The paper presents a new approach to the computer aided diagnostic systems for the needs of quantitative electromyography. The approach is based on the analysis of wavelet scalograms of the motor unit action potentials calculated on the basis of 4th order Symlet wavelet. The scalograms provide the vector consisting of six features describing the state of a muscle that can be reduced to the two features with use of Linear Discriminant Analysis. Consequently, the healthy, myogenic and neurogenic cases can be successfully classified using the linear methods.