Figure 4. Neural network predication.

Neural network classification of 23 individuals (x-axis) with known clinical information. Values (y-axis) are predicted over the trained network and are 0.1 to 1; values (x) ≤0.54 reflect a neural-network classification of “normal,” and values (x) ≥0.55 reflect a neural-network classification of PD. Individuals denoted by a triangle  =  normal, circle  =  PD and square  =  misdiagnosed individual.