Diagnostic Performance of Publicly Available Large Language Models in Corneal Diseases: A Comparison with Human Specialists.

Diagnostics (Basel) · 2025 · PMC12110359 · PMID 40428214

Europe PMC DOI

hedged sentence

0.0630

closest p · 1.3× alpha

0.0630

boldest claim

The sentences

marginally significantp = 0.063so close (0.05 < p ≤ 0.1)

Claude 3.5 Sonnet showed mixed results, with a marginally significant difference from human consensus ( p = 0.063) and a significant difference from one expert (H1: p = 0.031).

also in 26,082 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.