Comparative analysis of machine learning and regularized regression models for predicting cardiovascular outcomes in patients with type 2 diabetes after acute coronary syndrome
4 affiliations
- 1RISE-Health, Departamento de Cirurgia e Fisiologia, Faculdade de Medicina da Universidade do Porto
- 2Centre D’Investigation Clinique-Plurithématique Inserm CIC-P 1433, Inserm U1116, CHRU Nancy Hopitaux de Brabois, F-CRIN INI-CRC (Cardiovascular and Renal Clinical Trialists), Université de Lorraine
- 3Division of Cardiology, McGill University Health Centre
- 4Calhoun Cardiology Center, University of Connecticut School of Medicine
Abstract
Identifying type 2 diabetes (T2D) patients at high cardiovascular risk following acute coronary syndrome (ACS) remains challenging despite treatment advances. We systematically compared machine learning and regularized regression methods for predicting cardiovascular outcomes using data from the EXAMINE trial (NCT00968708). Prediction models incorporating over 100 clinical and biomarker variables were developed for three endpoints: cardiovascular death, nonfatal myocardial infarction, or stroke; all-cause mortality; and cardiovascular death or heart failure hospitalization. Eleven algorithms were evaluated using area under the ROC curve (AUC) at 12 and 24 months, with tenfold stratified cross-validation. Regularized regression methods showed the most consistent and generalizable performance, with substantial overlap in confidence intervals between top-performing methods. At 24 months, among regularized models LASSO achieved the highest testing AUC for cardiovascular death or heart failure hospitalization (0.80, 95% CI 0.75–0.85) and all-cause mortality (0.75, 95% CI 0.69–0.81), while the best regularized model for the primary composite endpoint reached an AUC of 0.69 (95% CI 0.64–0.74); the strongest discrimination overall was observed for the 12-month heart failure endpoint (AUC up to 0.83). Adding the proteomic panel to clinical predictors improved or maintained discrimination across all six outcome-by-horizon strata (mean ΔAUC + 0.03). Complex algorithms including neural networks and random forests exhibited overfitting despite cross-validation. These findings indicate that regularized regression methods provide the most consistent and generalizable performance for cardiovascular risk prediction in T2D patients with recent ACS. For the heart failure hospitalization endpoint, the leading regularized model outperformed the best-tuned tree-ensemble method (XGBoost) significantly at 12 months (ΔAUC + 0.065, 95% CI + 0.031 to + 0.100, DeLong p < 0.001) and by a consistent but non-significant margin at 24 months (ΔAUC + 0.037, 95% CI − 0.007 to + 0.082, p = 0.10). The superior performance for heart failure events suggests current clinical and proteomic markers are particularly valuable for heart failure risk stratification in this population.
Related
- Predicting cardiovascular disease in peritoneal dialysis patients using glycated proteomics and machine learning: A prospective multicentre study
- Identifying Mild Cognitive Impairment from Routinely Collected Physical, Functional and Psychosocial Measures in Community-Dwelling Older Adults: A Comparative Machine-Learning and Regression Modelling Study in the Northern Japanese ORANGE Registry.
- Explainable Machine Learning for Predicting Major Adverse Renal and Cardiovascular Events in Acute Myocardial Infarction With Chronic Kidney Disease: Algorithm Development and Validation
- Predicting microvascular invasion in hepatocellular carcinoma using contrast-enhanced CT-based deep learning models: a comparative study of transformer, CNN, and MIL
- Development and validation of a novel metabolic-inflammatory health-related nomogram for predicting in-hospital mortality in older patients with type 2 diabetes mellitus combined with cardiovascular disease
BibTeX
@article{barros2026comparative,
title = {{Comparative analysis of machine learning and regularized regression models for predicting cardiovascular outcomes in patients with type 2 diabetes after acute coronary syndrome}},
author = {António S. Barros and Nicolas Girerd and Abhinav Sharma and Kevin Duarte and João Sérgio Neves and Adelino Leite-Moreira and William B. White and Faiez Zannad and João Pedro Ferreira},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-62630-z},
url = {https://doi.org/10.1038/s41598-026-62630-z},
note = {CC BY},
}
RIS
TY - JOUR
TI - Comparative analysis of machine learning and regularized regression models for predicting cardiovascular outcomes in patients with type 2 diabetes after acute coronary syndrome
AU - António S. Barros
AU - Nicolas Girerd
AU - Abhinav Sharma
AU - Kevin Duarte
AU - João Sérgio Neves
AU - Adelino Leite-Moreira
AU - William B. White
AU - Faiez Zannad
AU - João Pedro Ferreira
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-62630-z
UR - https://doi.org/10.1038/s41598-026-62630-z
AB - Identifying type 2 diabetes (T2D) patients at high cardiovascular risk following acute coronary syndrome (ACS) remains challenging despite treatment advances. We systematically compared machine learning and regularized regression methods for predicting cardiovascular outcomes using data from the EXAMINE trial (NCT00968708). Prediction models incorporating over 100 clinical and biomarker variables were developed for three endpoints: cardiovascular death, nonfatal myocardial infarction, or stroke; all-cause mortality; and cardiovascular death or heart failure hospitalization. Eleven algorithms were evaluated using area under the ROC curve (AUC) at 12 and 24 months, with tenfold stratified cross-validation. Regularized regression methods showed the most consistent and generalizable performance, with substantial overlap in confidence intervals between top-performing methods. At 24 months, among regularized models LASSO achieved the highest testing AUC for cardiovascular death or heart failure hospitalization (0.80, 95% CI 0.75–0.85) and all-cause mortality (0.75, 95% CI 0.69–0.81), while the best regularized model for the primary composite endpoint reached an AUC of 0.69 (95% CI 0.64–0.74); the strongest discrimination overall was observed for the 12-month heart failure endpoint (AUC up to 0.83). Adding the proteomic panel to clinical predictors improved or maintained discrimination across all six outcome-by-horizon strata (mean ΔAUC + 0.03). Complex algorithms including neural networks and random forests exhibited overfitting despite cross-validation. These findings indicate that regularized regression methods provide the most consistent and generalizable performance for cardiovascular risk prediction in T2D patients with recent ACS. For the heart failure hospitalization endpoint, the leading regularized model outperformed the best-tuned tree-ensemble method (XGBoost) significantly at 12 months (ΔAUC + 0.065, 95% CI + 0.031 to + 0.100, DeLong p < 0.001) and by a consistent but non-significant margin at 24 months (ΔAUC + 0.037, 95% CI − 0.007 to + 0.082, p = 0.10). The superior performance for heart failure events suggests current clinical and proteomic markers are particularly valuable for heart failure risk stratification in this population.
SN - 2045-2322
ER -