Table 4 Performance of each of the three logistic regression (LR) classification models

From: Smartphone-based prediction of dopaminergic deficit in prodromal and manifest Parkinson’s disease

 

AUC ± SD (95% CI)

AUC adjusted ± SD (95% CI)

Sensitivity ± SD

Specificity ± SD

Balanced accuracy ± SD (Sensitivity + Specificity)/2

MDS-UPDRS-III (LR)

0.88 ± 0.02 (0.78 - 0.94)

0.83 ± 0.04 (0.76-0.92)

0.70 ± 0.15

0.93 ± 0.09

0.82 ± 0.08

Smartphone features (LR)

0.76 ± 0.09 (0.66-0.85)

0.73 ± 0.05 (0.64-0.83)

0.73 ± 0.09

0.75 ± 0.16

0.74 ± 0.09

Smartphone features + MDS-UPDRS-III (LR)

0.88 ± 0.04 (0.80-0.94)

0.85 ± 0.04 (0.77-0.93)

0.79 ± 0.08

0.89 ± 0.10

0.84 ± 0.06

  1. Reported using the Area-Under-the-Curve (AUC) with 95% confidence intervals (CI), sensitivity, and specificity. The AUC adjusted for the effect of sex is also reported (AUC adjusted). Balanced accuracy is the average of sensitivity and specificity. SD: standard deviation of the error metric.
Back to article page