blood cell count)] × 10; mean corpuscular hemoglobin (MCH) = [HGB (hemoglobin concentration) / RBC (red blood cell count)] × 10; red blood cell distribution width (RDW) = (standard deviation of red blood cell volume / MCV) × 100; and body mass index (BMI) = weight (kg) / [height (m)]². First, binary logistic regression was used to screen indicators related to mortality from cardiovascular and cerebrovascular diseases, ensuring that all indicators included in subsequent analyses were related to these outcomes and reducing interference from other irrelevant indicators. A total of 28 indicators were ultimately selected.

[0053] S2. Construct and train an all-cause mortality risk prediction model based on the Cox regression model to obtain the trained all-cause mortality risk prediction model.

[0054] Specifically, an all-cause mortality risk prediction model based on a Cox regression model was constructed and trained to obtain the trained all-cause mortality risk prediction model. The input data for this model consisted of 28 analytical indicators and covariates, which were divided into numerical and categorical data. The numerical data were preprocessed after standardization, while the categorical data were obtained through one-hot encoding. The all-cause mortality risk prediction model used a Cox regression model. The data of analytical indicators and covariates of diabetic patients, along with their corresponding survival time and event status, constituted the training data. The all-cause mortality risk prediction model was trained using this training data. During training, the survival time could be selected from the follow-up time in the NHANES database, and the event status was either survival or all-cause mortality. The parameters of the all-cause mortality risk prediction model were optimized using grid search, and the model stability was evaluated using 5-fold stratified cross-validation. The overall performance of the optimal all-cause mortality risk prediction model was evaluated using AUC. The best AUC result was 0.76, so the setting corresponding to the highest AUC was selected to obtain the trained all-cause mortality risk prediction model.

[0055] In this all-cause mortality risk prediction model, a LassoCV (Least Absolute Contraction and Selection Operator) regularization model with cross-validation is used to select key indicators. The analysis ultimately identifies five key indicators most relevant to all-cause mortality, two of which are risk factors and three are protective factors. These key indicators are incorporated into the linear combination calculation in the Cox regression model to obtain a risk score. This risk score is compared with a threshold to determine whether the group is low-risk or high-risk. If the risk score is below the threshold, the group is classified as low-risk and predicted to be alive; if the risk score is above the threshold, the group is classified as high-risk and predicted to be all-cause mortality.

[0056] S3. Input the data of the analysis indicators and covariates corresponding to the diabetic patients to be analyzed into the trained all-cause mortality risk prediction model to obtain the intermediate calculated risk score as the inflammatory metabolic index.

[0057] Specifically, the trained all-cause mortality risk prediction model is used to analyze the outcome of a diabetic patient with an unknown outcome. Data of the analysis indicators corresponding to the diabetic patient to be analyzed are obtained and input into the trained all-cause mortality risk prediction model. The risk score calculated in the model is used as the inflammatory metabolic index (IMCI) to participate in the subsequent analysis process.

[0058] S4, based on the inflammatory metabolic index, analyzes the mortality rate and cardiovascular disease status of the diabetic patients to be analyzed, and obtains the analysis results.

[0059] In a specific embodiment, the mortality rate and cardiovascular disease status of the diabetic patients to be analyzed are based on the inflammatory metabolic index, and the analysis results are obtained, including:

[0060] The optimal cutoff value of the inflammatory metabolic index most significantly associated with survival was determined by Youden index analysis; based on the optimal cutoff value, the diabetic patients to be analyzed were divided into a high inflammatory metabolic index group and a low inflammatory metabolic index group.

[0061] Kaplan-Meier survival analysis was used to analyze the survival of individuals in the high-inflammatory metabolic index group and the low-inflammatory metabolic index group, and survival curves for the two groups were obtained. The unit of the survival curves is months, and the outcome events are all-cause mortality or death from cardiovascular and cerebrovascular diseases.

[0062] The inflammatory metabolic index of the diabetic patients to be analyzed was used to assess mortality and disease status.

