Using Language Models for Surgical Consensus: Key Findings

Large language models may enhance consensus-building on ventral rectopexy but vary significantly in reliability.

Openevidence had the highest content appropriateness score (3.5/5), outperforming Gemini (3.0/5) and ChatGPT (2.8/5; p < 0.001).
ChatGPT fabricated 53% of citations compared to Gemini’s 12% and Openevidence’s 0% (p < 0.001).

This suggests a need for careful selection of tools in clinical discussions.

Only 34% of Openevidence citations were lower than level I-III studies, making it a trusted source for guidelines.

Journal Article by Lee FG, Larson EL (…) Perry WRG et 12 al. in Dis Colon Rectum

read the whole article in Dis Colon Rectum

open it in PubMed

Summaries are written to help you decide what to read. They do not replace the full paper.

Free · 5 minutes a day

Get every new paper in Digital Surgery and Telemedicine.

Plus the Daily Selection: the five most relevant papers of the day, each cut to its key points.

More in Digital Surgery and Telemedicine

The latest stitches

J Am Coll Surg28 Oct 2026

AI Narration Is No Gallbladder Safety Check

In laparoscopic gallbladder surgery, targeted prompts made AI narration sound more like a surgeon’s but did not make safety checks reliable.

Digital Surgery and Telemedicine20 Oct 2026

AI Segments Abdominal Wall Layers During Trocar Entry

In a 10-procedure pilot, deep learning identified abdominal wall layers in optical trocar-entry video with promising accuracy—but this is not yet evidence of safer access.

Digital Surgery and Telemedicine14 Oct 2026

AI Enhancements in Robotic Surgical Training Still Lagging

Artificial intelligence is progressively being integrated into robotic surgical skills training, but its application remains in early development stages, limiting widespread uptake.

All papers in Digital Surgery and Telemedicine →