Application of large language models in clinical record correction: a comprehensive study on various retraining methods
This study underscores the potential of LLMs in medical education, providing an innovative, effective approach to CR correction. Low-rank adaptation emerged as the most effective technique, enabling open-source models to perform on par with proprietary models. Future research should focus on overcoming current limitations to further improve model performance.
Authors
- Álvaro J. García‐Tejedor (ORCID: https://orcid.org/0000-0001-6458-2618)
- Alberto Nogales (ORCID: https://orcid.org/0000-0003-4951-8102)
- Sophia Denizon-Arranz
- Emilio Cervera Barba (ORCID: https://orcid.org/0000-0001-7117-8314)
- Ana M. Maitín (ORCID: https://orcid.org/0000-0001-6396-8068)
- Enrique Aranguren
- Alonso Mateos Rodríguez (ORCID: https://orcid.org/0000-0001-8281-9308)
- Sergio Fernández-Rincón
Institutions
- Universidad Francisco de Vitoria (ES)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2024-12-20
- DOI
- https://doi.org/10.1093/jamia/ocae302
- Citations
- 5
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.60
Funders
- Universidad Francisco de Vitoria