Predicting atrial fibrillation in primary care using machine learning.

Journal: PloS one
Published Date:

Abstract

BACKGROUND: Atrial fibrillation (AF) is the most common sustained heart arrhythmia. However, as many cases are asymptomatic, a large proportion of patients remain undiagnosed until serious complications arise. Efficient, cost-effective detection of the undiagnosed may be supported by risk-prediction models relating patient factors to AF risk. However, there exists a need for an implementable risk model that is contemporaneous and informed by routinely collected patient data, reflecting the real-world pathology of AF.

Authors

  • Nathan R Hill
    Bristol-Myers Squibb Pharmaceuticals Ltd, Uxbridge Business Park, Sanderson Road, Uxbridge, Middlesex UB8 1DH, UK.
  • Daniel Ayoubkhani
    Health Economics and Outcomes Research Ltd, Cardiff, United Kingdom.
  • Phil McEwan
    Health Economics and Outcomes Research Ltd, Cardiff, United Kingdom.
  • Daniel M Sugrue
    Health Economics and Outcomes Research Ltd, Cardiff, United Kingdom.
  • Usman Farooqui
    Bristol-Myers Squibb Pharmaceuticals Ltd, Uxbridge Business Park, Sanderson Road, Uxbridge, Middlesex UB8 1DH, UK.
  • Steven Lister
    Bristol-Myers Squibb Pharmaceutical Ltd, Uxbridge, United Kingdom.
  • Matthew Lumley
    Pfizer Ltd, Surrey, United Kingdom.
  • Ameet Bakhai
    Department of Cardiology, Royal Free Hospital, London, United Kingdom.
  • Alexander T Cohen
    Guy's and St Thomas' Hospitals, London, UK.
  • Mark O'Neill
    Division of Cardiovascular Medicine, Guys and St Thomas' NHS Foundation Trust, King's College London, London, United Kingdom.
  • David Clifton
    Computational Health Informatics Lab, Oxford Institute of Biomedical Engineering, University of Oxford, Oxford, United Kingdom.
  • Jason Gordon
    Health Economics and Outcomes Research Ltd, Cardiff, United Kingdom.