Key result
Machine learning model predicts 1-year mortality in non-ischaemic acute myocardial injury with ~0.77 AUC.
Why the study?
Non-ischaemic acute myocardial injury carries high long-term mortality, yet no dedicated risk prediction tool existed and acute coronary syndrome scores inadequately capture its systemic pathophysiology.
Does an interpretable machine learning model accurately predict 1-year all-cause mortality in patients with non-ischaemic acute myocardial injury?
Cohort (n=78,666)
Yes
Does an interpretable machine learning model accurately predict 1-year all-cause mortality in patients with non-ischaemic acute myocardial injury?
An interpretable gradient boosting machine model using 11 routine clinical variables accurately predicts 1-year mortality in patients with non-ischaemic acute myocardial injury, highlighting renal function and inflammation as primary prognostic drivers.
May aid risk stratification in non-ischaemic acute myocardial injury; extends ML models to this population but remains hypothesis-generating pending trials.
Background Non-ischaemic acute myocardial injury (NI-AMInj) carries high long-term mortality, yet no dedicated risk prediction tool exists. Existing scores developed for acute coronary syndromes inadequately capture the systemic pathophysiology of NI-AMInj. Purpose To develop and externally validate an interpretable machine learning model predicting 1-year all-cause mortality in NI-AMInj, and to identify key prognostic drivers. Methods NI-AMInj patients were identified from a regional multi-centre platform (development cohort, 2013–2022) and an independent critical care database (external validation, 2008–2022). NI-AMInj required troponin above the 99th percentile with >20% dynamic change, excluding acute myocardial infarction. The development cohort was split 8:2 for training and internal validation. Feature selection used a consensus strategy across LASSO, Boruta, and recursive feature elimination. Nine algorithms were compared. Performance was evaluated by area under the curve (AUC), calibration, and decision curve analysis. Shapley Additive exPlanations (SHAP) provided interpretability. Results 78,666 patients were included (development: 67,773; external: 10,893; 1-year mortality: 19.3% vs 34.7%). Eleven predictors were selected: age, estimated glomerular filtration rate (eGFR), white blood cell count (WBC), pulmonary infection, heart failure, malignancy, intensive care unit admission, cardiology admission, surgical procedures, reperfusion therapy, and statin use. Gradient boosting machine (GBM) achieved optimal performance (internal AUC: 0.783; external AUC: 0.773), with good calibration and positive net clinical benefit. SHAP analysis identified eGFR, WBC, pulmonary infection, age, and heart failure as top prognostic drivers. Statin use and reperfusion showed protective associations. A web-based calculator was deployed for individualised assessment. Conclusions An interpretable GBM model using 11 routine clinical variables accurately predicts 1-year mortality in NI-AMInj with good cross-population generalisability. Renal function and inflammatory markers are dominant prognostic determinants. This tool may support early risk stratification in this high-risk population.SHAP
No takes yet. Share an insight, caveat, or question.
Sun et al. (2026) conducted a cohort in Non-ischaemic acute myocardial injury (NI-AMInj) (n=78,666). Gradient boosting machine (GBM) risk prediction model vs. Eight other machine learning algorithms was evaluated on 1-year all-cause mortality (Internal AUC 0.783; External AUC 0.773). A gradient boosting machine model using 11 clinical variables accurately predicted 1-year all-cause mortality in non-ischaemic acute myocardial injury (internal AUC 0.783, external AUC 0.773).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: