Can Machine Learning Predict Metastatic Sites in Pancreatic Ductal Adenocarcinoma? A Radiomic Analysis.

J Imaging Inform Med · 2026 · PMC13103170 · PMID 40760262

Europe PMC DOI

hedged sentences

0.0566

closest p · 1.1× alpha

0.0570

boldest claim

The sentences

a trend toward significancep = 0.0566so close (0.05 < p ≤ 0.1)

LargeDependenceEmphasis showed a trend toward significance ( p = 0.0566) as a discriminative feature.

also in 3,729 other papers

trending toward significancep = 0.057so close (0.05 < p ≤ 0.1)

Bootstrap resampling (1000 iterations) confirmed LargeDependenceEmphasis as the most stable discriminator (selection frequency 92.4%), maintaining consistent predictive value (coefficient: −0.404; standardized odds ratio: 0.667; 95% CI: 0.44, 0.89; trending toward significance with p = 0.057) across validation folds (Table 6 ).

also in 580 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.