Computer recognition of brain stem auditory evoked potential wave V by a neural network.

A neural network simulator was used to create a connectionist model for the recognition of the peak of wave V of the brain stem auditory evoked potential (BAEP) test. Wave forms were selected from BAEPs performed in the last four years at the University of Pittsburgh Presbyterian University Hospital (PUH). The ipsilateral and contralateral wave forms were digitized and then sampled at 0.1 msec intervals using linear interpolation. The resulting amplitudes were normalized to the range less than -1, 1 greater than. The normalized amplitudes were used as the initial activation values for the processing elements of the input layer. The desired outputs (the target locations for wave V) were determined by adjusting the latencies recorded by the physician interpreter for any distortion in the digitizing process. The location of wave V was represented in the output layer by setting the output element which correspond to the target location and its immediate neighbors to high activation levels and all the remaining output units to zero activity. Two network architectures, differing only in the hidden unit layer, with 40 and 16 hidden units respectively, were used. The networks were trained using standard back-propagation. Several trials from different starting points were performed for each architecture. The training set was composed of the wave forms resulting from the stimulation of 50 ears. The best network, found after 60 epochs (3000 presentations) was able to correctly identify 17 out of 20 cases (85%) from a set of test cases which were independent from the training set.