Biclustered Independent Component Analysis for Complex Biomarker and Subtype Identification from Structural Magnetic Resonance Images in Schizophrenia

Abstract

Clinical and cognitive symptoms domain-based subtyping in schizophrenia (Sz) has been critiqued due to the lack of neurobiological correlates and heterogeneity in symptom scores. We, therefore, present a novel data-driven framework using biclustered independent component analysis to detect subtypes from the reliable and stable gray matter concentration (GMC) of patients with Sz. The developed methodology consists of the following steps: source-based morphometry (SBM) decomposition, selection and sorting of two component loadings, subtype component reconstruction using group information-guided ICA (GIG-ICA). This framework was applied to the top two group discriminative components namely the insula/superior temporal gyrus/inferior frontal gyrus (I-STG-IFG component) and the superior frontal gyrus/middle frontal gyrus/medial frontal gyrus (SFG-MiFG-MFG component) from our previous SBM study, which showed diagnostic group difference and had the highest effect sizes. The aggregated multisite dataset consisted of 382 patients with Sz regressed of age, gender, and site voxelwise. We observed two subtypes (i.e., two different subsets of subjects) each heavily weighted on these two components, respectively. These subsets of subjects were characterized by significant differences in positive and negative syndrome scale (PANSS) positive clinical symptoms (p = 0.005). We also observed an overlapping subtype weighing heavily on both of these components. The PANSS general clinical symptom of this subtype was trend level correlated with the loading coefficients of the SFG-MiFG-MFG component (r = 0.25; p = 0.07). The reconstructed subtype-specific component using GIG-ICA showed variations in voxel regions, when compared to the group component. We observed deviations from mean GMC along with conjunction of features from two components characterizing each deciphered subtype. These inherent variations in GMC among patients with Sz could possibly indicate the need for personalized treatment and targeted drug development.

Keywords: biclustering; gray matter concentration; group information-guided independent component analysis; independent component analysis; positive and negative syndrome scale symptoms; subtypes.

Figure 1

Biclustered Independent Component Analysis (B-ICA) framework illustrating the various steps to decipher subtypes.

Figure 2

First row: group components for 382 schizophrenia subjects (column one is insula/superior temporal gyrus/inferior frontal gyrus component while column two is superior frontal gyrus/middle frontal gyrus/medial frontal gyrus component). Subtype-specific components were reconstructed using biclustered independent component analysis and group information-guided ICA. Second row: S₁ subtype components (65 subjects), third row: S₂ subtype components (62 subjects), fourth row: S_inter subtype components (53 subjects). All components were thresholded at |z| > 2.5 and cross hairs indicate the maximum voxel.

Figure 3

Scatter plots for subtypes S₁, S₂, S_inter I-STG-IFG component loadings Vs PP.

Figure 4

Scatter plot for subtypes S₁, S₂, S_inter SFG-MiFG-MFG component loadings Vs PP.

Figure 5

Bird’s eye view of the subtype associations with positive and negative syndrome scale clinical symptoms obtained using biclustered independent component analysis.