Skip to main content

Table 3 The specificity, sensitivity, AUC, PPV, NPV and F1 score of the train set and test set in 1-year cohort and 5-year cohort, respectively

From: Development and testing of a random forest-based machine learning model for predicting events among breast cancer patients with a poor response to neoadjuvant chemotherapy

 

1-year cohort

5-year cohort

Random forest

Logistics regression

Random forest

Logistics regression

Train set

Specificity

0.91

0.657

0.75

0.721

Sensitivity

0.833

0.792

0.688

0.672

AUC (95% CI)

0.933 (0.876–0.989)

0.709 (0.615–0.804)

0.774 (0.693–0.854)

0.74 (0.656–0.825)

PPV

0.526

0.216

0.721

0.694

NPV

0.977

0.964

0.718

0.70

F1 score

0.645

0.339

0.704

0.683

Test set

Specificity

0.80

0.52

0.882

0.882

Sensitivity

0.833

0.833

0.75

0.688

AUC (95% CI)

0.81 (0.64–0.98)

0.653 (0.363–0.944)

0.829 (0.676–0.982)

0.752 (0.575–0.929)

PPV

0.333

0.172

0.857

0.846

NPV

0.976

0.963

0.789

0.75

F1 score

0.476

0.285

0.80

0.759