Explainable Machine Learning for Predicting Major Adverse Renal and Cardiovascular Events in Acute Myocardial Infarction With Chronic Kidney Disease: Algorithm Development and Validation
Abstract
BackgroundMajor adverse renal and cardiovascular events (MARCE) have been proposed as a comprehensive end point reflecting both cardiac and renal outcomes in patients with acute myocardial infarction (AMI) and chronic kidney disease (CKD). However, existing prediction tools lack accuracy and generalizability for this high-risk population. ObjectiveThis study aimed to develop and externally validate explainable machine learning models and a nomogram for predicting in-hospital MARCE among patients with AMI and CKD. MethodsWe enrolled patients with AMI and CKD who underwent emergency treatment at the First Affiliated Hospital of Wenzhou Medical University as the discovery cohort and those at Wenzhou TCM (traditional Chinese medicine) Hospital of Zhejiang Chinese Medical University as the external validation cohort. Clinical features, including demographic details, comorbidities, laboratory results, echocardiography measurements, procedural details, and medication parameters, were collected for all participants. Important variables were selected using least absolute shrinkage and selection operator regression in the training set. We developed extreme gradient boosting (XGBoost), random forest, decision tree, and logistic regression (LR) models and evaluated their discrimination, calibration, and classification metrics in the hold-out test set and external cohort. ResultsIn the training set, we identified 6 important variables (Killip class, lactate, estimated glomerular filtration rate, use of diuretics, use of beta-blockers, and use of renin-angiotensin system inhibitors). In the test set, model discrimination was comparable across XGBoost (area under the receiver operating characteristic curve [AUC] 0.882, 95% CI 0.816-0.947), LR (AUC 0.875, 95% CI 0.799-0.950), and random forest (AUC 0.870, 95% CI 0.800-0.940), while decision tree showed lower performance (AUC 0.814, 95% CI 0.720-0.886). Shapley additive explanations (SHAP) values illustrated both global and individual feature contributions in the XGBoost model. A nomogram based on LR achieved an AUC of 0.873 (95% CI 0.714-0.926) in external validation. ConclusionsOur study identified 6 important predictors and provided a series of prediction models to enhance risk stratification of MARCE for patients with AMI and CKD. These models might aid in stratifying risk and choosing appropriate therapeutic strategies in the management of patients with AMI and CKD.
Related
- Development and internal validation of an oxygen saturation-based prehospital cardiac risk assessment index (P-CRAI) for predicting 30-day mortality in acute myocardial infarction: a multicentre registry study from the Mie ACS Registry, Japan
- Predictive value of combined estimated plasma volume status and neutrophil-to-lymphocyte ratio for cardiovascular mortality in patients with acute myocardial infarction with heart failure
- Evaluation of Clinical SYNTAX Score in Predicting New-Onset Atrial Fibrillation and Long-Term Prognosis in Patients Hospitalized with Non-ST Segment Elevation Myocardial Infarction
- Community-Level Wastewater Surveillance of Nicotine Biomarkers Tracks Cardiovascular Disease Burden and Myocardial Infarction
- Mental Stress-Induced Myocardial Ischemia and Cardiovascular Events in Women after a Premature Myocardial Infarction: A Prospective Cohort Study
BibTeX
@article{feng2026explainable,
title = {{Explainable Machine Learning for Predicting Major Adverse Renal and Cardiovascular Events in Acute Myocardial Infarction With Chronic Kidney Disease: Algorithm Development and Validation}},
author = {Wang Feng and Ruihao Jiang and Wendi Huang and Chuanpeng Wang and Zhuoquan Wang and Jingwen Chang and Jinguo Cheng and Nianshao Chen and Xi Liu},
journal = {JMIR Medical Informatics},
year = {2026},
month = oct,
doi = {10.2196/96654},
url = {https://doi.org/10.2196/96654},
note = {CC BY},
}
RIS
TY - JOUR
TI - Explainable Machine Learning for Predicting Major Adverse Renal and Cardiovascular Events in Acute Myocardial Infarction With Chronic Kidney Disease: Algorithm Development and Validation
AU - Wang Feng
AU - Ruihao Jiang
AU - Wendi Huang
AU - Chuanpeng Wang
AU - Zhuoquan Wang
AU - Jingwen Chang
AU - Jinguo Cheng
AU - Nianshao Chen
AU - Xi Liu
PY - 2026
DA - 2026/10/23
JO - JMIR Medical Informatics
DO - 10.2196/96654
UR - https://doi.org/10.2196/96654
AB - BackgroundMajor adverse renal and cardiovascular events (MARCE) have been proposed as a comprehensive end point reflecting both cardiac and renal outcomes in patients with acute myocardial infarction (AMI) and chronic kidney disease (CKD). However, existing prediction tools lack accuracy and generalizability for this high-risk population. ObjectiveThis study aimed to develop and externally validate explainable machine learning models and a nomogram for predicting in-hospital MARCE among patients with AMI and CKD. MethodsWe enrolled patients with AMI and CKD who underwent emergency treatment at the First Affiliated Hospital of Wenzhou Medical University as the discovery cohort and those at Wenzhou TCM (traditional Chinese medicine) Hospital of Zhejiang Chinese Medical University as the external validation cohort. Clinical features, including demographic details, comorbidities, laboratory results, echocardiography measurements, procedural details, and medication parameters, were collected for all participants. Important variables were selected using least absolute shrinkage and selection operator regression in the training set. We developed extreme gradient boosting (XGBoost), random forest, decision tree, and logistic regression (LR) models and evaluated their discrimination, calibration, and classification metrics in the hold-out test set and external cohort. ResultsIn the training set, we identified 6 important variables (Killip class, lactate, estimated glomerular filtration rate, use of diuretics, use of beta-blockers, and use of renin-angiotensin system inhibitors). In the test set, model discrimination was comparable across XGBoost (area under the receiver operating characteristic curve [AUC] 0.882, 95% CI 0.816-0.947), LR (AUC 0.875, 95% CI 0.799-0.950), and random forest (AUC 0.870, 95% CI 0.800-0.940), while decision tree showed lower performance (AUC 0.814, 95% CI 0.720-0.886). Shapley additive explanations (SHAP) values illustrated both global and individual feature contributions in the XGBoost model. A nomogram based on LR achieved an AUC of 0.873 (95% CI 0.714-0.926) in external validation. ConclusionsOur study identified 6 important predictors and provided a series of prediction models to enhance risk stratification of MARCE for patients with AMI and CKD. These models might aid in stratifying risk and choosing appropriate therapeutic strategies in the management of patients with AMI and CKD.
SN - 2291-9694
ER -