Tabu Search and Machine-Learning Classification of Benign and Malignant Proliferative Breast Lesions

Table 4

Comparison of proposed method and other methods on BIDMC-MGH.

Model	AUC (%)
L1-regularized LR [5]	85.8
L1-regularized LR with active feature [5]	89.7
LR with early stopping and active features [34]	88.4
CAFE model [34]	91.8
Proposed model	95