The Quality of AI-Generated CABG Counseling: A Blinded Comparison of Two Language Models.

J Clin Med · 2026 · PMC13207662 · PMID 42194857

Europe PMC DOI

hedged sentence

0.3400

closest p · 6.8× alpha

0.3400

boldest claim

The sentences

did not reach statistical significancep = 0.34not close (p > 0.1)

When the mean of the three categories was evaluated, it was found that DeepSeek demonstrated a slightly higher score than ChatGPT; however, this difference did not reach statistical significance (mean values of 4.32 ± 0.28 and 4.27 ± 0.30, respectively; p = 0.34).

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.