Large Language Models vs. Professional Resources for Post-Treatment Quality-of-Life Questions in Head and Neck Cancer: A Cross-Sectional Comparison
In our study, we found that LLMs (ChatGPT, Gemini, Claude) can produce patient information that is comparable to professional resources in terms of quality, understandability, actionability, and empathy. However, readability remains a key limitation, as LLM-generated responses often require simplification to align with recommended health-literacy standards.
Authors
- A. Yousif (ORCID: https://orcid.org/0009-0007-9408-0556)
- Mohammed Elnibras (ORCID: https://orcid.org/0000-0002-0142-7917)
- Muhammad Basharat (ORCID: https://orcid.org/0000-0003-1412-1383)
- Manish Mair (ORCID: https://orcid.org/0000-0003-3957-2738)
- Suzan Abdelrahman Hamad
- Mustafa Qais Muhsin Al-Khafaji (ORCID: https://orcid.org/0009-0001-5629-4939)
- Ali Alabdalhussein (ORCID: https://orcid.org/0009-0001-0273-410X)
- Shazaan Nadeem
- Sahar Alghnaimawi (ORCID: https://orcid.org/0009-0003-0303-5858)
- Juman Baban
- Hasan Aldallal
- Sarah Mozan
- Ibrahim Saleem (ORCID: https://orcid.org/0009-0005-8374-9651)
Institutions
- Chelsea and Westminster Hospital NHS Foundation Trust (GB)
- Salford Royal NHS Foundation Trust (GB)
- James Cook University Hospital (GB)
- Dudley Group NHS Foundation Trust (GB)
- Croydon University Hospital (GB)
- University Hospitals of Leicester NHS Trust (GB)
- Northern Health and Social Care Trust (GB)
- University Hospitals of Derby and Burton NHS Foundation Trust (GB)
- Independent Age (GB)
Publication Details
- Journal
- Current Oncology
- Published
- 2025-11-28
- DOI
- https://doi.org/10.3390/curroncol32120668
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00