Hybrid ICA–Bayesian network approach reveals distinct effective connectivity differences in schizophrenia

Abstract

We utilized a discrete dynamic Bayesian network (dDBN) approach (Burge et al., 2007) to determine differences in brain regions between patients with schizophrenia and healthy controls on a measure of effective connectivity, termed the approximate conditional likelihood score (ACL) (Burge and Lane, 2005). The ACL score represents a class-discriminative measure of effective connectivity by measuring the relative likelihood of the correlation between brain regions in one group versus another. The algorithm is capable of finding non-linear relationships between brain regions because it uses discrete rather than continuous values and attempts to model temporal relationships with a first-order Markov and stationary assumption constraint (Papoulis, 1991). Since Bayesian networks are overly sensitive to noisy data, we introduced an independent component analysis (ICA) filtering approach that attempted to reduce the noise found in fMRI data by unmixing the raw datasets into a set of independent spatial component maps. Components that represented noise were removed and the remaining components reconstructed into the dimensions of the original fMRI datasets. We applied the dDBN algorithm to a group of 35 patients with schizophrenia and 35 matched healthy controls using an ICA filtered and unfiltered approach. We determined that filtering the data significantly improved the magnitude of the ACL score. Patients showed the greatest ACL scores in several regions, most markedly the cerebellar vermis and hemispheres. Our findings suggest that schizophrenia patients exhibit weaker connectivity than healthy controls in multiple regions, including bilateral temporal and frontal cortices, plus cerebellum during an auditory paradigm.

Altered default mode network connectivity in alzheimer's disease—A resting functional MRI and bayesian network study

“…Nodes in these two studies were the activated brain regions identified from first performing SPM analysis over the same dataset (SPM+BN/DBN). Additionally, Kim et al (2008) used DBN to examine the effective connectivity difference in schizophrenia during an auditory paradigm, and ICA was used to reduce the noise in all the fMRI data (Kim et al, 2008). And the nodes in the DBN were also the regions showing significant activity from SPM analysis (ICA+SPM+DBN).…”

Large-scale directional connections among multi resting-state neural networks in human brain: A functional MRI and Bayesian network modeling study

“…BN is recently introduced to fMRI studies to investigate the effective connectivity patterns among brain regions (Kim et al, 2008; Li et al, 2008; Li et al, 2009; Rajapakse and Zhou, 2007; Zheng and Rajapakse, 2006). It can characterize the relation of conditional dependencies/independencies between a set of variables, and identify the directionality of connections (but see the cautionary note in the Discussion section and the work by Smith et al (2010)).…”

Characterization of groups using composite kernels and multi-source fMRI analysis data: Application to schizophrenia

“…ICA has been extensively applied to fMRI data to identify differences among healthy controls and schizophrenia patients (Kim et al, 2008; Demirci et al, 2009; Calhoun et al, 2006). Thus, Calhoun et al (2008) showed that the temporal lobe and the default mode components (networks) could reliably be used together to identify patients with bipolar disorder and schizophrenia from each other and from healthy controls.…”