Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets

D'Ascenzo, F.; De Filippo, O.; Gallone, G.; Mittone, G.; Deriu, M. A.; Iannaccone, M.; Ariza-Sole, A.; Liebetrau, C.; Manzano-Fernandez, S.; Quadri, G.; Kinnaird, T.; Campo, G.; Simao Henriques, J. P.; Hughes, J. M.; Dominguez-Rodriguez, A.; Aldinucci, M.; Morbiducci, U.; Patti, G.; Raposeiras-Roubin, S.; Abu-Assi, E.; De Ferrari, G. M.; Piroli, F.; Saglietto, A.; Conrotto, F.; Omede, P.; Montefusco, A.; Pennone, M.; Bruno, F.; Bocchino, P. P.; Boccuzzi, G.; Cerrato, E.; Varbella, F.; Sperti, M.; Wilton, S. B.; Velicki, L.; Xanthopoulou, I.; Cequier, A.; Iniguez-Romo, A.; Munoz Pousa, I.; Cespon Fernandez, M.; Caneiro Queija, B.; Cobas-Paz, R.; Lopez-Cuenca, A.; Garay, A.; Blanco, P. F.; Rognoni, A.; Biondi Zoccai, G.; Biscaglia, S.; Nunez-Gil, I.; Fujii, T.; Durante, A.; Song, X.; Kawaji, T.; Alexopoulos, D.; Huczek, Z.; Gonzalez Juanatey, J. R.; Nie, S. -P.; Kawashiri, M. -A.; Colonnelli, I.; Cantalupo, B.; Esposito, R.; Leonardi, S.; Grosso Marra, W.; Chieffo, A.; Michelucci, U.; Piga, D.; Malavolta, M.; Gili, S.; Mennuni, M.; Montalto, C.; Oltrona Visconti, L.; Arfat, Y.

doi:10.1016/S0140-6736(20)32519-8

Background: The accuracy of current prediction tools for ischaemic and bleeding events after an acute coronary syndrome (ACS) remains insufficient for individualised patient management strategies. We developed a machine learning-based risk stratification model to predict all-cause death, recurrent acute myocardial infarction, and major bleeding after ACS. Methods: Different machine learning models for the prediction of 1-year post-discharge all-cause death, myocardial infarction, and major bleeding (defined as Bleeding Academic Research Consortium type 3 or 5) were trained on a cohort of 19 826 adult patients with ACS (split into a training cohort [80%] and internal validation cohort [20%]) from the BleeMACS and RENAMI registries, which included patients across several continents. 25 clinical features routinely assessed at discharge were used to inform the models. The best-performing model for each study outcome (the PRAISE score) was tested in an external validation cohort of 3444 patients with ACS pooled from a randomised controlled trial and three prospective registries. Model performance was assessed according to a range of learning metrics including area under the receiver operating characteristic curve (AUC). Findings: The PRAISE score showed an AUC of 0·82 (95% CI 0·78–0·85) in the internal validation cohort and 0·92 (0·90–0·93) in the external validation cohort for 1-year all-cause death; an AUC of 0·74 (0·70–0·78) in the internal validation cohort and 0·81 (0·76–0·85) in the external validation cohort for 1-year myocardial infarction; and an AUC of 0·70 (0·66–0·75) in the internal validation cohort and 0·86 (0·82–0·89) in the external validation cohort for 1-year major bleeding. Interpretation: A machine learning-based approach for the identification of predictors of events after an ACS is feasible and effective. The PRAISE score showed accurate discriminative capabilities for the prediction of all-cause death, myocardial infarction, and major bleeding, and might be useful to guide clinical decision making. Funding: None.