Detecting emergencies in patient portal messages using large language models and knowledge graph-based retrieval-augmented generation
LLMs can effectively assist in triaging emergency patient messages after integrating with a knowledge graph about a nurse triage book. Future research should focus on expanding the knowledge graph and deploying the system to evaluate its impact on patient outcomes.
Authors
- Adam T. Wright (ORCID: https://orcid.org/0000-0001-6844-145X)
- Bryan D. Steitz (ORCID: https://orcid.org/0000-0003-2066-8692)
- Aileen P. Wright (ORCID: https://orcid.org/0000-0002-7550-4284)
- Sean S Huang
- Allison B. McCoy (ORCID: https://orcid.org/0000-0003-2292-9147)
- Siru Liu (ORCID: https://orcid.org/0000-0002-5003-5354)
Institutions
- Vanderbilt University (US)
- Vanderbilt University Medical Center (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-04-12
- DOI
- https://doi.org/10.1093/jamia/ocaf059
- Citations
- 16
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 39.70
Funders
- National Institutes of Health