In an important subset of surgical procedures, the procedure itself po
ses a significant threat to the patient's nervous system. In order to
reduce this threat, neurophysiological function of the structures at r
isk may be monitored during surgery using time-locked sensory or motor
-evoked responses. A simple but powerful extension of the segmented an
d sliding average techniques currently in wide use is described and de
monstrated. By filling polynomial functions of time to capture time va
riations in tire evoked response, signal/noise enhancement comparable
with that of averaging if obtained.,More importantly, a considerable i
mprovement in lime resolution is gained. In the demonstration data set
Presented in the fixtures, clinically significant changes were identi
fiable in one-sixth of the time required using signal averaging.