Can artificial intelligence outperform experts in assessing clinical skills? Evidence from a comparative experiment.

Front Med (Lausanne) · 2026 · PMC13283888 · PMID 42338953

Europe PMC DOI

hedged sentence

0.0750

closest p · 1.5× alpha

0.0750

boldest claim

The sentences

did not reach statistical significancep = 0.075so close (0.05 < p ≤ 0.1)

3.3.3 CPR In the CPR assessment, paired samples t -test revealed that CEA scores were on average 3.75 points higher than AIA scores, though this difference did not reach statistical significance ( t = 1.99, p = 0.075), with a moderate effect size (Cohen’s d = 0.60).

also in 111,027 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.