Assessing ChatGPT responses to patient questions on epidural steroid injections: A comparative study of general vs specific queries
ChatGPT can provide clear and largely accurate answers to patient questions about ESIs, with general prompts often producing more complete responses. However, AI-generated content still has limitations, particularly in conveying empathy and avoiding tangential information. These findings highlight the need for thoughtful prompt design and further research into how AI can be integrated into clinical workflows while ensuring accuracy and patient safety.
Authors
- Weibin Shi (ORCID: https://orcid.org/0000-0002-8267-2796)
- Ankit Patel (ORCID: https://orcid.org/0000-0001-6177-4454)
- Timothy Olivier
- Thiru M. Annaswamy (ORCID: https://orcid.org/0000-0002-3969-9221)
- Nicole Hatchard
- Zilin Ma (ORCID: https://orcid.org/0000-0002-7259-9353)
- Mohammed Murtuza
Institutions
- Pain Management Institute (US)
- Southwestern Medical Center (US)
- Intelligent Systems Research (United States) (US)
- Southwestern Medical Center (US)
- Penn State Milton S. Hershey Medical Center (US)
- The University of Texas Southwestern Medical Center (US)
Publication Details
- Journal
- Interventional Pain Medicine
- Published
- 2025-05-26
- DOI
- https://doi.org/10.1016/j.inpm.2025.100592
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65