Functional classification of schizophrenia using feed forward neural networks

In medicine, the nature of an illness is often determined through behavioral or biological markers. The process of diagnosis becomes difficult when dealing with mental disorders since they rely primarily on behavioral markers. Schizophrenia is an example of a complex mental disorder that relies on aberrant behavior such as auditory hallucinations, dampening of emotions, paranoia, etc. This research is an attempt to determine a biological marker for schizophrenia through the use of functional magnetic resonance imaging (fMRI). In this paper, we propose a method of classification of schizophrenia and healthy controls, using a neural network approach and functional brain 'modes' estimated from resting state data using independent component analysis. A reliable technique for discriminating schizophrenia based upon fMRI would be a significant advance and may also provide additional information about the biological implications of mental illness.