Jd. Slater et al., NEURAL-NETWORK ANALYSIS OF THE P300 EVENT-RELATED POTENTIAL IN MULTIPLE-SCLEROSIS, Electroencephalography and clinical neurophysiology, 90(2), 1994, pp. 114-122
Neural network analysis is sensitive to subtle changes in patterns of
data. We hypothesized that a disease process which can cause impairmen
t of cortical function such as multiple sclerosis (MS) would affect th
e P300 cognitive evoked potential (P300) in a manner detectable by a f
eedforward backpropagation neural network. Such a network was trained
using a learning data set consisting of 101 P300 wave forms (from 26 M
S patients and 26 normal controls). The network was then used to class
ify a randomly selected test data set of 20 studies (2 studies each of
5 MS patients and 5 controls) to which it had not been previously exp
osed, with an average accuracy (MS = abnormal, control = normal) of 81
% for a single midline electrode, increasing to 90% using 3 midline el
ectrodes in a jury system. Neural network analysis can be of help in d
istinguishing normal (control) P300 from abnormal (MS) P300.