[0063] In a specific embodiment, a logistic regression classification model is used to analyze the inflammatory metabolic index of the diabetic patients to be analyzed, including mortality and disease status, specifically:

[0064] The inflammatory metabolic index was analyzed using the time-dependent ROC curve in the logistic regression classification model to predict the all-cause mortality rate of the diabetic patients under analysis at 1, 3, 5, and 10 years.

[0065] The nonlinear relationship between the inflammatory metabolic index and the mortality rate of diabetic patients was analyzed by using restricted cubic spline curves in a logistic regression classification model, and it was determined that there is a nonlinear relationship between the inflammatory metabolic index and the mortality rate of diabetic patients.

[0066] The inflammatory metabolic index was analyzed using the receiver operating characteristic curve in a logistic regression classification model to determine the relationship between the inflammatory metabolic index and cardiovascular disease events, including total cardiovascular disease, congestive heart failure, coronary heart disease, heart attack, stroke, angina pectoris, and stroke. The inflammatory metabolic index was found to have the best predictive effect on congestive heart failure.

[0067] The nonlinear relationship between the inflammatory metabolic index and cardiovascular disease events was analyzed using restricted cubic spline curves in a logistic regression classification model. This analysis revealed a linear relationship between the inflammatory metabolic index and total cardiovascular disease, congestive heart failure, heart attack, angina pectoris, stroke, and coronary heart disease.

[0068] Specifically, using Youden's index analysis, the optimal cutoff value for the IMCI most significantly associated with survival was determined to be 0.04. Participants were divided into two groups: a high IMCI group (IMCI > 0.04, n = 1386) and a low IMCI group (IMCI ≤ 0.04, n = 1969). Compared to the low IMCI group, participants in the high IMCI group were older, had a higher proportion of lighter skin, and were predominantly male; they also exhibited lower platelet counts, lymphocyte percentages, triglycerides, calcium, glycated hemoglobin, and albumin (ALB), but higher levels of white blood cells, gamma-glutamyl transferase, blood urea nitrogen, uric acid, creatinine, eosinophils, neutrophils, and monocytes.

[0069] Kaplan-Meier survival analysis was used to perform curve analysis on the survival of individuals with diabetes. The unit of the survival curve is months, and the outcome event is all-cause mortality or death from cardiovascular disease. (Reference) Figure 2 and Figure 3Using a trained all-cause mortality risk prediction model to construct the IMCI (Intense Motive Criterion), the optimal cutoff point was found through the Youden index. Patients were divided into high IMCI and low IMCI groups based on their IMCI scores. Kaplan-Meier survival analysis was used to compare the survival rates of these two groups, with the outcomes corresponding to all-cause mortality and death from cardiovascular disease, respectively. The analysis showed that regardless of whether the outcome was all-cause mortality or death from cardiovascular disease, the survival probabilities of the high and low IMCI groups, defined by the optimal cutoff point of this IMCI, were significantly different, effectively distinguishing the survival rates of the two groups.

[0070] Furthermore, a logistic regression classification model can be used to analyze the inflammatory metabolic index of the diabetic patients under analysis to assess mortality and disease status. Specifically, a time-dependent ROC analysis is performed on the IMCI constructed using a trained all-cause mortality risk prediction model to predict the all-cause mortality rate of the diabetic patient population at 1, 3, 5, and 10 years. The specific process is as follows: using the IMCI constructed by the model, the R package is used to analyze the all-cause mortality rate of the diabetic patient population at 1, 3, 5, and 10 years respectively, and ROC curves are plotted. (Reference) Figure 4 The area under the curve (AUC) of the IMCI for predicting all-cause mortality at 1, 3, 5, and 10 years were 0.71 (95% CI 0.63–0.78), 0.68 (95% CI 0.64–0.72), 0.67 (95% CI 0.67–0.71), and 0.67 (95% CI 0.65–0.70), respectively. These results suggest that the IMCI appears to have effective predictive value for both short-term and long-term mortality. (Reference) Figure 5 The ROC curves of IMCI predicting cardiovascular disease mortality at 1, 3, 5 and 10 years indicate that IMCI also has effective predictive value for short-term and long-term cardiovascular disease mortality.

