Accuracy of Large Language Models for Infective Endocarditis Prophylaxis in Dental Procedures
LLMs like GPT-4o show promise for retrieving AHA-IE guideline information, achieving up to 80% accuracy. However, complex medical questions may still pose a challenge. Pre-prompts offer a potential solution, and domain-specific training is essential for optimizing LLM performance in healthcare, especially with the emergence of models with increased token limits.
Authors
- Vorapat Trachoo (ORCID: https://orcid.org/0000-0002-1478-1122)
- Thantrira Porntaveetus (ORCID: https://orcid.org/0000-0003-0145-9801)
- Paak Rewthamrongsris (ORCID: https://orcid.org/0009-0004-3678-8554)
- Jirayu Burapacheep
Institutions
- Chulalongkorn University (TH)
- Stanford University (US)
Publication Details
- Journal
- International Dental Journal
- Published
- 2024-10-12
- DOI
- https://doi.org/10.1016/j.identj.2024.09.033
- Citations
- 29
- Primary Topic
- Infective Endocarditis Diagnosis and Management
- Type
- article
- Field-Weighted Citation Impact
- 11.21
Funders
- Chulalongkorn University
- National Research Council of Thailand
- Health Systems Research Institute
- Thailand Science Research and Innovation