September 10, 2025Obesity SurgeryOpen Access

Comparative Analysis of Large Language Model and Physician-Generated Responses in Bariatric Patient Inquiries: Assessing the Accuracy and Patient Satisfaction

View Full Paper

Ask AI

Bookmark

LLMs provided higher patient satisfaction ratings compared to physician responses, indicating improved clarity and empathy.
Patients rated LLM responses significantly higher in completeness, averages being 4.5 over 3.4 for physicians.
The large language model generated responses significantly faster than human experts, averaging 2.7 seconds versus 87.2 seconds.
Lower education levels in patients were associated with a stronger preference for LLM-generated responses over physician responses.

Discussion

No takes yet. Share an insight, caveat, or question.

Comparative analysis assesses response accuracy and patient satisfaction in bariatric communications.

Vedder et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark