Statistical Technique for Classification of MUAPs for Neuromuscular disease

The Electromyograph (EMG) is useful to know the state of a patient under medical diagnosis and treatment. As the number of neuromuscular patients is increasing, it is not possible to take care of all the neuromuscular patients by carrying out manual investigations under all the conditions. Therefore it is required to design a computer aided expert system which can analyze and interpret the EMG signal. The EMG data acquisition and preprocessing, detection of MUAPs, classification of EMGs into similar groups, feature extraction of these groups and their usage in disease classification and diagnostics are the important stages in computer aided EMG analysis and interpretation. The objective of the present work is to detection of MUAPs, classification of EMGs into similar groups for computer aided analysis and interpretation of EMG signals for disease diagnosis. In the work real time recordings of myopathy, motor neuron disease and normal cases have been considered for MUAP segmentation and classification by statistical technique. EMG signal recorded by the needle electrode has been used.