Development and Validation of a Machine Learning Model Integrating SPECT MPI Multiparametric Features for Risk Prediction in Coronary Artery Disease with Preserved Ejection Fraction
Abstract
Abstract Objective Early identification of high-risk patients with coronary artery disease (CAD) and preserved left ventricular ejection fraction (LVEF) is essential for optimizing management. This study aimed to develop a machine learning model integrating clinical and myocardial perfusion imaging (MPI)–derived parameters to predict major adverse cardiac events (MACE). Methods We retrospectively included 1,675 patients with suspected or confirmed CAD and preserved LVEF who underwent resting MPI. Demographic, clinical, and imaging variables were collected, and missing data were handled via multiple imputation. Ten machine learning algorithms were developed and compared. Model performance was assessed by the area under the receiver operating characteristic curve (AUC) and additional metrics. Shapley additive explanations analysis (SHAP) was applied to interpret feature contributions. Results The CatBoost model showed the best performance, with cross-validated AUC of 0.693, accuracy 0.632, precision 0.551, F1 score 0.451, and Brier score 0.234. SHAP analysis identified nine key predictors: prior cardio-cerebrovascular disease, age, peak filling rate, low-density lipoprotein cholesterol, total perfusion deficit, eccentricity index (no-gated), entropy, coronary stenosis ≥ 50%, and New York Heart Association functional class. Conclusions We developed an interpretable CatBoost model integrating clinical and MPI features to predict MACE risk in CAD patients with preserved LVEF. The…
Read the paper
Related studies
- Comparative effectiveness of GLP-1 receptor agonists on glycaemic control, body weight, and lipid profile for type 2 diabetes: systematic review and network meta-analysis
- Adverse effects of cyclooxygenase 2 inhibitors on renal and arrhythmia events: meta-analysis of randomized trials
- Benefits and harms of drug treatment for type 2 diabetes: systematic review and network meta-analysis of randomised controlled trials
- Comparative effectiveness and safety of statins as a class and of specific statins for primary prevention of cardiovascular disease: A systematic review, meta‐analysis, and network meta‐analysis of randomized trials with 94,283 participants
- Screen time increases overweight and obesity risk among adolescents: a systematic review and dose-response meta-analysis
- Exposure to WHO AWaRe antibiotics and isolation of multi-drug resistant bacteria: a systematic review and meta-analysis
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.