Table 4 AUROC, BA, F1 Score and MCC for the best models, comparing the best radiomics model to the semantic features, clinical baseline and SINS variable.

From: The importance of planning CT-based imaging features for machine learning-based prediction of pain response

Data

Model

AUROC

BA

F1

MCC

CTV

RFC

0.62 ± 0.01

0.58 ± 0.02

0.37 ± 0.03

0.15 ± 0.04

Semantic

RFC

0.63 ± 0.01

0.58 ± 0.02

0.39 ± 0.03

0.16 ± 0.04

Clinical

SVM

0.80 ± 0.01

0.72 ± 0.03

0.56 ± 0.05

0.43 ± 0.06

SINS

LR

0.65 ± 0.01

0.58 ± 0.03

0.36 ± 0.05

0.16 ± 0.06

SINS (binary)

0.54 ± 0.01

0.52 ± 0.03

0.19 ± 0.05

0.04 ± 0.06

Back to article page