Neural Networks is Computer Aided Clinical Electromyography

In concentric needle elecromyography quantitative measurement are applied on the motor unit actin potentials, which are recorded from the biceps muscle of normal subjects and patients suffering with neuromuscular disorders. In this study an "unsupervised" learning neural network is employed for the classification of neuromuscuar disorders. The results suggest that unsupervised learning haw certain advantages in case where the classes of the training data are unknown in number, or are not easily separated. The issue of separability haw always been an important aspect of clinical science, illustrated in the present study as an "unsupervised" neural network problem