Recursive Cluster Elimination Based Support Vector Machine for Disease State Prediction Using Resting State Functional and Effective Brain Connectivity

Abstract

BackgroundBrain state classification has been accomplished using features such as voxel intensities, derived from functional magnetic resonance imaging (fMRI) data, as inputs to efficient classifiers such as support vector machines (SVM) and is based on the spatial localization model of brain function. With the advent of the connectionist model of brain function, features from brain networks may provide increased discriminatory power for brain state classification.Methodology/Principal FindingsIn this study, we introduce a novel framework where in both functional connectivity (FC) based on instantaneous temporal correlation and effective connectivity (EC) based on causal influence in brain networks are used as features in an SVM classifier. In order to derive those features, we adopt a novel approach recently introduced by us called correlation-purged Granger causality (CPGC) in order to obtain both FC and EC from fMRI data simultaneously without the instantaneous correlation contaminating Granger causality. In addition, statistical learning is accelerated and performance accuracy is enhanced by combining recursive cluster elimination (RCE) algorithm with the SVM classifier. We demonstrate the efficacy of the CPGC-based RCE-SVM approach using a specific instance of brain state classification exemplified by disease state prediction. Accordingly, we show that this approach is capable of predicting with 90.3% accuracy whether any given human subject was prenatally exposed to cocaine or not, even when no significant behavioral differences were found between exposed and healthy subjects.Conclusions/SignificanceThe framework adopted in this work is quite general in nature with prenatal cocaine exposure being only an illustrative example of the power of this approach. In any brain state classification approach using neuroimaging data, including the directional connectivity information may prove to be a performance enhancer. When brain state classification is used for disease state prediction, our approach may aid the clinicians in performing more accurate diagnosis of diseases in situations where in non-neuroimaging biomarkers may be unable to perform differential diagnosis with certainty.

A Review of Feature Reduction Techniques in Neuroimaging

“…An interesting variant of RFE, which involves backward-elimination of voxel clusters rather than individual features, has recently been explored (Deshpande et al 2010). In passing, we note that although the majority of RFE applications in neuroimaging are largely in predictive classification, recently RFE has been used for regression tasks (Fan et al 2010; He et al 2008; Mwangi et al 2013).…”

Decreased Effective Connectivity from Cortices to the Right Parahippocampal Gyrus in Alzheimer's Disease Subjects

“…In the R-fMRI studies, the test proved to be a feasible method to study the EC network architecture at voxel (Wu et al, 2013) or regional (Deshpande et al, 2011;Liao et al, 2010;Uddin et al, 2009) levels. It also improved disease classification (Deshpande et al, 2010). Several studies investigated brain EC, using GC on subjects with AD (Liu et al, 2012;Miao et al, 2011) and amnestic mild cognitive impairment (Adamcio et al, 2010;Liang et al, 2014), which is often considered to be prodromal AD.…”

Brain Network Activation Analysis Utilizing Spatiotemporal Features for Event Related Potentials Classification

“…With the developing field of imaging connectomics (Fornito and Bullmore, 2015) and its relation to cognitive processes (Sporns, 2014), other modeling methods of functional interactions between brain regions should be examined (Wang et al, 2014) in order to improve the spatiotemporal network model currently embedded in BNA analysis. Modeling techniques to be tested will include structural equation modeling (SEM, Büchel and Friston, 1997; Tsubomi et al, 2009), dynamic causal modeling (Friston et al, 2003; Moran et al, 2013), Granger causality (Ding et al, 2006; Deshpande et al, 2010) and multivariate regression (Friston, 1994; for a review, see Craddock et al, 2015). …”