Use of Large Language Models to Classify Epidemiological Characteristics in Synthetic and Real-World Social Media Posts About Conjunctivitis Outbreaks: Infodemiology Study
This investigation into the potential of LLMs for public health infoveillance suggests effectiveness in classifying key epidemiological characteristics from social media content about conjunctivitis outbreaks. Future studies should further explore LLMs' potential to support public health monitoring through the automated assessment and classification of potential infectious eye disease or other outbreaks. Their optimal role may be to act as a first line of documentation, alerting public health organizations for the follow-up of LLM-detected and -classified small, early outbreaks, with a focus on the most severe ones.
Authors
- Thomas Bukowski (ORCID: https://orcid.org/0000-0001-5720-8564)
- Cherie Fathy (ORCID: https://orcid.org/0000-0002-0529-7830)
- Thuy Doan (ORCID: https://orcid.org/0000-0003-2733-8370)
- Gerami D. Seitzman (ORCID: https://orcid.org/0000-0003-1791-5509)
- Michael Deiner (ORCID: https://orcid.org/0000-0002-4977-6147)
- Travis C. Porco (ORCID: https://orcid.org/0000-0001-8813-3171)
- Thomas M. Lietman (ORCID: https://orcid.org/0000-0001-8216-0240)
- Stephen D. McLeod (ORCID: https://orcid.org/0000-0003-4825-1522)
- Natalie A Deiner (ORCID: https://orcid.org/0009-0008-5477-0429)
- Vagelis Hristidis
- Russell Y Deiner
Institutions
- University of California, Riverside (US)
- Center for Biologics Evaluation and Research (US)
- American Academy of Ophthalmology (US)
- University of California, Santa Barbara (US)
- University of California, San Francisco (US)
- San Francisco University High School (US)
- San Francisco Foundation (US)
- Abraham Lincoln University (US)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-05-06
- DOI
- https://doi.org/10.2196/65226
- Citations
- 4
- Primary Topic
- Data-Driven Disease Surveillance
- Type
- article
- Field-Weighted Citation Impact
- 5.42