Assessing Artificial Intelligence–Generated Responses to Urology Patient In-Basket Messages
ChatGPT generated acceptable responses to nearly 50% of patient messages with better performance for easy questions compared to difficult questions. Use of ChatGPT to help respond to patient messages can help to decrease the time burden for the care team and improve wellness. Artificial intelligence performance will likely continue to improve with advances in generative artificial intelligence technology.
Authors
- Federico Belladelli (ORCID: https://orcid.org/0000-0002-2165-659X)
- Michael A. Scott (ORCID: https://orcid.org/0009-0007-0213-0588)
- Michael L. Eisenberg (ORCID: https://orcid.org/0000-0001-5482-0141)
- Albert Ha
- Frank Glover (ORCID: https://orcid.org/0000-0002-2940-8689)
- Chiyuan Amy Zhang
- Nicolas Seranio (ORCID: https://orcid.org/0000-0001-8951-9842)
- Wade Muncey (ORCID: https://orcid.org/0000-0001-8323-7094)
- Shufeng Li (ORCID: https://orcid.org/0000-0001-6031-0893)
- Francesco Del Giudice (ORCID: https://orcid.org/0000-0003-3865-5988)
Institutions
- Emory University (US)
- Policlinico Umberto I (IT)
- IRCCS Ospedale San Raffaele (IT)
- Idaho Urologic Institute (US)
- Stanford University (US)
Publication Details
- Journal
- Urology Practice
- Published
- 2024-08-20
- DOI
- https://doi.org/10.1097/upj.0000000000000637
- Citations
- 20
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.41