Skip to main content
. Author manuscript; available in PMC: 2018 May 11.
Published in final edited form as: IEEE Trans Biomed Eng. 2016 Oct 25;64(8):1761–1771. doi: 10.1109/TBME.2016.2611862

Table IV.

Depression Classification Results

No. Features LOO Cross-Validation
10-fold Cross-Validation
5-fold Cross-Validation
3-fold Cross-Validation
Accuracy AUC Accuracy AUC Accuracy AUC Accuracy AUC
1 0.747 ± 0.016 0.810 ± 0.014 0.747 ± 0.016 0.811 ± 0.017 0.753 ± 0.027 0.812 ± 0.028 0.758 ± 0.022 0.824 ± 0.011
2 0.785 ± 0.016 0.833 ± 0.016 0.780 ± 0.011 0.837 ± 0.016 0.780 ± 0.027 0.825 ± 0.026 0.785 ± 0.022 0.855 ± 0.010
3 0.806 ± 0.005 0.867 ± 0.012 0.801 ± 0.016 0.867 ± 0.014 0.801 ± 0.022 0.859 ± 0.021 0.817 ± 0.022 0.885 ± 0.012
4 0.839 ± 0.016 0.882 ± 0.014 0.828 ± 0.016 0.871 ± 0.023 0.844 ± 0.022 0.878 ± 0.022 0.833 ± 0.016 0.900 ± 0.013
5 0.849 ± 0.016 0.878 ± 0.013 0.833 ± 0.022 0.876 ± 0.016 0.860 ± 0.022 0.889 ± 0.015 0.876 ± 0.011 0.909 ± 0.010
6 0.844 ± 0.016 0.871 ± 0.017 0.844 ± 0.016 0.879 ± 0.016 0.849 ± 0.022 0.887 ± 0.024 0.887 ± 0.016 0.919 ± 0.009
7 0.844 ± 0.016 0.869 ± 0.014 0.833 ± 0.016 0.869 ± 0.021 0.839 ± 0.054 0.885 ± 0.078 0.892 ± 0.011 0.908 ± 0.012
8 0.849 ± 0.016 0.879 ± 0.015 0.839 ± 0.016 0.869 ± 0.018 0.833 ± 0.027 0.882 ± 0.024 0.882 ± 0.022 0.908 ± 0.020
9 0.844 ± 0.016 0.867 ± 0.015 0.839 ± 0.016 0.872 ± 0.018 0.817 ± 0.027 0.855 ± 0.042 0.876 ± 0.016 0.899 ± 0.021

All values are presented as median ± IQR. Classification was performed using 100 iterations of group equalization for each left out participant or fold. 3-fold cross-validation was performed by splitting all the data for each participant into the three partitions to use for cross-validation.