[0071] refer to Figure 6 and 7 Nonlinear relationship analysis was performed using restricted cubic spline (RCS) curves in a logistic regression classification model. The analysis process involved using the immature mortality index (IMCI) constructed from the model and performing RCS analysis on the IMCI with all-cause mortality and cardiovascular disease mortality. RCS analysis showed no nonlinear relationship between the IMCI and all-cause mortality and cardiovascular disease mortality in the diabetic population (P < 0.05). 非线性 <0.05).

[0072] refer to Figure 8The receiver operating characteristic (ROC) curves of IMCI (Intense Motion Detection Complex) revealed the relationship between IMCI and cardiovascular diseases. The analysis process involved using the R package to analyze IMCI and various cardiovascular diseases and plotting ROC curves. After adjusting for covariates, the ROC curves based on the logistic regression classification model showed that IMCI had the highest diagnostic efficiency for congestive heart failure (AUC=0.75), followed by coronary artery disease (AUC=0.74), then total cardiovascular disease (AUC=0.73), heart attack (AUC=0.72), angina pectoris (AUC=0.72), and stroke (AUC=0.70). This indicates that the constructed high-level fitting feature IMCI also has a certain predictive effect on the diagnosis of cardiovascular diseases.

[0073] refer to Figure 9 This study employed restricted cubic spline curves based on a logistic regression classification model to flexibly model and visualize the relationship between intravascular coagulation (IMCI) and total cardiovascular disease, congestive heart failure, heart attack, angina pectoris, stroke, and coronary artery disease. The analysis process involved performing restricted cubic spline analysis on IMCI using the R package. After adjusting for the main covariates, a linear relationship was observed between IMCI and total cardiovascular disease, congestive heart failure, heart attack, angina pectoris, stroke, and coronary artery disease (P < 0.05). 非线性 >0.05). This indicates a positive correlation between the constructed inflammatory metabolic index (IMCI) and cardiovascular disease.

[0074] The embodiments of this application also compared the distinguishing effect of several individual important indicators with the inflammatory metabolic index. The results showed that the AUC of the inflammatory metabolic index was higher than that of the individual important indicators, indicating that the inflammatory metabolic index obtained by fitting can better distinguish between healthy people and people with cardiovascular and cerebrovascular diseases.

[0075] Further reference Figure 10 As an implementation of the methods shown in the above figures, this application provides an embodiment of a device for analyzing the mortality rate and cardiovascular disease status of diabetic patients. This device embodiment is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0076] This application provides a device for analyzing the mortality rate and cardiovascular disease status of diabetic patients, including:

[0077] The analysis indicator screening module 1 is configured to acquire metabolic and inflammatory indicators related to diabetes, select covariates and independent variables from the metabolic and inflammatory indicators, perform binary logistic regression analysis on the outcomes of diabetic patients based on the covariates and independent variables, and screen the analysis indicators from the independent variables. The outcome is survival or death due to cardiovascular and cerebrovascular diseases.

[0078] Model building module 2 is configured to build and train an all-cause mortality risk prediction model based on the Cox regression model, and obtain the trained all-cause mortality risk prediction model.

[0079] Prediction module 3 is configured to input the data of the analysis indicators and covariates corresponding to the diabetic patients to be analyzed into the trained all-cause mortality risk prediction model to obtain the intermediate calculated risk score and use it as the inflammatory metabolic index.

[0080] Analysis module 4 is configured to analyze the mortality rate and cardiovascular disease status of the diabetic patients to be analyzed based on the inflammatory metabolic index, and obtain the analysis results.

[0081] Figure 11 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. For example... Figure 11 As shown, the electronic device in this embodiment includes a processor 1101 and a memory 1102; wherein the memory 1102 is used to store computer execution instructions; and the processor 1101 is used to execute the computer execution instructions stored in the memory to implement the various steps performed by the electronic device in the above embodiment. For details, please refer to the relevant descriptions in the foregoing method embodiments.

[0082] Alternatively, the memory 1102 can be either standalone or integrated with the processor 1101.

[0083] When the memory 1102 is set up independently, the electronic device also includes a bus 1103 for connecting the memory 1102 and the processor 1101.

[0084] This invention also provides a computer storage medium storing computer execution instructions, which, when executed by the processor 1101, implement the above method.

