Table 6.
Classification result using selected features of 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=80) and Swing (n=122) | 20 | Random forest | 75.19 (8.38) | 91.92 (6.71) |
| Steady-remission (n=18) and Swing-drastic (n=48) | 9 | KNNb | 75.48 (16.53) | 85.17 (15.10) |
| Steady-remission (n=18) and Swing-moderate (n=74) | 13 | KNN | 82.67 (10.03) | 97.64 (4.73) |
| Steady-depressed (n=62) and Swing-drastic (n=48) | 8 | Decision tree | 74.55 (13.97) | 73.79 (16.04) |
| Steady-depressed (n=62) and Swing-moderate (n=74) | 18 | Random forest | 69.29 (13.21) | 75.16 (13.96) |
aML: machine learning.
bKNN: K-nearest neighbors.