Large Language Models Facilitate the Generation of Electronic Health Record Phenotyping Algorithms.

Chao YanHenry H OngMonika E GrabowskaMatthew S KrantzWu-Chen SuAlyson L DicksonJosh F PetersonQiPing Feng Dan M RodenC Michael SteinVern Eric KerchbergerBrad A MalinWei-Qi Wei

Published in: medRxiv : the preprint server for health sciences (2023)

Both ChatGPT versions 3.5 and 4 demonstrate the capability to enhance EHR phenotyping efficiency by drafting algorithms of reasonable quality. However, the optimal performance of these algorithms necessitates the involvement of domain experts.

Keyphrases

electronic health record
machine learning
deep learning
clinical decision support
high throughput
adverse drug
quality improvement