Comparing clinical decision-making between colposcopists and large language models in cervical dysplasia management: a pilot prospective multicenter study
Jan Lennart Stalp, Juliane Alexandra Schneider, Lena Steinkasserer, Jens Hachenberg, Matthias Jentschke, Peter Hillemanns, Dominik Wolff, Agnieszka Denecke · 2026
Read Comparing clinical decision-making between colposcopists and large language models in cervical dysplasia management: a pilot prospective multicenter study by Jan Lennart Stalp, Juliane Alexandra Schneider, Lena Steinkasserer, Jens Hachenberg, Matthias Jentschke, Peter Hillemanns, Dominik Wolff, Agnieszka Denecke (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13279379.txt.
Description
Jan Lennart Stalp and colleagues report a 2026 pilot study that pits doctors against chatbots in cervix care choices. Cervical dysplasia means odd cell growth on the cervix that can precede cancer. Board certified colposcopists, doctors who exam the cervix with a scope, made the human group. Two large language models, ChatGPT-4o and ChatGPT-5, made the machine group.
Twenty three real, name free cases with choice questions were judged against a gold standard set by two guide authors. Ten doctors and both models gave like overall match rates, near seventy percent. One model beat doctors on pre cancer cases, while doctors led on hard cases with unclear tissue results. The pilot hints at help, not replacement, in cervix care.
Catalog record
| CREATOR | Jan Lennart Stalp, Juliane Alexandra Schneider, Lena Steinkasserer, Jens Hachenberg, Matthias Jentschke, Peter Hillemanns, Dominik Wolff, Agnieszka Denecke |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30555 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |