Table 8.
Classification result using selected features of call logs, sleep data, step count data, and heart rate 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=79) and Swing (n=122) | 37 | Random forest | 75.64 (5.09) | 89.93 (7.26) |
| Steady-remission (n=18) and Swing-drastic (n=48) | 8 | Naïve Bayes | 81.67 (15.32) | 93.33 (10.41) |
| Steady-remission (n=18) and Swing-moderate (n=74) | 7 | Decision tree | 80.56 (10.49) | 92.88 (10.43) |
| Steady-depressed (n=61) and Swing-drastic (n=48) | 35 | Random forest | 84.27 (14.36) | 85.33 (15.72) |
| Steady-depressed (n=61) and Swing-moderate (n=74) | 25 | SVMb | 77.86 (8.90) | 88.99 (9.76) |
aML: machine learning.
bSVM: support vector machine.