Mitigating Clinical Confounding in AI Models: A Comparative Analysis of Associative and Causal-Fused AI for ICU Readmissions.

Healthcare (Basel) · 2026 · PMC13409962 · PMID 42512583

Europe PMC DOI

hedged sentence

0.0006

closest p · 0.0× alpha

0.0006

boldest claim

The sentences

highly significantp = 6.4778 × 10 −4actually significant

Additionally, Body Mass Index (BMI) categories demonstrated a highly significant association with readmission status (x 2 = 21.513, p = 6.4778 × 10 −4 ), characterized by a non-linear relationship where underweight patients exhibited the highest readmission rate (15.79%) and obese patients the lowest (11.49%). 4.2.

also in 132,142 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.