Table 6.

Combined anatomical and network features.

Cross-validation	10	20	50	100	200	400	800	1200	2000	3000	4000	6000	All (12,426)
2 Sample t-test	0.63	0.64	0.61	0.60	0.62	0.66	0.71	0.72	0.75	0.75	0.76	0.77	0.77
Nested CV	0.62	0.64	0.65	0.63	0.62	0.64	0.68	0.70	0.75	0.77	0.76	0.77	0.77
Recursive FE	0.65	0.65	0.65	0.69	0.72	0.73	0.76	0.76	0.76	0.77	0.77	0.77	0.77
Test set	10	20	50	100	200	400	800	1200	2000	3000	4000	6000	All (12,426)
2 Sample t-test	0.72	0.74	0.72	0.66	0.66	0.70	0.67	0.71	0.70	0.70	0.70	0.73	0.76
Nested CV	0.49	0.63	0.62	0.64	0.57	0.69	0.68	0.69	0.70	0.72	0.74	0.73	0.76
Recursive FE	0.74	0.73	0.69	0.67	0.69	0.70	0.72	0.72	0.76	0.75	0.77	0.77	0.76

Results summarizing ADHD prediction using anatomical features combined with SIC network features (but not non-imaging phenotypic features). Entries indicate the area under the ROC curve (AUC) for classifiers built using different feature selection methods (rows) and different numbers of features (columns). Top: results on leave-out folds during cross-validation. Bottom: results on separate test set based on training across all examples in the training/cross-validation set.