ChatGPT and low back pain - Evaluating AI-driven patient education in the context of interventional pain medicine
This analysis complicates the assumption that "simpler is better" in prompting LLMs for clinical education. Whereas earlier work in structured conditions suggested that plain-language prompts improved accuracy, our findings indicate that a moderate reading level, not maximal simplicity, yields the most reliable outputs in complex domains like pain. This study further supports that AI LLMs can be integrated into a clinical workflow, possibly through electronic health record (EHR) software.
Authors
- N. Elane Wilcox
- Narayana Varhabhatla
- Nisarg Gandhi
- Preeti Kansal (ORCID: https://orcid.org/0009-0009-6308-3759)
- Robert Chow
- Charles Amoatey Odonkor (ORCID: https://orcid.org/0000-0002-8280-4015)
- Gökhan Tür
- Rohan J. Shah (ORCID: https://orcid.org/0000-0002-6930-0605)
- George Chong
- Ahmed Basharat
- Siddarth Tripati
- Sreekrishna Pokuri
Institutions
- Ronald Reagan UCLA Medical Center (US)
- Yale Cancer Center (US)
- Yale University (US)
- Pain Management Institute (US)
- Aetion (United States) (US)
- SC Solutions (United States) (US)
- Southington Public School (US)
- Memorial (RU)
- Goodwin College (US)
- Columbia University (US)
- University of Colorado Denver (US)
Publication Details
- Journal
- Interventional Pain Medicine
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1016/j.inpm.2025.100636
- Primary Topic
- Musculoskeletal pain and rehabilitation
- Type
- article
- Field-Weighted Citation Impact
- 0.00