An artificial neural network that uses eye-tracking performance to identify patients with schizophrenia

Several researchers have underscored the importance of precise characteriza tion of eye-tracking dysfunction (ETD) in patients with schizophrenia. This biological trait appears to be useful in estimating the probability of gen etic recombination in an individual, so it may be helpful in linkage studie s. This article describes a nonlinear computational model for using ETD to identify schizophrenia, A back-propagation neural network (BPNN) was used t o classify schizophrenia patients and normal control subjects on the basis of their eye-tracking performance, Better classification results were obtai ned with BPNN than with a linear computational model (discriminant analysis ): a priori predictions were approximately 80 percent correct. These result s suggest, first, that eye-tracking patterns can be useful in distinguishin g patients with schizophrenia from a normal comparison group with an accura cy of approximately 80 percent. Second, parallel distributed processing net works are able to detect higher order nonlinear relationships among predict or quantitative measurements of eye-tracking performance.