Evaluation of Large Language Models in Tailoring Educational Content for Cancer Survivors and Their Caregivers: Quality Analysis
All 3 LLMs demonstrated high potential for delivering multilingual, concise, and low health literacy educational content for cancer survivors and caregivers who face limited literacy or language barriers. GPT-4 family models were notably more robust. While further refinement is required to ensure simpler reading levels and fully comprehensive information, these findings highlight LLMs as an emerging tool for bridging gaps in cancer education and advancing health equity. Future research should integrate expert feedback, additional prompt engineering strategies, and specialized training data to optimize content accuracy and accessibility.
Authors
- La-Urshalar Brock (ORCID: https://orcid.org/0000-0002-7088-9373)
- Yu‐Fen Lin (ORCID: https://orcid.org/0000-0002-9182-2928)
- Canhua Xiao (ORCID: https://orcid.org/0000-0003-1391-5325)
- Darren Liu (ORCID: https://orcid.org/0009-0004-5019-4402)
- Zahra Amirkhanzadeh Barandouzi (ORCID: https://orcid.org/0000-0002-8537-4751)
- Caitlin Webster (ORCID: https://orcid.org/0000-0002-6464-6308)
- Jinbing Bai (ORCID: https://orcid.org/0000-0001-6726-5714)
- Xiao Hu (ORCID: https://orcid.org/0000-0001-9478-5571)
- Delgersuren Bold (ORCID: https://orcid.org/0000-0002-2983-571X)
- Lindsay Lee (ORCID: https://orcid.org/0009-0006-5918-853X)
- Stephanie Lee (ORCID: https://orcid.org/0000-0002-6553-3161)
Institutions
- Emory University (US)
- University of Florida (US)
Publication Details
- Journal
- JMIR Cancer
- Published
- 2025-02-28
- DOI
- https://doi.org/10.2196/67914
- Citations
- 3
- Primary Topic
- Palliative Care and End-of-Life Issues
- Type
- article
- Field-Weighted Citation Impact
- 5.64