Syndromic Analysis of Sepsis Cohorts Using Large Language Models
This cohort study found that an LLM accurately extracted presenting signs and symptoms from admission notes that clustered into syndromes differentially correlated with infection sources, multidrug-resistant infections, and mortality. Further research is warranted to evaluate the value of large-scale sign-and-symptom data in models of antibiotic choice, effectiveness, and outcomes in patients with possible sepsis.
Authors
- Sanjat Kanjilal (ORCID: https://orcid.org/0000-0002-1221-5725)
- Alexander Hoffner-Heinike (ORCID: https://orcid.org/0000-0003-3434-7814)
- Michael Klompas (ORCID: https://orcid.org/0000-0001-8641-4498)
- Theodore R. Pak (ORCID: https://orcid.org/0000-0002-1676-2523)
- Chanu Rhee (ORCID: https://orcid.org/0000-0002-9537-4245)
- Caroline McKenna (ORCID: https://orcid.org/0009-0000-1093-3080)
Institutions
- Brigham and Women's Hospital (US)
- Harvard University (US)
- Massachusetts General Hospital (US)
- Harvard Pilgrim Health Care (US)
Publication Details
- Journal
- JAMA Network Open
- Published
- 2025-10-24
- DOI
- https://doi.org/10.1001/jamanetworkopen.2025.39267
- Citations
- 3
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 4.06
Funders
- Agency for Healthcare Research and Quality
- National Institute of Allergy and Infectious Diseases