RT Journal Article
SR Electronic
T1 Distinctive BOLD Connectivity Patterns in the Schizophrenia Brain: Machine-learning based comparison between various connectivity measures
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 084160
DO 10.1101/084160
A1 Hio-Been Han
YR 2016
UL http://biorxiv.org/content/early/2016/10/31/084160.abstract
AB Recent functional magnetic resonance imaging (fMRI) studies have found distinctive functional connectivity in the schizophrenia brain. However, most of the studies focused on the correlation value to define the functional connectivity for BOLD fluctuations between brain regions, which resulted in the limited understanding to the network properties of altered wirings in the schizophrenia brain. Here I characterized the distinctiveness of BOLD connectivity pattern in the schizophrenia brain relative to healthy brain with various similarity measures in the time-frequency domain, while participants performing the working memory task in the MRI scanner. To assess the distinctiveness of the connectivity pattern, discrimination performances of pattern classifier machine trained with each similarity measure were compared. Interestingly, classifier machine trained by time-lagging patterns of low frequency fluctuation (LFF) produced highest classifying accuracy than the machines trained by other measures. Also, classifier machine trained by coherence pattern in LFF band also made better performance than the machine trained by correlation-based connectivity pattern. These results indicate that there have been unwatched but important features in the functional connectivity pattern of schizophrenia brain on which traditional emphasis on correlation analysis could not capture.