The effect of medical explanations from large language models on diagnostic accuracy in radiology.

NPJ Digit Med · 2026 · PMC13106719 · PMID 42026140

Europe PMC DOI

hedged sentence

0.0504

closest p · 1.0× alpha

0.0504

boldest claim

The sentences

only marginally significantP = 0.0504so close (0.05 < p ≤ 0.1)

Here, the diagnostic accuracy in the chain-of-thought group tends to be higher than in the standard output group but the improvement is only marginally significant ( P = 0.0504).

also in 5,085 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.