Machine learning-based risk prediction for major adverse cardiovascular events in a Brazilian hospital: Development, external validation, and interpretability.

Journal: PloS one
Published Date:

Abstract

BACKGROUND: Studies of cardiovascular disease risk prediction by machine learning algorithms often do not assess their ability to generalize to other populations and few of them include an analysis of the interpretability of individual predictions. This manuscript addresses the development and validation, both internal and external, of predictive models for the assessment of risks of major adverse cardiovascular events (MACE). Global and local interpretability analyses of predictions were conducted towards improving MACE's model reliability and tailoring preventive interventions.

Authors

  • Gilson Yuuji Shimizu
    Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.
  • Michael Schrempf
    Steiermärkische Krankenanstaltengesellschaft m. b. H., Graz, Austria.
  • Elen Almeida Romão
    Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.
  • Stefanie Jauk
    CBmed, Graz, Austria.
  • Diether Kramer
    Steiermärkische Krankenanstaltengesellschaft m.b.H. (KAGes), Graz, Austria.
  • Peter P Rainer
    Medical University of Graz, Graz, Austria.
  • José Abrão Cardeal da Costa
    Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.
  • João Mazzoncini de Azevedo-Marques
    Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.
  • Sandro Scarpelini
    Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.
  • Katia Mitiko Firmino Suzuki
    Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.
  • Hilton Vicente César
    Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, São Paulo, Brazil.
  • Paulo Mazzoncini de Azevedo-Marques
    Ribeirão Preto Medical School, University of São Paulo, São Paulo, Brazil.