Table 2 Experimental results on the test set of the DAIC-WOZ data set
From: Towards automatic text-based estimation of depression through symptom prediction
Model | Binary Diagnosis Eval | PHQ-8 Score Severity Eval | 5-Class Severity Eval | |||
|---|---|---|---|---|---|---|
\(miF_1 \pm \sigma\) | \(maF_1 \pm \sigma\) | \(\text {MAE} \pm \sigma\) | \(ma\text {MAE} \pm \sigma\) | miF1-5c \(\pm \sigma\) | maF1-5c \(\pm \sigma\) | |
Binary Diagnosis | 0.719 ± 0.016 | 0.701 ± 0.010 | – | – | – | – |
5-Class Severity | 0.711 ± 0.026 | 0.683 ± 0.024 | – | – | 0.468 ± 0.023 | 0.270 ± 0.025 |
PHQ-8 Score Severity | 0.681 ± 0.019 | 0.584 ± 0.024 | 5.03 ± 0.09 | 5.69 ± 0.12 | 0.289 ± 0.029 | 0.135 ± 0.014 |
Symptom Prediction | 0.766 ± 0.023 | 0.739 ± 0.025 | 3.78 ± 0.13 | 4.19 ± 0.13 | 0.426 ± 0.014 | 0.270 ± 0.019 |
HCAN [7] | – | 0.630 | – | – | – | – |
HAN+L [8] | – | 0.700 | – | – | – | – |
ASP MT. DLC+DLR+EIR [25] | – | – | 3.69 | – | 0.600 | – |
HCAG-T [23] | – | 0.770\(\ddag\) | 3.73\(\ddag\) | – | – | – |
SGNN [27] | – | – | 3.76 | – | – | – |