1. Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets
- Author
-
Iván J. Núñez-Gil, José Ramón González Juanatey, Marco G. Mennuni, Umberto Michelucci, Sergio Manzano-Fernández, Tim Kinnaird, Marco Aldinucci, Claudio Montalto, Giuseppe Patti, Pierluigi Omedè, Gianluca Mittone, Tetsuma Kawaji, Berenice Caneiro Queija, Lazar Velicki, Dario Piga, Alessandro Durante, Francesco Bruno, Stephen B. Wilton, Roberto Esposito, Andrés Íñiguez-Romo, Sergio Raposeiras-Roubín, Enrico Cerrato, Ovidio De Filippo, Iacopo Colonnelli, Masa-aki Kawashiri, Walter Grosso Marra, Andrea Saglietto, Guglielmo Gallone, Michela Sperti, Pier Paolo Bocchino, Gianluca Campo, Albert Ariza-Solé, Rafael Cobas-Paz, Angel Cequier, Antonio Montefusco, Federico Conrotto, Sergio Leonardi, Barbara Cantalupo, Andrea Rognoni, Alaide Chieffo, Marco Agostino Deriu, Francesco Piroli, Yasir Arfat, Fabrizio D'Ascenzo, Zenon Huczek, Alberto Dominguez-Rodriguez, Sebastiano Gili, Giorgio Quadri, Isabel Muñoz Pousa, María Cespón Fernández, Ferdinando Varbella, James M. Hughes, Mauro Pennone, Luigi Oltrona Visconti, José P.S. Henriques, Xiantao Song, Ioanna Xanthopoulou, Pedro Flores Blanco, Simone Biscaglia, Gaetano M. De Ferrari, Umberto Morbiducci, Giuseppe Biondi Zoccai, Shaoping Nie, Toshiharu Fujii, Emad Abu-Assi, Dimitrios Alexopoulos, Alberto Garay, Ángel López-Cuenca, Giacomo Boccuzzi, Christoph Liebetrau, Marta Malavolta, Mario Iannaccone, Cardiology, and ACS - Atherosclerosis & ischemic syndromes
- Subjects
Adult ,Male ,Acute coronary syndrome ,media_common.quotation_subject ,Clinical Decision-Making ,MEDLINE ,Datasets as Topic ,Socio-culturale ,Hemorrhage ,030204 cardiovascular system & hematology ,Machine learning ,computer.software_genre ,law.invention ,Machine Learning ,03 medical and health sciences ,Postoperative Complications ,0302 clinical medicine ,Randomized controlled trial ,law ,Humans ,Medicine ,acute coronary syndromes ,030212 general & internal medicine ,Myocardial infarction ,Acute Coronary Syndrome ,Mortality ,Praise ,Adverse effect ,cardiovascular disease ,machine learning ,myocardial infarction ,media_common ,Receiver operating characteristic ,business.industry ,General Medicine ,medicine.disease ,3. Good health ,Cohort ,Female ,Artificial intelligence ,business ,computer - Abstract
Summary 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.
- Published
- 2021