Table 2 Performance of semi-supervised classifier on test data.

From: Variational autoencoder provides proof of concept that compressing CDT to extremely low-dimensional space retains its ability of distinguishing dementia

Dataset

AUROC (95% C.I.)

Accuracy (95% C.I.)

F1-score (95% C.I.)

Precision (95% C.I.)

Sensitivity (95% C.I.)

Specificity (95% C.I.)

NPV (95% C.I.)

Test

0.78 (0.59–0.91)

0.71 (0.54–0.83)

0.70 (0.51–0.82)

0.71 (0.47–0.87)

0.69 (0.49–0.86)

0.74 (0.54–0.87)

0.74 (0.49–0.88)

Secondary validation

0.77 (0.66–0.86)

0.75 (0.65–0.84)

0.74 (0.59–0.83)

0.73 (0.56–0.85)

0.75 (0.58–0.86)

0.76 (0.67–0.85)

0.79 (0.63–0.88)

  1. AUROC area under the receiver operating curve, C.I confidence interval, NPV negative predictive value.
Back to article page