Prompt Engineering and Follow-Up Questioning Improves the Readability of Spine Surgery Questions in Large Language Models
Prompt engineering and follow-up questioning significantly enhanced the readability of LLM-generated responses to spine surgery questions at a level appropriate for patients. Further investigation is needed to assess whether these responses are more readable in real-world clinical settings instead of relying on objective readability scoring methods.
Authors
- Nikhil Dholaria (ORCID: https://orcid.org/0000-0002-0873-5525)
- Qazi Zeeshan (ORCID: https://orcid.org/0000-0002-4785-4682)
- Gregory Burnet
- Rida Mitha (ORCID: https://orcid.org/0009-0002-4074-3952)
- Nitin Agarwal (ORCID: https://orcid.org/0000-0003-0256-3897)
- David Kojo Hamilton (ORCID: https://orcid.org/0009-0009-7713-7252)
- Shaunak Patil
- Aditi Choudhary
- Sohail Daulat (ORCID: https://orcid.org/0009-0003-4751-6282)
- Bhavesh Manne
Institutions
- University of Pittsburgh (US)
- University of Phoenix (US)
- VA Pittsburgh Healthcare System (US)
- University of Pittsburgh Medical Center (US)
- Neurological Surgery (US)
Publication Details
- Journal
- World Neurosurgery
- Published
- 2025-08-30
- DOI
- https://doi.org/10.1016/j.wneu.2025.124423
- Citations
- 3
- Primary Topic
- Interpreting and Communication in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 8.45