Quality assessment of large language model–generated prior authorization letters in nephrology
ChatGPT-5 can generate clinically coherent PA drafts for nephrology medications, but limitations in coding precision and citation reliability persist. With appropriate oversight, AI-assisted documentation may reduce administrative burden while maintaining safety and accuracy.
Authors
- Kitinan Phichedwanichskul
- Noppawit Aiumtrakul (ORCID: https://orcid.org/0000-0003-0479-7785)
- Chutawat Kookanok
- Methavee Poochanasri
- Wisit Cheungpasitporn
- Charat Thongprayoon
Institutions
- Interfaith Medical Center (US)
- WinnMed (US)
- Phramongkutklao Hospital (TH)
- Bhumibol Adulyadej Hospital (TH)
Publication Details
- Journal
- Frontiers in Digital Health
- Published
- 2026-03-03
- DOI
- https://doi.org/10.3389/fdgth.2026.1767648
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00