Physician vs. AI-generated messages in urology: evaluation of accuracy, completeness, and preference by patients and physicians

1

The study evaluates the performance of chatbots and urologists in answering common patient questions about Benign Prostatic Hyperplasia (BPH).
2

A sandbox environment was established to securely test chatbot responses while preventing exposure of personal health information (PHI).
3

ChatGPT and another chatbot were assessed for accuracy, completeness, and tone against answers from four board-certified urologists.
4

The study utilized real-world patient questions compiled by a nursing messaging management team to emulate clinical communication scenarios.
5

Findings suggest chatbots can provide reliable, empathetic responses in a clinical setting, enhancing physician-patient communication.

World Journal Of Urology

by Eric J. Robinson, Chunyuan Qiu, Stuart Sands, Mohammad Khan, Shivang Vora, Kenichiro Oshima, Khang Nguyen, L. Andrew DiFronzo, David Rhew, Mark I. Feng
December 27, 2024

1