Table 4.
Classification result using selected features of sleep data.
| Two classes or subclasses being predicted (number of data samples) | Features selected, n | Best MLa model | Average percent accuracy (SD) | Average percent recall (SD) |
| Steady (n=230) and Swing (n=382) | 48 | Random forest | 72.70 (4.74) | 90.80 (3.92) |
| Steady-remission (n=88) and Swing-drastic (n=124) | 44 | Random forest | 77.34 (7.50) | 90.61 (6.23) |
| Steady-remission (n=88) and Swing-moderate (n=258) | 17 | Random forest | 84.46 (5.94) | 97.38 (2.95) |
| Steady-depressed (n=142) and Swing-drastic (n=124) | 48 | Random forest | 68.87 (9.34) | 67.09 (9.19) |
| Steady-depressed (n=142) and Swing-moderate (n=258) | 5 | Random forest | 74.75 (5.96) | 90.37 (5.18) |
aML: machine learning.