Affordable Access

deepdyve-link
Publisher Website

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

Authors
  • Almog, Yasmeen Adar1
  • Rai, Angshu1
  • Zhang, Patrick1
  • Moulaison, Amanda1
  • Powell, Ross1
  • Mishra, Anirban1
  • Weinberg, Kerry1
  • Hamilton, Celeste2
  • Oates, Mary3
  • McCloskey, Eugene4
  • Cummings, Steven R5
  • 1 Digital Health & Innovation, Amgen Inc, Thousand Oaks, CA, United States. , (United States)
  • 2 Global Medical Operations, Amgen Inc, Thousand Oaks, CA, United States. , (United States)
  • 3 US Medical, Amgen Inc, Thousand Oaks, CA, United States. , (United States)
  • 4 Department of Oncology & Metabolism, The University of Sheffield, Sheffield, United Kingdom. , (United Kingdom)
  • 5 Department of Medicine, University of California San Francisco, San Francisco, CA, United States. , (United States)
Type
Published Article
Journal
Journal of Medical Internet Research
Publisher
JMIR Publications Inc.
Publication Date
Oct 16, 2020
Volume
22
Issue
10
Identifiers
DOI: 10.2196/22550
PMID: 32956069
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

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. The goal of this study was to develop and evaluate an algorithm for the identification of patients at risk of fracture in a subsequent 1- to 2-year period. In order to address the aforementioned limitations of current prediction tools, this approach focused on a short-term timeframe, automated data entry, and the use of longitudinal data to inform the predictions. Using retrospective electronic health record data from over 1,000,000 patients, we developed Crystal Bone, an algorithm that applies machine learning techniques from natural language processing to the temporal nature of patient histories to generate short-term fracture risk predictions. Similar to how language models predict the next word in a given sentence or the topic of a document, Crystal Bone predicts whether a patient's future trajectory might contain a fracture event, or whether the signature of the patient's journey is similar to that of a typical future fracture patient. A holdout set with 192,590 patients was used to validate accuracy. Experimental baseline models and human-level performance were used for comparison. The model accurately predicted 1- to 2-year fracture risk for patients aged over 50 years (area under the receiver operating characteristics curve [AUROC] 0.81). These algorithms outperformed the experimental baselines (AUROC 0.67) and showed meaningful improvements when compared to retrospective approximation of human-level performance by correctly identifying 9649 of 13,765 (70%) at-risk patients who did not receive any preventative bone-health-related medical interventions from their physicians. These findings indicate that it is possible to use a patient's unique medical history as it changes over time to predict the risk of short-term fracture. Validating and applying such a tool within the health care system could enable automated and widespread prediction of this risk and may help with identification of patients at very high risk of fracture. ©Yasmeen Adar Almog, Angshu Rai, Patrick Zhang, Amanda Moulaison, Ross Powell, Anirban Mishra, Kerry Weinberg, Celeste Hamilton, Mary Oates, Eugene McCloskey, Steven R Cummings. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 16.10.2020.

Report this publication

Statistics

Seen <100 times