Key result
Eight-variable random forest model predicts post-PCI in-hospital MACE with ~0.90 external AUROC.
Why the study?
Electronic medical record data can support early risk stratification in ACS, but models with large predictor sets are difficult to implement, motivating the development and external validation of a parsimonious, interpretable machine learning model for in-hospital MACE after PCI.
Does an eight-variable random forest machine learning model derived from routine electronic medical record data accurately predict in-hospital major adverse cardiovascular events in patients with acute coronary syndrome undergoing percutaneous coronary intervention?
Cohort (n=1,726)
Yes
Does an eight-variable random forest machine learning model derived from routine electronic medical record data accurately predict in-hospital major adverse cardiovascular events in patients with acute coronary syndrome undergoing percutaneous coronary intervention?
A parsimonious eight-variable random forest model using routine electronic medical record data provides high discrimination and interpretable early risk stratification for in-hospital major adverse cardiovascular events in ACS patients undergoing PCI.
Answers are grounded in this paper and cite their sources.
May support early MACE risk stratification after ACS-PCI using routine EMR data; leaves open prospective validation before clinical adoption.
Background Electronic medical record (EMR) data provide an opportunity to support early risk stratification in acute coronary syndrome (ACS), but models with large predictor sets may be difficult to implement. We aimed to develop and externally validate a parsimonious, interpretable machine learning model for in-hospital major adverse cardiovascular events (MACE) in patients with ACS undergoing percutaneous coronary intervention (PCI). Methods: This two-center retrospective cohort study included 1,726 patients: 1,218 in the derivation cohort and 508 in an independent external validation cohort. The primary outcome was in-hospital MACE, defined as a composite of death, cerebral hemorrhage, cerebral infarction, cardiogenic shock, cardiac rupture, recurrent myocardial infarction, stent thrombosis, or Bleeding Academic Research Consortium bleeding events. A total of 125 candidate EMR variables were evaluated. LASSO and Boruta-based feature selection, alternative preprocessing strategies including ADASYN, seven machine learning algorithms, and grid-search cross-validation were compared. Discrimination was assessed using AUROC and AUPRC, with calibration and decision-curve analyses used to assess agreement and potential clinical utility. Results: In-hospital MACE occurred in 138 of 1,218 patients (11.3%) in the derivation cohort and 15 of 508 patients (3.0%) in the external cohort. The final random forest model retained eight predictors: Killip class, inorganic phosphorus, extracorporeal membrane oxygenation, left ventricular ejection fraction, absolute neutrophil count, total protein, alanine aminotransferase, and potassium. The model achieved an AUROC of 0.82 (95% CI 0.73–0.90) in internal validation and 0.90 (95% CI 0.85–0.95) in external validation. At the reported operating point, sensitivity was 0.488 and specificity was 0.991. Conclusions: An eight-variable random forest model derived from routinely collected EMR data showed good discrimination and preserved ranking performance in an independent hospital cohort. The model is best considered an early in-hospital risk-stratification tool; prospective validation with a prespecified prediction time is required before clinical implementation.
No takes yet. Share an insight, caveat, or question.
Yan et al. (2026) conducted a cohort in Acute coronary syndrome undergoing percutaneous coronary intervention (n=1,726). Eight-variable Random Forest machine learning prediction model (Killip class, inorganic phosphorus, ECMO, LVEF, absolute neutrophil count, total protein, ALT, potassium) vs. Alternative preprocessing strategies (LASSO, Boruta, ADASYN) and six other machine learning algorithms (LightGBM, SVM, XGBoost, LR, KNN, DNN) was evaluated on In-hospital MACE (composite of death, cerebral hemorrhage, cerebral infarction, cardiogenic shock, cardiac rupture, recurrent myocardial infarction, stent thrombosis, or BARC bleeding events) (AUROC 0.90 in external validation (0.82 in internal validation), 95% CI 0.85-0.95). An 8-variable random forest model predicted in-hospital MACE after PCI in ACS patients with an AUROC of 0.82 (95% CI 0.73-0.90) internally and 0.90 (95% CI 0.85-0.95) in external validation.
Synapse has enriched 10 related papers. Consider them for comparative context: