Login / Signup

A GPT-based EHR modeling system for unsupervised novel disease detection.

Boran HaoYang HuWilliam G AdamsSabrina A AssoumouHeather E HsuNahid BhadeliaIoannis Ch Paschalidis
Published in: Journal of biomedical informatics (2024)
This study demonstrates that an emerging outbreak can be accurately detected within a hospital, by using a GPT to model patient EHR time sequences and labeling them as anomalous when actual outcomes are not supported by the model. Such a GPT is also a comprehensive model with the functionality of generating future patient clinical variables, which can potentially assist clinicians in developing personalized treatment plans.
Keyphrases
  • case report
  • machine learning
  • electronic health record
  • healthcare
  • type diabetes
  • palliative care
  • insulin resistance
  • skeletal muscle
  • metabolic syndrome
  • health insurance
  • label free