AI-Generated Versus Human Supervisor Feedback on Medical Students’ Clinical Clerkship Logs: Cross-Sectional Convergent Mixed Methods Study
Takeshi Kondo, Jeroen Donkers, Hiroshi Nishigori, Sanne Rovers, Sylvia Heeneman · 2026
Read AI-Generated Versus Human Supervisor Feedback on Medical Students’ Clinical Clerkship Logs: Cross-Sectional Convergent Mixed Methods Study by Takeshi Kondo, Jeroen Donkers, Hiroshi Nishigori, Sanne Rovers, Sylvia Heeneman (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/PMC13271589.txt.
Description
Takeshi Kondo is lead author of a 2026 mixed-methods study comparing AI-generated feedback with human supervisor feedback on medical students' clinical clerkship logs. Feedback is essential in workplace training, yet busy supervising doctors often lack time to write it well, and most earlier comparisons happened in classrooms, not real clinics.
The study used 161 weekly logs from 47 senior medical students across twelve departments at Nagoya University, Japan, with AI feedback produced by GPT-4o. Ten faculty doctors and ten students judged both feedback types blind, in random order, against a five-part rubric covering clear direction, accuracy, prioritisation, and supportive tone. AI feedback was far longer, averaging 382 words against 99 for supervisors.
Catalog record
| CREATOR | Takeshi Kondo, Jeroen Donkers, Hiroshi Nishigori, Sanne Rovers, Sylvia Heeneman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 96472 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |