Table 7.
Classification result using selected features of all data collected.
| 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) | 75 | KNNb | 76.67 (8.47) | 90.44 (6.93) |
| Steady-remission (n=18) and Swing-drastic (n=48) | 7 | Naïve Bayes | 74.29 (9.27) | 84.31 (10.89) |
| Steady-remission (n=18) and Swing-moderate (n=74) | 8 | KNN | 80.56 (15.28) | 97.08 (5.91) |
| Steady-depressed (n=61) and Swing-drastic (n=48) | 7 | Logistic regression | 75.91 (13.18) | 89.83 (10.34) |
| Steady-depressed (n=61) and Swing-moderate (n=74) | 12 | SVMc | 74.73 (8.44) | 83.95 (12.27) |
aML: machine learning.
bKNN: K-nearest neighbors.
cSVM: support vector machine.