Fig. 2: Boxplots of the area under the receiver operating characteristic curve of four models. | npj Parkinson's Disease

Fig. 2: Boxplots of the area under the receiver operating characteristic curve of four models.

From: Baseline [18F]FP-CIT PET-based deep learning prediction of levodopa-induced dyskinesia in Parkinson’s disease

Fig. 2

Center line, median; box limits, upper and lower quartiles; whiskers, 1.5x interquartile range; diamond-shaped points, outliers. CNN MTL convolutional neural network multi-task learning, LR logistic regression, RF random forest, XGBoost extreme gradient boosting, AUROC area under the receiver operating characteristic curve. P-values: <0.05 (*), <0.01 (**).

Back to article page