Predicting cardiovascular risk from national administrative databases using a combined survival analysis and deep learning approach.

Journal: International journal of epidemiology
PMID: 34910160

Abstract

BACKGROUND: Machine learning-based risk prediction models may outperform traditional statistical models in large datasets with many variables, by identifying both novel predictors and the complex interactions between them. This study compared deep learning extensions of survival analysis models with Cox proportional hazards models for predicting cardiovascular disease (CVD) risk in national health administrative datasets.

Authors

  • Sebastiano Barbieri
    Centre for Big Data Research in Health, UNSW, Sydney, Australia.
  • Suneela Mehta
    Section of Epidemiology and Biostatistics, University of Auckland, Auckland, New Zealand.
  • Billy Wu
    Section of Epidemiology and Biostatistics, University of Auckland, Auckland, New Zealand.
  • Chrianna Bharat
    National Drug and Alcohol Research Centre, University of New South Wales, Sydney, NSW, Australia. Electronic address: c.bharat@student.unsw.edu.au.
  • Katrina Poppe
    Section of Epidemiology and Biostatistics, University of Auckland, Auckland, New Zealand.
  • Louisa Jorm
    Centre for Big Data Research in Health, University of New South Wales, Sydney, NSW, Australia.
  • Rod Jackson
    Section of Epidemiology and Biostatistics, University of Auckland, Auckland, New Zealand.

Keywords

External Resources

Popular Topics
Recent Journals