Large language models as information providers for appropriate antimicrobial use: computational text analysis and expert-rated comparison of ChatGPT, Claude and Gemini.

BMJ Health Care Inform · 2025 · PMC12530423 · PMID 41093628

Europe PMC DOI

hedged sentence

0.0620

closest p · 1.2× alpha

0.0620

boldest claim

The sentences

slightly significantp=0.062so close (0.05 < p ≤ 0.1)

Only a slightly significant result (p=0.062) is observed between GME and G3E-G4E ( table 2 ).

also in 1,762 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.