Table 6 Per-class performance metrics under type-blind evaluation settings.

From: Interpretable graph Kolmogorov–Arnold networks for multi-cancer classification and biomarker identification using multi-omics data

Cancer types

Accuracy

Precision

Recall

F1 Score

TCGA-LUAD

0.9590

0.9596

0.9198

0.9393

TCGA-LUSC

0.9237

0.9206

0.7945

0.8529

TCGA-PRAD

0.9847

0.9973

0.9620

0.9793

Back to article page