Can machine-learning improve cardiovascular risk prediction using routine clinical data?

Journal: PloS one
Published Date:

Abstract

BACKGROUND: Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction.

Authors

  • Stephen F Weng
    NIHR School for Primary Care Research, University of Nottingham, Nottingham, United Kingdom.
  • Jenna Reps
    Advanced Data Analysis Centre, University of Nottingham, Nottingham, United Kingdom.
  • Joe Kai
    NIHR School for Primary Care Research, University of Nottingham, Nottingham, United Kingdom.
  • Jonathan M Garibaldi
    IMA group, School of Computer Science, University of Nottingham, Nottingham, NG81BB, United Kingdom.
  • Nadeem Qureshi
    NIHR School for Primary Care Research, University of Nottingham, Nottingham, United Kingdom.