Discriminating Bipolar Disorder From Major Depression Based on SVM-FoBa: Efficient Feature Selection With Multimodal Brain Imaging Data

Abstract

Discriminating between bipolar disorder (BD) and major depressive disorder (MDD) is a major clinical challenge due to the absence of known biomarkers; hence a better understanding of their pathophysiology and brain alterations is urgently needed. Given the complexity, feature selection is especially important in neuroimaging applications, however, feature dimension and model understanding present serious challenges. In this study, a novel feature selection approach based on linear support vector machine with a forward-backward search strategy (SVM-FoBa) was developed and applied to structural and resting-state functional magnetic resonance imaging data collected from 21 BD, 25 MDD and 23 healthy controls. Discriminative features were drawn from both data modalities, with which the classification of BD and MDD achieved an accuracy of 92.1% (1,000 bootstrap resamples). Weight analysis of the selected features further revealed that the inferior frontal gyrus may characterize a central role in BD-MDD differentiation, in addition to the default mode network and the cerebellum. A modality-wise comparison also suggested that functional information outweighs anatomical by a large margin when classifying the two clinical disorders. This work validated the advantages of multimodal joint analysis and the effectiveness of SVM-FoBa, which has potential for use in identifying possible biomarkers for several mental disorders.

Resting-state functional network connectivity in prefrontal regions differs between unmedicated patients with bipolar and major depressive disorders

“…We observed that, compared to the MDD group, the FNC of the BD group exhibited higher FC strengths and also was characterized by more efficient topological structures based on measures obtained using graph theory at the functional-network-level in prefrontal cortex as well as at the whole-brain-level. In particular, our findings revealed that the FC strengths and corresponding graph structures which differentiate BD and MDD were mainly located in prefrontal networks including the DLPFC and VLPFC as well as ACC, which is consistent with findings in (Jie et al, 2015). Greater depressive symptom severity correlated with less interconnected structure in prefrontal cortical areas in the patients from both the BD and MDD groups.…”

Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls

“…It enables robust identification of correspondence among N diverse data types and enables one to investigate the important question of whether certain disease risk factors are shared or are distinct across multiple modalities, which can also serve as multimodal feature selection method for schizophrenia (Sui et al, 2013a, 2013b). Similarly, Jie et al adopted SVM-FoBa to classify between bipolar versus unipolar disorders by combining GM and ALFF features, achieving an accuracy of 92% This suggests that using complimentary multimodal biomarkers may be more informative and effective to discriminate brain disorders (Jie et al, 2015). …”

Machine learning in major depression: From classification to treatment outcome prediction

“…Additionally, nonimaging measures have also been used in depression . Thus, it is important to study how multimodal MRI in conjunction with nonimaging features affects prediction models of depression . Each MRI modality represents different view of the brain, and data fusion capitalizes on the strengths of each modality and their inter‐relationships in a joint analysis to unravel the pathophysiology of brain disease .…”