[0085] This invention also provides a computer program product, including a computer program that, when executed by a processor 1101, implements the above-described method.

[0086] In the embodiments provided by this invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0087] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0088] Furthermore, the functional modules in the various embodiments of this invention can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit formed by the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0089] The integrated modules implemented as software functional modules described above can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor 1101 to execute some steps of the methods of the various embodiments of this application.

[0090] It should be understood that the processor 1101 described above can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor, or the processor 1101 can be any conventional processor 1101. The steps of the method disclosed in this invention can be directly manifested as the hardware processor 1101 executing the steps, or as a combination of hardware and software modules within the processor 1101 executing the steps.

[0091] The memory 1102 may include high-speed RAM memory, and may also include non-volatile memory NVM, such as at least one disk storage, and may also be a USB flash drive, portable hard drive, read-only memory, disk or optical disc, etc.

[0092] Bus 1103 can be an Industry Standard Architecture (ISA), a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Bus 1103 can be divided into address bus, data bus, control bus, etc. For ease of illustration, the bus 1103 in the accompanying drawings of this application is not limited to only one bus 1103 or one type of bus 1103.

[0093] The aforementioned storage medium can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible to general-purpose or special-purpose computers.

[0094] An exemplary storage medium is coupled to a processor 1101, enabling the processor 1101 to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor 1101. The processor 1101 and the storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor 1101 and the storage medium can exist as discrete components in an electronic device or a host device.

[0095] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing mortality and cardiovascular disease status in diabetic patients, characterized in that, Includes the following steps: Obtain metabolic and inflammatory indicators related to diabetes, select covariates and independent variables from the metabolic and inflammatory indicators, perform binary logistic regression analysis on the outcomes of diabetic patients based on the covariates and independent variables, and screen out analysis indicators from the independent variables. The outcomes are survival or death due to cardiovascular and cerebrovascular diseases. A Cox regression-based all-cause mortality risk prediction model was constructed and trained to obtain the trained all-cause mortality risk prediction model. The data of analytical indicators and covariates corresponding to the diabetic patients to be analyzed are input into the trained all-cause mortality risk prediction model to obtain the intermediate calculated risk score as the inflammatory metabolic index. The mortality rate and cardiovascular disease status of the diabetic patients to be analyzed were analyzed based on the inflammatory metabolic index, and the analysis results were obtained.

2. The method for analyzing mortality and cardiovascular disease status in diabetic patients according to claim 1, characterized in that, The metabolic and inflammatory indicators include demographic indicators, laboratory indicators, and questionnaire indicators. The demographic indicators include age, sex, height, weight, race, marital status, and education level. The laboratory indicators include BMI, waist circumference, C-reactive protein, triglycerides, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, total cholesterol, glycated hemoglobin, fasting blood glucose, insulin, systolic blood pressure, diastolic blood pressure, triglyceride-glucose index, white blood cell count, basophil count, basophil percentage, eosinophil count, eosinophil percentage, lymphocyte count, lymphocyte percentage, neutrophil count, neutrophil percentage, and monocyte count. The questionnaire included the following parameters: percentage of monocytes, mean corpuscular hemoglobin (MCH), mean corpuscular volume (MCV), red blood cell count, hematocrit, hemoglobin, red blood cell distribution width (RDW), platelet count, mean platelet volume (MCV), neutrophil-to-lymphocyte ratio, albumin, alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase (ALP), blood urea nitrogen, calcium, bicarbonate, gamma-glutamyl transferase (GGT), iron, lactate dehydrogenase (LDH), phosphorus, total protein, total bilirubin, uric acid, creatinine, sodium, potassium, chloride, osmolarity, globulin, creatine kinase, and hematocrit. The questionnaire also included indicators such as presence of hypertension, hyperlipidemia, hypercholesterolemia, ischemic heart failure, heart attack, coronary heart disease, angina pectoris, stroke, smoking and alcohol consumption, and physical activity index.

