Signals

We present a methodology to predict the presence of myopathy (muscle disease) from intramuscular elec-tromyography (EMG) signals. By evaluating the shape and frequency of electrical action potentials produced by muscular fibers and captured in EMG measure-ments, a physician can often detect both the presence and the severity of such disorders. However, EMG measurements can vary significantly across different subjects, different muscles, and according to session-specific characteristics such as muscle fatigue and de-gree of contraction. By considering fixed-duration (0.5-2 sec) frequency-domain samples of diagnostic regions in EMG signals measured at full muscle con-traction, we can automatically detect the presence of myopathies across different subjects and muscles with ~90 % accuracy. We argue that our methodology is more generally applicable than existing methods that depend upon accurate segmentation of individual mo-tor unit action potential (MUAP) waveforms. We pre-sent a rigorous evaluation of our technique across sev-eral different subjects and muscles