JMIR Publications

ABSTRACT

Background:

Accurately predicting left ventricular ejection fraction (LVEF) recovery after percutaneous coronary intervention (PCI) in patients with chronic coronary syndrome (CCS) is crucial for clinical decision-making.

Objective:

This study aimed to develop and compare multiple machine learning models to predict LVEF recovery and identify key contributing features.

Methods:

We retrospectively analyzed 520 CCS patients from the Clinical Deep Data Accumulation System (CLIDAS) database. Patients were categorized into four binary classification tasks based on baseline LVEF (≥50% or <50%) and degree of recovery: (1) LVEF increase >10% vs. ≤0% for good recovery tasks; (2) LVEF increase 0–10% vs. ≤0% for normal recovery tasks. For each task, three feature selection strategies (all features, Least Absolute Shrinkage and Selection Operator [LASSO], and recursive feature elimination [RFE]) were combined with four machine learning algorithms (XGBoost, CatBoost, LightGBM, and Random Forest), resulting in 48 models. Models were evaluated using 10-fold cross-validation and assessed by the area under the curve (AUC), decision curve analysis, and calibration plots.

Results:

The highest AUCs were achieved by RFE combined with XGBoost (0.93) for preserved LVEF with good recovery, LASSO combined with XGBoost (0.79) for preserved LVEF with normal recovery, LASSO combined with XGBoost (0.88) for reduced LVEF with good recovery, and RFE combined with XGBoost (0.84) for reduced LVEF with normal recovery. SHapley Additive exPlanation analysis identified uric acid, platelets, hematocrit, brain natriuretic peptide, glycated hemoglobin, glucose, creatinine, baseline LVEF, left ventricular end-diastolic internal diameter, heart rate, R wave amplitude in V5, and R wave amplitude in V6 as important predictive factors of LVEF recovery.

Conclusions:

Machine learning models incorporating feature selection strategies demonstrated strong predictive performance for LVEF recovery after PCI. The deployed web application supports clinical decision making and can improve the management of CCS patients after PCI.