Skip to main content

Table 7 Diagnostic performances of the clinical model, radiomic model and RNWCF in the validation and external test cohorts

From: Noninvasive prediction of node-positive breast cancer response to presurgical neoadjuvant chemotherapy therapy based on machine learning of axillary lymph node ultrasound

Data set

Models

Accuracy (95% CI)

Sensitivity (95% CI)

Specificity (95% CI)

Validation cohort

Clinical

0.809 (0.757–0.860)

0.814 (0.750–0.875)

0.795 (0.684–0.896)

Radiomics

0.706 (0.640–0.772)

0.711 (0.630–0.781)

0.692 (0.564–0.821)

RNWCF

0.846 (0.794–0.897)

0.907 (0.853–0.955)

0.692 (0.568–0.812)

External test cohort

Clinical

0.802 (0.716–0.877)

0.808 (0.708–0.893)

0.793 (0.656–0.920)

Radiomics

0.728 (0.642–0.815)

0.865 (0.787–0.941)

0.483 (0.333–0.647)

RNWCF

0.778 (0.691–0.852)

0.731 (0.623–0.830)

0.862 (0.750–0.963)