Table 2.

Diagnostic performance of contrast-enhanced T1-weighted image radiomic-based prediction of EGFR mutation status in lung cancer brain metastases cases.

Classification	Best feature selection method	Optimal feature number	AUC	Sensitivity	Specificity	Accuracy
RF	RF	22	86.81	84.41	72.72	86.66
SVM	RF	17	85.76	82.07	81.81	86.19
AdaBoost	RF	18	85.71	83.093	72.72	85.23
LASSO-LR	Laplacian	48	68.11	55.03	81.81	69.04

Epidermal growth factor receptor (EGFR); area under the curve (AUC); random forest (RF); support vector machine (SVM).