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

Acute Coronary Syndrome / complications Adult Clinical Decision-Making Datasets as Topic Female Hemorrhage / etiology Humans Machine Learning Male Mortality Postoperative Complications

Journal

Lancet (London, England)

ISSN: 1474-547X

Titre abrégé: Lancet

Pays: England

ID NLM: 2985213R

Informations de publication

Date de publication:
16 01 2021

Historique:

received: 28 08 2020

revised: 16 10 2020

accepted: 09 11 2020

entrez: 17 1 2021

pubmed: 18 1 2021

medline: 23 2 2021

Statut: ppublish

Résumé

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. 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). 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. 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. None.

Sections du résumé

BACKGROUND

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.

Identifiants

DOI: 10.1016/S0140-6736(20)32519-8 PMID: 33453782

pubmed: 33453782

pii: S0140-6736(20)32519-8

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

pii:

doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

Pagination

199-207

Investigateurs

Francesco Piroli (F)

Andrea Saglietto (A)

Federico Conrotto (F)

Pierluigi Omedé (P)

Antonio Montefusco (A)

Mauro Pennone (M)

Francesco Bruno (F)

Pier Paolo Bocchino (PP)

Giacomo Boccuzzi (G)

Enrico Cerrato (E)

Ferdinando Varbella (F)

Michela Sperti (M)

Stephen B Wilton (SB)

Lazar Velicki (L)

Ioanna Xanthopoulou (I)

Angel Cequier (A)

Andres Iniguez-Romo (A)

Isabel Munoz Pousa (I)

Maria Cespon Fernandez (M)

Berenice Caneiro Queija (B)

Rafael Cobas-Paz (R)

Angel Lopez-Cuenca (A)

Alberto Garay (A)

Pedro Flores Blanco (PF)

Andrea Rognoni (A)

Giuseppe Biondi Zoccai (G)

Simone Biscaglia (S)

Ivan Nunez-Gil (I)

Toshiharu Fujii (T)

Alessandro Durante (A)

Xiantao Song (X)

Tetsuma Kawaji (T)

Dimitrios Alexopoulos (D)

Zenon Huczek (Z)

Jose Ramon Gonzalez Juanatey (JR)

Shao-Ping Nie (SP)

Masa-Aki Kawashiri (MA)

Iacopo Colonnelli (I)

Barbara Cantalupo (B)

Roberto Esposito (R)

Sergio Leonardi (S)

Walter Grosso Marra (W)

Alaide Chieffo (A)

Umberto Michelucci (U)

Dario Piga (D)

Marta Malavolta (M)

Sebastiano Gili (S)

Marco Mennuni (M)

Claudio Montalto (C)

Luigi Oltrona Visconti (L)

Yasir Arfat (Y)

Commentaires et corrections

Type : CommentIn