Use of Generative AI to Identify Helmet Status Among Patients With Micromobility-Related Injuries From Unstructured Clinical Notes
This study's findings suggest that although there are efficiency gains for using the LLM to extract information from clinical notes, the inadequate reliability compared with a text string-search approach, hallucinations, and inconsistent performance significantly hinder the potential of the currently available LLM.
Authors
- Nicole G. Itzkowitz (ORCID: https://orcid.org/0000-0001-5076-3522)
- Katie Burford (ORCID: https://orcid.org/0000-0001-5500-9609)
- Julien O. Teitler
- Andrew Graham Rundle (ORCID: https://orcid.org/0000-0003-0211-7707)
- Ashley G. Ortega
Institutions
- Columbia University (US)
Publication Details
- Journal
- JAMA Network Open
- Published
- 2024-08-13
- DOI
- https://doi.org/10.1001/jamanetworkopen.2024.25981
- Citations
- 27
- Primary Topic
- Autopsy Techniques and Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 10.92
Funders
- Centers for Disease Control and Prevention