November 16, 2026 · Urogynecology (Philadelphia, Pa.) · DOI: 10.1097/SPV.0000000000001954

Utility of Artificial Intelligence in Diagnosing Image-Based Vaginal Pathology.

Listen to this summary

This study asked how accurately publicly available AI models (ChatGPT, Gemini, Claude, and Grok) can identify vaginal pathology from 25 clinical images compared with two board-certified urogynecologists. The experts were more accurate (84% top-3, 66% top-1) than the AI models (mean 51.8% top-3, 32.5% top-1), though ChatGPT and Gemini performed best among the AI tools and approached expert performance in identifying malignancy. The AI models also recommended urgent evaluation far more often than experts (77% vs. 22%), suggesting that patient-facing AI may have a limited, but evolving, role in image-based triage that still requires clinical oversight.

Anjali Shekar, Dara F Shalom, Meghana Reddy, Iyla Bagheri, Gregory T Bales, Sarah F Faris, Anne P Cameron, Doreen E Chung

This is one of 33,000+ journals available on OSLR. Try it free for 14 days.

Free 14-day trial. 33,000+ journals. Cancel anytime.

14-day free trial. No commitment.

“

"Oslr has become part of my weekly routine on my day off. The clinical relevance of the summaries is outstanding — I'd rate it 9/10. Being able to consume research hands-free is a huge advantage for busy physicians."

Dr. Jennifer Thompson

Dr. Jennifer Thompson

Portland, OR

Stay current without falling behind

33,000+ journals. 3-minute audio summaries. Free for 14 days.

Download on the App StoreGet it on Google Play