Skip to main content

Table 3 Performance of the DLR and Integrated models constructed using the XGBoost machine learning algorithm in predicting the efficacy of NAC in the training and test cohorts

From: Predicting the efficacy of neoadjuvant chemotherapy in breast cancer patients based on ultrasound longitudinal temporal depth network fusion model

Cohort

Model

AUC

95%CI

Accuracy

Sensitivity

Specificity

Training cohort

DLR model

0.827

0.817–0.886

0.763

0.665

0.890

Integrated

0.924

0.898–0.967

0.831

0.786

0.960

Test cohort

DLR model

0.827

0.799–0.836

0.752

0.700

0.792

Integrated

0.875

0.806–0.877

0.817

0.775

0.849