Fine-Tuned Bidirectional Encoder Representations From Transformers Versus ChatGPT for Text-Based Outpatient Department Recommendation: Comparative Study
Although ChatGPT did not surpass the fine-tuned KM-BERT model in recommending the correct medical specialties, it showcased notable advantages as a conversational artificial intelligence model. By providing detailed, contextually appropriate explanations, ChatGPT has the potential to significantly enhance patient comprehension of medical information, thereby improving the medical referral process.
Authors
- Hakje Yoo (ORCID: https://orcid.org/0000-0003-4341-5540)
- Hyung Joon Joo (ORCID: https://orcid.org/0000-0003-1846-8464)
- Sanghoun Song (ORCID: https://orcid.org/0000-0002-4234-232X)
- Young-Min Kim (ORCID: https://orcid.org/0000-0002-6914-901X)
- Jong-Ho Kim (ORCID: https://orcid.org/0000-0002-1309-0821)
- Eunbeen Jo (ORCID: https://orcid.org/0000-0002-2468-0114)
Institutions
- Korea University (KR)
- Samsung Medical Center (KR)
- Hanyang University (KR)
- Sungkyunkwan University (KR)
Publication Details
- Journal
- JMIR Formative Research
- Published
- 2024-10-18
- DOI
- https://doi.org/10.2196/47814
- Citations
- 3
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.36
Funders
- Iran Telecommunication Research Center
- Ministry of Science and ICT, South Korea
- Institute for Information and Communications Technology Promotion