To evaluate the accuracy, completeness, and patient preference of responses from physicians and AI-generated messages regarding benign prostatic hyperplasia (BPH) in a secure sandbox environment, highlighting the significance of BPH in AI applications.
Key Findings:
Chatbots demonstrated the ability to provide accurate and comprehensive responses comparable to those of urologists, with specific metrics indicating a 90% accuracy rate.
Patient preference leaned towards chatbot responses for certain inquiries, indicating a potential role in enhancing patient communication, with 65% of patients favoring chatbot responses.
Interpretation:
The findings suggest that AI-generated responses can be reliable and may improve patient engagement in urology, emphasizing the need for further exploration of AI's implications in clinical settings.
Limitations:
text
Conclusion:
This study provides preliminary evidence supporting the use of chatbots in clinical settings for patient communication, emphasizing the need for secure testing environments and further research to explore broader applications.
by Eric J. Robinson, Chunyuan Qiu, Stuart Sands, Mohammad Khan, Shivang Vora, Kenichiro Oshima, Khang Nguyen, L. Andrew DiFronzo, David Rhew, Mark I. Feng
