Granger causality analysis in combination with directed network measures for classification of MS patients and healthy controls using task-related fMRI. (December 2019)

• Record Type: Journal Article
• Authors: Azarmi, Farzad; Miri Ashtiani, Seyedeh Naghmeh; Shalbaf, Ahmad; Behnam, Hamid; Daliri, Mohammad Reza
• Is Part Of: Computers in biology and medicine. Volume 115(2019)
• Publication Date: 2019-12
• Subjects: fMRI -- Effective connectivity -- Brain network -- PASAT -- Machine learning -- Support vector machine; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2019.103495
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Several studies have already assessed brain network variations in multiple sclerosis (MS) patients and healthy controls (HCs). The underlying neural system's functioning is apparently too complicated, however. Therefore, the neural time series' analysis through new methods is the aim of any recent research. Functional magnetic resonance imaging (fMRI) is a prominent modality for investigating the human brain's neural substrate, especially when cognitive impairment occurs. The present study was an attempt to investigate the brain network's differences between MS patients and HCs using graph-theoretic measures constructed by an effective connectivity measure through statistical tests. The results of the significant measures were then evaluated through machine learning methods. To this end, we gathered blood-oxygen level dependent (BOLD) fMRI data of the participants during the execution of paced auditory serial addition test (PASAT). Granger causality analysis (GCA) was then employed between brain regions' time series on each subject in order to construct a brain network. Afterward, the Wilcoxon rank-sum test was implemented to find the alteration of brain networks between the mentioned groups. According to the results, Global flow coefficient was significantly different between HCs and patients. Moreover, MS disease impacted several areas of the brain including Hippocampus, Para Hippocampal, Thalamus, Cuneus, Superior temporal gyrus, Heschl, Caudate, Medial Frontal Superior Gyrus, Fusiform, Pallidum, and several parts of Cerebellum in centrality measures and local flow coefficient. Most of the obtained regions were related to the cognitive impacts of the disease. We also found the best subset of graph features by means of Fisher score, and classified them to evaluate the features strength for the discrimination of MS patients from HCs via several machine learning methods. Having used the combination of Wilcoxon rank-sum test and Fisher score, we were able to classify MS patients from HCs using linear support vector machine (SVM) with an accuracy of 95%. With regard to the few existing studies on brain network of MS patients, especially during a cognitive task execution, our findings showed that the selected graph measures by Wilcoxon rank-sum test and Fisher score from the GCA-based brain networks resulted in a promising classification accuracy.