Skip to main content

Table 2 NAC prediction performance with Emory Hospital cohort

From: Digital image analysis and machine learning-assisted prediction of neoadjuvant chemotherapy response in triple-negative breast cancer

 

Accuracy

AUC

Sensitivity

Specificity

Precision

F1

1NN

0.729

[0.703, 0.756]

0.735

[0.690, 0.779]

0.745

[0.693, 0.797]

0.706

[0.676, 0.736]

0.792

[0.755, 0.828]

0.768

[0.747, 0.788]

Linear SVM

0.624

[0.586, 0.660]

0.709

[0.654, 0.764]

0.490

[0.425, 0.555]

0.824

[0.801, 0.846]

0.806

[0.774, 0.839]

0.610

[0.581, 0.638]

RBF SVM

0.835

[0.808, 0.862]

0.827

[0.786, 0.868]

0.824

[0.768, 0.879]

0.853

[0.818, 0.887]

0.894

[0.849, 0.938]

0.857

[0.823, 0.892]

EnsembleTree RUSBoost

0.706

[0.686, 0.725]

0.681

[0.648, 0.714]

0.784

[0.735, 0.833]

0.588

[0.566, 0.611]

0.741

[0.705, 0.777]

0.762

[0.740, 0.784]

  1. The average and 95% confidence interval of accuracy, AUC, sensitivity, specificity, precision, and F1-Score are presented for each model by a leave-one-out cross-validation strategy
Back to article page

Breast Cancer Research

ISSN: 1465-542X

Contact us