User-centred design for machine learning in health care: a case study from care management.

Journal: BMJ health & care informatics
PMID:

Abstract

OBJECTIVES: Few machine learning (ML) models are successfully deployed in clinical practice. One of the common pitfalls across the field is inappropriate problem formulation: designing ML to fit the data rather than to address a real-world clinical pain point.

Authors

  • Martin G Seneviratne
    Department of Biomedical Informatics, Stanford School of Medicine, CA.
  • Ron C Li
    Department of Medicine, Stanford University, Stanford, California, USA.
  • Meredith Schreier
    Research, Google Inc, Mountain View, California, USA.
  • Daniel Lopez-Martinez
  • Birju S Patel
    Research, Google Inc, Mountain View, California, USA.
  • Alex Yakubovich
    Research, Google Inc, Mountain View, California, USA.
  • Jonas B Kemp
    Research, Google Inc, Mountain View, California, USA.
  • Eric Loreaux
    Google Health, London, United Kingdom.
  • Paul Gamble
    Google Health, Google, Palo Alto, CA, USA.
  • Kristel El-Khoury
    Research, Google Inc, Mountain View, California, USA.
  • Laura Vardoulakis
    Google LLC, Mountain View, California.
  • Doris Wong
    Research, Google Inc, Mountain View, California, USA.
  • Janjri Desai
    Division of Pharmacy, Stanford Medicine, Stanford, California, USA.
  • Jonathan H Chen
    Stanford Center for Biomedical Informatics Research, Stanford, CA.
  • Keith E Morse
    Division of Pediatric Hospital Medicine, Department of Pediatrics, Stanford University School of Medicine, Stanford, California, USA.
  • N Lance Downing
    From the Department of Computer Science (S.Y., L.F.-F.), the Center for Biomedical Informatics Research (N.L.D.), the Department of Medicine (A.M.), and the Clinical Excellence Research Center (S.Y., N.L.D., L.F.-F., A.M.), Stanford University, Stanford, CA.
  • Lutz T Finger
    Research, Google Inc, Mountain View, California, USA.
  • Ming-Jun Chen
    Research, Google Inc, Mountain View, California, USA.
  • Nigam Shah
    Center for Biomedical Informatics Research, Stanford University School of Medicine, Stanford, CA, United States.