Large language models outperform traditional natural language processing methods in extracting patient-reported outcomes in IBD.

Perseus V PatelConner DavisAmariel RalbovskyDaniel TinocoChristopher Y K WilliamsShadera SlatterBehzad NaderalvojoudMichael J RosenTina Hernandez-BoussardVivek Ashok Rudrapatna

Published in: medRxiv : the preprint server for health sciences (2024)

LLMs are accurate and generalizable methods for extracting PROs. They maintain excellent accuracy across institutions, despite heterogeneity in note templates and authors. Widespread adoption of such tools has the potential to enhance IBD research and patient care.

Keyphrases

patient reported outcomes
autism spectrum disorder
ulcerative colitis
single cell
high resolution
electronic health record
mass spectrometry
climate change