Table 3 The results of evaluation metrices according to dataset-level evaluation.

From: Convolutional neural networks-based early Parkinson’s disease classification using cycling data from a steerable indoor bicycle

 

Accuracy

Precision

Recall

Specificity

F1 score

Fold 1

0.794

0.960

0.579

0.979

0.722

Fold 2

0.813

0.711

1.000

0.652

0.831

Fold 3

0.730

0.884

0.477

0.947

0.620

Fold 4

0.745

0.656

0.940

0.578

0.773

Fold 5

0.954

0.976

0.901

0.986

0.937

Average

0.807

0.837

0.779

0.828

0.777

Back to article page