Machine learning based on body composition radiomics for predicting early recurrence in colorectal cancer: a multicenter study.

Front Nutr · 2026 · PMC13275260 · PMID 42325524

Europe PMC DOI

hedged sentence

0.0570

closest p · 1.1× alpha

0.0570

boldest claim

The sentences

borderline significantp = 0.057so close (0.05 < p ≤ 0.1)

Although advanced T stage (T3 – T4) was only borderline significant (OR = 2.558, 95% CI: 1.061–7.627, p = 0.057), it was retained in the clinical model due to its established prognostic relevance in CRC. 3.2 Radiomics feature engineering and signature construction A total of 1,896 high-dimensional 2D radiomics features were extracted from SM, SAT, IMAT, and VAT at the L3 level.

also in 11,409 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.