Can artificial intelligence outperform experts in assessing clinical skills? Evidence from a comparative experiment
Yan Wang, Ning Wang · 2026
Read Can artificial intelligence outperform experts in assessing clinical skills? Evidence from a comparative experiment by Yan Wang, Ning Wang (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/pmc-13283888.txt.
Description
Yan Wang and Ning Wang ran a head-to-head test in 2026 of artificial intelligence versus human experts for grading medical students' clinical skills. Both judged the same performances at two skills competitions in late 2024 and spring 2025. The tasks covered patient interviewing, placing a breathing tube, and chest resuscitation. Agreement was measured with correlation and consistency statistics.
The judges agreed excellently on the breathing tube task, moderately on interviewing, and poorly on resuscitation. The authors read the pattern as a split in strengths. Software handles structured, measurable content well. It struggles where judgement and context dominate. Experts bring whole-picture judgement, yet risk bias and lapses of attention. They recommend pairing the two, with heavy calibration before any full rollout.
Catalog record
| CREATOR | Yan Wang, Ning Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |