Differences Between Schizophrenic and Normal Subjects Using Network Properties from fMRI

Schizophrenia has been proposed to result from impairment of functional connectivity. We aimed to use machine learning to distinguish schizophrenic subjects from normal controls using a publicly available functional MRI (fMRI) data set. Global and local parameters of functional connectivity were extracted for classification. We found decreased global and local network connectivity in subjects with schizophrenia, particularly in the anterior right cingulate cortex, the superior right temporal region, and the inferior left parietal region as compared to healthy subjects. Using support vector machine and 10-fold cross-validation, nine features reached 92.1% prediction accuracy, respectively. Our results suggest that there are significant differences between control and schizophrenic subjects based on regional brain activity detected with fMRI.

[1]  Vince D. Calhoun,et al.  Accurate classification of schizophrenia patients based on novel resting-state fMRI features , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[3]  L. Freeman.  Centrality in social networks conceptual clarification , 1978 .

[4]  Hee Chan Kim,et al.  Automated network analysis to measure brain effective connectivity estimated from EEG data of patients with alcoholism , 2017, Physiological measurement.

[5]  J B Poline,et al.  Evidence for abnormal cortical functional connectivity during working memory in schizophrenia. , 2001, The American journal of psychiatry.

[6]  M. Bradley,et al.  Emotional arousal and activation of the visual cortex: an fMRI analysis. , 1998, Psychophysiology.

[7]  Thomas E. Nichols,et al.  Functional connectomics from resting-state fMRI , 2013, Trends in Cognitive Sciences.

[8]  A. Malhotra,et al.  Antipsychotic treatment and functional connectivity of the striatum in first-episode schizophrenia. , 2015, JAMA psychiatry.

[9]  M. H. Parks,et al.  Reduced fronto-cerebellar functional connectivity in chronic alcoholic patients. , 2012, Alcoholism, clinical and experimental research.

[10]  G. Bush,et al.  Functional Neuroimaging of Attention-Deficit/Hyperactivity Disorder: A Review and Suggested Future Directions , 2005, Biological Psychiatry.

[11]  R. Kikinis,et al.  A review of diffusion tensor imaging studies in schizophrenia. , 2007, Journal of psychiatric research.

[12]  P. Matthews,et al.  White matter abnormalities and brain activation in schizophrenia: A combined DTI and fMRI study , 2007, Schizophrenia Research.

[13]  C. Stam,et al.  Small‐world properties of nonlinear brain activity in schizophrenia , 2009, Human brain mapping.

[14]  Karl J. Friston,et al.  Regional Brain Activity in Chronic Schizophrenic Patients during the Performance of a Verbal Fluency Task , 1995, British Journal of Psychiatry.

[15]  R. Poldrack.  Region of interest analysis for fMRI. , 2007, Social cognitive and affective neuroscience.

[16]  R Pastor-Satorras,et al.  Dynamical and correlation properties of the internet. , 2001, Physical review letters.

[17]  Karl J. Friston,et al.  The left medial temporal region and schizophrenia. A PET study. , 1992, Brain : a journal of neurology.

[18]  M. Weiner,et al.  Reduced hippocampal functional connectivity in Alzheimer disease. , 2007, Archives of neurology.

[19]  Andrea Bergmann,et al.  Statistical Parametric Mapping The Analysis Of Functional Brain Images , 2016 .

[20]  Guillaume A. Rousselet,et al.  Improving standards in brain-behavior correlation analyses , 2012, Front. Hum. Neurosci..

[21]  S. Lawrie,et al.  Towards the identification of imaging biomarkers in schizophrenia, using multivariate pattern classification at a single-subject level , 2013, NeuroImage: Clinical.

[22]  Sébastien Ourselin,et al.  Issues with threshold masking in voxel-based morphometry of atrophied brains , 2009, NeuroImage.

[23]  D. Barch,et al.  Brain Network Connectivity in Individuals with Schizophrenia and Their Siblings , 2011, Biological Psychiatry.

[24]  Stephan Heckers,et al.  Reversed hemispheric asymmetry during simple visual perception in schizophrenia , 2002, Psychiatry Research: Neuroimaging.

[25]  Feng Wen,et al.  Research and Application of Data Mining Feature Selection Based on Relief Algorithm , 2014, J. Softw..

[26]  Shekhar Saxena,et al.  Research capacity for mental health in low - and middle - income countries , 2007 .

[27]  Alan A. Wilson,et al.  5-HT2 and D2 receptor occupancy of olanzapine in schizophrenia: a PET investigation. , 1998, The American journal of psychiatry.

[28]  Yuan Zhou,et al.  Functional dysconnectivity of the dorsolateral prefrontal cortex in first-episode schizophrenia using resting-state fMRI , 2007, Neuroscience Letters.

[29]  E. L. Berger,et al.  Research Capacity for Mental Health in Low- and Middle-Income Countries: Results of a Mapping Project , 2010 .

[30]  Rudi A. Dierckx,et al.  Neuroinflammation in Schizophrenia-Related Psychosis: A PET Study , 2009, Journal of Nuclear Medicine.

[31]  J. O. Johannessen,et al.  Early detection and intervention with schizophrenia: rationale. , 1996, Schizophrenia bulletin.

[32]  Olaf Sporns,et al.  Complex network measures of brain connectivity: Uses and interpretations , 2010, NeuroImage.

[33]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[34]  P. J. McKenna,et al.  Failure of deactivation in the default mode network: a trait marker for schizophrenia? , 2014, Psychological Medicine.

[35]  Thomas M. Cover,et al.  Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..

[36]  Michael C. Stevens,et al.  The Effects of Stimulant Medication on Working Memory Functional Connectivity in Attention-Deficit/Hyperactivity Disorder , 2012, Biological Psychiatry.

[37]  S. Taylor,et al.  Low-frequency BOLD fluctuations demonstrate altered thalamocortical connectivity in schizophrenia. , 2010, Schizophrenia bulletin.

[38]  Dewen Hu,et al.  Discriminative analysis of resting-state functional connectivity patterns of schizophrenia using low dimensional embedding of fMRI , 2010, NeuroImage.

[39]  Michelle Hampson,et al.  Functional connectivity between ventral prefrontal cortex and amygdala at low frequency in the resting state in bipolar disorder , 2010, Psychiatry Research: Neuroimaging.

[40]  Ulrike M. Krämer,et al.  BASCO: a toolbox for task-related functional connectivity , 2015, Front. Syst. Neurosci..

[41]  Jonathan D. Cohen,et al.  Full correlation matrix analysis (FCMA): An unbiased method for task-related functional connectivity , 2015, Journal of Neuroscience Methods.

[42]  Tianzi Jiang,et al.  Automatic classification of schizophrenia using resting-state functional language network via an adaptive learning algorithm , 2014, Medical Imaging.

[43]  Kurt Hornik,et al.  The support vector machine under test , 2003, Neurocomputing.

[44]  Vince D. Calhoun,et al.  Human Neuroscience , 2022 .

[45]  Karl J. Friston,et al.  Abnormal Cingulate Modulation of Fronto-Temporal Connectivity in Schizophrenia , 1999, NeuroImage.

[46]  Hae-Jeong Park,et al.  Functional disconnection between the prefrontal and parietal cortices during working memory processing in schizophrenia: a[15(O)]H2O PET study. , 2003, The American journal of psychiatry.

[47]  Y. Wang,et al.  The CHRM3 gene is implicated in abnormal thalamo-orbital frontal cortex functional connectivity in first-episode treatment-naive patients with schizophrenia , 2016, Psychological Medicine.