Achieving Expert-Level Clinical Infection Detection with LLMs from Clinical Documents: Validation in Complex Patient Cases with Cirrhosis
INFEHR offers a scalable, reproducible, and accurate method for infection phenotyping in cirrhosis. By overcoming limitations of traditional coding and manual review, it supports high-throughput infection surveillance, improves cohort construction for clinical research, and enables future integration into real-time decision-support tools in hepatology.
Authors
- Gabriel Wardi (ORCID: https://orcid.org/0000-0002-4845-0217)
- Eileen Kim (ORCID: https://orcid.org/0000-0002-6782-1810)
- Yufei Yu (ORCID: https://orcid.org/0000-0002-1149-542X)
- Shamim Nemati
- Joseph C Ahn
- Atul Malhotra
- James Ford
- Rohit Loomba
- Avi Patel
Institutions
- UC San Diego Health System (US)
- University of California San Diego (US)
- Mayo Clinic in Arizona (US)
Publication Details
- Journal
- medRxiv
- Published
- 2026-01-15
- DOI
- https://doi.org/10.64898/2026.01.13.26344046
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- American Association for the Study of Liver Diseases
- National Institutes of Health
- National Institute of General Medical Sciences
- U.S. National Library of Medicine