TABLE 5.

Cross-validation results from DNN according to the number of top features (mean ± standard deviation).

Cross-validation results (n = 34)
The number of features	Sensitivity	Specificity	Accuracy	Balanced accuracy	AUROC
1	0.73 ± 0.24	0.22 ± 0.09	0.27 ± 0.06	0.47 ± 0.09	0.45 ± 0.15
2	0.73 ± 0.32	0.27 ± 0.10	0.32 ± 0.05	0.50 ± 0.11	0.52 ± 0.13
3	0.53 ± 0.40	0.45 ± 0.06	0.46 ± 0.03	0.49 ± 0.17	0.47 ± 0.16
4	0.66 ± 0.36	0.56 ± 0.08	0.57 ± 0.06	0.61 ± 0.17	0.60 ± 0.19
5	0.59 ± 0.24	0.76 ± 0.11	0.75 ± 0.08	0.68 ± 0.08	0.77 ± 0.09
6	0.53 ± 0.33	0.72 ± 0.07	0.70 ± 0.06	0.62 ± 0.15	0.71 ± 0.16
7	0.46 ± 0.33	0.83 ± 0.10	0.78 ± 0.08	0.63 ± 0.15	0.71 ± 0.20
8	0.49 ± 0.14	0.74 ± 0.10	0.72 ± 0.09	0.62 ± 0.09	0.71 ± 0.15
9	0.49 ± 0.13	0.77 ± 0.07	0.74 ± 0.09	0.63 ± 0.05	0.69 ± 0.09
10	0.64 ± 0.31	0.79 ± 0.09	0.77 ± 0.07	0.72 ± 0.13	0.76 ± 0.12
11	0.24 ± 0.24	0.78 ± 0.05	0.73 ± 0.04	0.51 ± 0.10	0.66 ± 0.14