3. The method for analyzing mortality and cardiovascular disease status in diabetic patients according to claim 2, characterized in that, The analytical indicators include: lymphocyte percentage, monocyte percentage, neutrophil percentage, eosinophil percentage, eosinophil count, basophil count, white blood cell count, basophil percentage, neutrophil count, lymphocyte count, monocyte count, platelet count, red blood cell count, albumin, C-reactive protein, hemoglobin, mean corpuscular volume, mean corpuscular hemoglobin content, red blood cell distribution width, mean platelet volume, hematocrit, triglyceride-glucose index, weight, presence of hypertension, presence of hyperlipidemia, height, BMI, and total cholesterol.

4. The method for analyzing mortality and cardiovascular disease status in diabetic patients according to claim 2, characterized in that, The covariates include age, gender, race, marital status, education level, smoking and drinking habits, hypertension, and hyperlipidemia; the remaining indicators of the metabolic and inflammatory indicators, excluding the covariates, are used as independent variables in binary logistic regression analysis.

5. The method for analyzing mortality and cardiovascular disease status in diabetic patients according to claim 1, characterized in that, The mortality rate and cardiovascular disease status of the diabetic patients under analysis were analyzed based on the inflammatory metabolic index, and the analysis results include: The optimal cutoff value of the inflammatory metabolic index most significantly associated with survival was determined by Youden index analysis; the diabetic patients to be analyzed were divided into a high inflammatory metabolic index group and a low inflammatory metabolic index group according to the optimal cutoff value. Kaplan-Meier survival analysis was used to analyze the survival of individuals in the high-inflammatory metabolic index group and the low-inflammatory metabolic index group, and survival curves for the two groups were obtained. The unit of the survival curves was months, and the outcome events were all-cause mortality or death from cardiovascular and cerebrovascular diseases. The inflammatory metabolic index of the diabetic patients to be analyzed was used to assess mortality and disease status.

6. The method for analyzing mortality and cardiovascular disease status in diabetic patients according to claim 5, characterized in that, The analysis of mortality and disease status of the diabetic patients under investigation was conducted using a logistic regression classification model, specifically including: The inflammatory metabolic index was analyzed using the time-dependent ROC curve in the logistic regression classification model to predict the all-cause mortality rate of the diabetic patients under analysis at 1, 3, 5, and 10 years. The nonlinear relationship between the inflammatory metabolic index and the mortality rate of diabetic patients was analyzed by using restricted cubic spline curves in the logistic regression classification model, and it was determined that there is a nonlinear relationship between the inflammatory metabolic index and the mortality rate of diabetic patients. The inflammatory metabolic index was analyzed using the receiver operating characteristic curve in the logistic regression classification model to determine the relationship between the inflammatory metabolic index and cardiovascular disease events, including total cardiovascular disease, congestive heart failure, coronary heart disease, heart attack, stroke, angina pectoris, and stroke. The inflammatory metabolic index was found to have the best predictive effect on congestive heart failure. The nonlinear relationship between the inflammatory metabolic index and cardiovascular disease events was analyzed using restricted cubic spline curves in the logistic regression classification model. This analysis determined that there is a linear relationship between the inflammatory metabolic index and total cardiovascular disease, congestive heart failure, heart attack, angina pectoris, stroke, and coronary heart disease.

7. A device for analyzing mortality rate and cardiovascular disease status in diabetic patients, characterized in that, include: The analysis indicator screening module is configured to acquire metabolic and inflammatory indicators related to diabetes, select covariates and independent variables from the metabolic and inflammatory indicators, perform binary logistic regression analysis on the outcomes of diabetic patients based on the covariates and independent variables, and screen analysis indicators from the independent variables, wherein the outcome is survival or death due to cardiovascular and cerebrovascular diseases. The model building module is configured to build and train an all-cause mortality risk prediction model based on the Cox regression model, resulting in a trained all-cause mortality risk prediction model. The prediction module is configured to input the data of the analysis indicators and covariates corresponding to the diabetic patients to be analyzed into the trained all-cause mortality risk prediction model to obtain the intermediate calculated risk score as an inflammatory metabolic index. The analysis module is configured to analyze the mortality rate and cardiovascular disease status of the diabetic patients to be analyzed based on the inflammatory metabolic index, and obtain the analysis results.

8. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

Images