Automatic discovery of the number of MUAP clusters and superimposed MUAP decomposition in electromyograms

A novel data driven method for needle EMG decomposition is presented. The method is capable of automatically detecting the number of MUAPs. Superimposed MUAPs are detected and decomposed automatically into their constituents. No a priori knowledge of the number of MUAPs is required. The method is evaluated using a dataset consisting of 8 normal, 8 suffering from myopathy and 7 suffering from neuropathy subjects. The success rate on finding the correct number of clusters was 95%, 89% and 80%, respectively.