From: Sparsifying machine learning models identify stable subsets of predictive features for behavioral detection of autism
Module
3
Number of features
9
Best classifier
L2 LR
L1 Lin SVM
Optimal parameters
C = 1
C = 0.5
Area under ROC
0.95
Precision
0.99
Recall/sensitivity
0.89
Specificity
0.90
0.87
Balanced accuracy
0.91
F1 score
0.94
0.97