Deep Learning With Electronic Health Records for Short-Term Fracture Risk Identification: Crystal Bone Algorithm Development and Validation.

Journal: Journal of medical Internet research
Published Date:

Abstract

BACKGROUND: Fractures as a result of osteoporosis and low bone mass are common and give rise to significant clinical, personal, and economic burden. Even after a fracture occurs, high fracture risk remains widely underdiagnosed and undertreated. Common fracture risk assessment tools utilize a subset of clinical risk factors for prediction, and often require manual data entry. Furthermore, these tools predict risk over the long term and do not explicitly provide short-term risk estimates necessary to identify patients likely to experience a fracture in the next 1-2 years.

Authors

  • Yasmeen Adar Almog
    Digital Health & Innovation, Amgen Inc, Thousand Oaks, CA, United States.
  • Angshu Rai
    Digital Health & Innovation, Amgen Inc, Thousand Oaks, CA, United States.
  • Patrick Zhang
    Digital Health & Innovation, Amgen Inc, Thousand Oaks, CA, United States.
  • Amanda Moulaison
    Digital Health & Innovation, Amgen Inc, Thousand Oaks, CA, United States.
  • Ross Powell
    Digital Health & Innovation, Amgen Inc, Thousand Oaks, CA, United States.
  • Anirban Mishra
    Digital Health & Innovation, Amgen Inc, Thousand Oaks, CA, United States.
  • Kerry Weinberg
    Digital Health & Innovation, Amgen Inc, Thousand Oaks, CA, United States.
  • Celeste Hamilton
    Global Medical Operations, Amgen Inc, Thousand Oaks, CA, United States.
  • Mary Oates
    US Medical, Amgen Inc, Thousand Oaks, CA, United States.
  • Eugene McCloskey
    Department of Oncology & Metabolism, The University of Sheffield, Sheffield, United Kingdom.
  • Steven R Cummings
    Department of Medicine, University of California San Francisco, San Francisco, CA, United States.