Risk prediction of mechanical complications in acute myocardial infarction patients with prior malignancy

Acute myocardial infarction (AMI) patients with prior malignancy have been largely understudied, despite potentially facing higher risks of adverse outcomes. This case-control study aimed to identify independent risk factors for in-hospital mechanical complications among AMI patients with prior malignancies.

This study enrolled AMI patients with prior malignancy who were hospitalized for treatment. Patients were divided into complication and control groups based on the occurrence of in-hospital mechanical complications. The mechanical complications in this study were defined as papillary muscle rupture (with or without acute mitral regurgitation), ventricular septal defect, large pericardial effusion, left ventricular pseudoaneurysm, and free wall rupture. Relaxed least absolute shrinkage and selection operator (LASSO) logistic regression was used to identify independent risk factors, and Shapley Additive Explanations (SHAP) analysis was employed to evaluate factors. A predictive nomogram was developed based on risk factors and evaluated through internal validation using Bootstrap method with Brier score.

A total of 127 AMI patients with prior malignancy were included, among whom 26 (20.5) were divided in the complication group. The in-hospital mortality was higher in the complication group compared to the control group [2 (7.7%) vs. 0 (0.0%), P = 0.041]. Following baseline analysis, LASSO logistic regression identified six independent risk factors, ranked by SHAP values as follows: body mass index, D-dimer, pulmonary hypertension, wall motion abnormalities, ventricular arrhythmia, and statin use. The nomogram, constructed by these factors, demonstrated good predictive performance, with a Brier score of 0.116 in the internal validation.

This study highlights key clinical predictors for mechanical complications in AMI patients with prior malignancy. The long-term usage of statins might benefit this specific patient population even after the onset of AMI. The proposed nomogram offers a practical tool for early risk assessment and may support improved clinical decision-making.