Enhancing Precision in Detecting Severe Immune-Related Adverse Events: Comparative Analysis of Large Language Models and International Classification of Disease Codes in Patient Records.
Virginia H SunJulius C HeemelaarIbrahim HadzicVineet K RaghuChia-Yun WuLeyre ZubiriAzin GhamariNicole R LeBoeufOsama Abu-ShawerKenneth L KehlShilpa GroverPrabhsimranjot SinghGiselle Alexandra Suero-AbreuJessica WuAyo S FaladeKelley GrealishMolly F ThomasNora HathawayBenjamin D MedoffHannah K GilmanAlexandra-Chloé VillaniJor Sam HoMeghan J MooradianMeghan E SiseDaniel A ZlotoffSteven M BlumMichael L DouganRyan J SullivanTomas G NeilanKerry Lynn ReynoldsPublished in: Journal of clinical oncology : official journal of the American Society of Clinical Oncology (2024)
LLMs are a useful tool for the detection of irAEs, outperforming ICD codes in sensitivity and adjudication in efficiency.