Large Language Model Symptom Identification From Clinical Text: Multicenter Study

• Published in: Journal of medical Internet research Vol. 27; p. e72984
• Main Authors: McMurry, Andrew J, Phelan, Dylan, Dixon, Brian E, Geva, Alon, Gottlieb, Daniel, Jones, James R, Terry, Michael, Taylor, David E, Callaway, Hannah, Manoharan, Sneha, Miller, Timothy, Olson, Karen L, Mandl, Kenneth D
• Format: Journal Article
• Language: English
• Published: Canada JMIR Publications 31.07.2025
• Subjects: AI Language Models in Health Care; Clinical Informatics; Clinical Information and Decision Making; Electronic Health Records; Generative Language Models Including ChatGPT; Humans; Infectious Diseases (non-STD/STI); Information Retrieval; Language; Large Language Models; Natural Language Processing; Ontologies, Classifications, and Coding; Original Paper; emergency medical services; clinical text mining; infectious disease surveillance; epidemiologic methods; medical informatics; natural language processing; symptom recognition; large language models; electronic health records; artificial intelligence

Recognizing patient symptoms is fundamental to medicine, research, and public health. However, symptoms are often underreported in coded formats even though they are routinely documented in physician notes. Large language models (LLMs), noted for their generalizability, could help bridge this gap by...