Adaptive signal enhancement of somatosensory evoked potentials based on least mean squares and Kalman filter: A comparative study

This paper undertakes a comparative study of adaptive signal enhancers (ASE) of somatosensory evoked potentials (SEP) for spinal cord compression detection. We compare the ASE methods based on two adaptive filtering algorithms: the least mean squares (LMS) and Kalman filter (KF) in terms of their convergence rate, variability, and complexity. In addition, the two ASE methods are compared with the conventional ensemble averaging (EA) method for SEP extraction. Experimental results on a rat model show that the LMS-based and KF-based ASE methods have similar superior performance over the EA method and the two ASE methods also exhibit some slightly different properties during SEP extraction.