Establishment and Evaluation of a Risk Prediction Model for Incidence of Acute Myocardial Infarction Based on Lasso Regression
XU Wei
WANG Hairu
FAN Yufeng
YU Peixia
QIN Yu
Abstract：Objective: To explore the risk factors for acute myocardial infarction (AMI) using routine laboratory test indicators and construct a predictive model through Lasso regression. Methods: A retrospective analysis was conducted on 50 AMI patients admitted to Dingxiang County People's Hospital from January to December 2024, along with 50 healthy controls during the same period. Student t-test or Mann-Whitney U test and chi-square test were used to compare the laboratory parameters. Lasso regression was applied to select variables and build the predictive model. The predictive value of the model was evaluated by the receiver operating characteristic (ROC) curve and the Hosmer-Lemeshow (H-L) goodness-of-fit test. Results: Lasso regression found that hematocrit (HCT) and high-density lipoprotein cholesterol (HDL-C) were negatively correlated with the occurrence of AMI, while neutrophil count (Neu), monocyte count (Mon), blood urea nitrogen (BUN), creatine kinase isoenzyme (CK-MB), and albumin-to-creatinine ratio (ACR) were positively correlated with the occurrence of AMI. Using these indicators as independent risk factors for AMI diagnosis, the model had an area under the curve (AUC) of 0.982 [95% CI (0.933, 0.998)], a sensitivity of 93.88%, and a specificity of 96.08%. The H-L goodness-of-fit test yielded P = 0.861. Conclusion: Neu, Mon, HCT, BUN, HDL-C, CK-MB, and ACR are risk factors for AMI. The constructed model has economic and easily obtainable indicators, and shows good predictive value and clinical utility.
Keywords：acute myocardial infarctionrisk factorsLasso regressionprediction model
Publication Date：2025-06-25
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1852-1856 )