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 19826 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.
Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets
D'Ascenzo F.
First
;De Filippo O.;Gallone G.;Mittone G.;Iannaccone M.;Quadri G.;Hughes J. M.;Aldinucci M.;Patti G.;De Ferrari G. M.Last
;Iacopo ColonnelliMembro del Collaboration Group
;Roberto EspositoMembro del Collaboration Group
;Yasir ArfatMembro del Collaboration Group
;Francesco PiroliMembro del Collaboration Group
;Andrea SagliettoMembro del Collaboration Group
;Federico ConrottoMembro del Collaboration Group
;Pier Paolo BocchinoMembro del Collaboration Group
;Cantalupo BarbaraMembro del Collaboration Group
2021-01-01
Abstract
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 19826 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.File | Dimensione | Formato | |
---|---|---|---|
1-s2.0-S0140673620325198-main.pdf
Accesso riservato
Tipo di file:
PDF EDITORIALE
Dimensione
762.9 kB
Formato
Adobe PDF
|
762.9 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
20201012paper.doc
Accesso aperto
Descrizione: bozza
Tipo di file:
PREPRINT (PRIMA BOZZA)
Dimensione
134.5 kB
Formato
Microsoft Word
|
134.5 kB | Microsoft Word | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.