Table 3. Fraction of subjects correctly classified during cross-validation – Automatic vs Manual (bold indicates highest performing metric among algorithms).
Threshold | 33 |
34 |
35 |
36 |
37 |
38 |
|||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Method a | A | LV | A | LV | A | LV | A | LV | A | LV | A | LV | |||||
Precision | 0.70 | 0.80 | 0.76 | 0.87 | 0.81 | 0.79 | 0.82 | 0.83 | 0.85 | 0.81 | 0.83 | 0.73 | |||||
Recall | 0.37 | 0.42 | 0.70 | 0.48 | 0.69 | 0.42 | 0.69 | 0.49 | 0.62 | 0.64 | 0.64 | 0.80 | |||||
DSC | 0.48 | 0.55 | 0.73 | 0.62 | 0.75 | 0.55 | 0.75 | 0.61 | 0.72 | 0.71 | 0.72 | 0.77 | |||||
Accuracy | 0.88 | 0.90 | 0.89 | 0.87 | 0.86 | 0.80 | 0.85 | 0.81 | 0.81 | 0.81 | 0.78 | 0.78 |
a A = automatic, LV = manual linear regression-based method