Tinnitus Identification based on Brain Network Analysis of EEG Functional Connectivity

Document Type : Conference Proceedings

Authors

1 Department of Medical Physics and Biomedical engineering, School of Medicine, Shahid Beheshti University of Medical Sciences (SBMU), Tehran, Iran

2 Department of Medical Physics and Biomedical engineering, School of Medicine, Tehran University of Medical Sciences (TUMS), Tehran, Iran

3 Department of Audiology, School of Rehabilitation, Shahid Beheshti University of Medical Sciences (SBMU), Tehran, Iran

4 Department of Medical Physics and Biomedical engineering, School of Medicine, Research Center for Biomedical Technology and Robotics (RCBTR), Institute of Advanced Medical Technologies (IAMT), Tehran University of Medical Sciences (TUMS), Tehran, Iran

5 Department of Medical Physics and Biomedical engineering, School of Medicine, Tehran University of Medical Sciences (TUMS), Tehran, Iran Research Center for Biomedical Technology and Robotics (RCBTR), Institute of Advanced Medical Technologies

Abstract

Introduction: Tinnitus known as a central nervous system disorder is correlated with specific oscillatory activities within auditory and non-auditory brain areas. Several studies in the past few years have revealed that in the most tinnitus cases, the response pattern of neurons in auditory system is changed due to auditory deafferentation, which leads to variation of the brain networks. According to neuroimaging studies, the human brain is assumed as an organization with the different degree of small-worldness, which is a concept in graph theory. Such organization is able to optimize the functional integration and segregation and therefore efficiently transfer the information among its different pairs of nodes.
Materials and Methods: In this paper, we introduce an approach to automatically distinguish tinnitus individuals from healthy controls based on whole-brain functional connectivity and network analysis. Eight participants with tinnitus and eight healthy individuals were included in the study. Resting state electroencephalographic (EEG) data were recorded using a 64-channel recorder. The functional connectivity analysis was applied to the EEG data using Weighted Phase Lag Index (WPLI) for various frequency bands in 2-44 Hz frequency range. The classification was performed on graph theoretical measures using support vector machine (SVM) as a robust classification method.
Results: Experimental results showed that the variations of connectivity patterns in tinnitus group were observed within the frontal, temporal and parietal regions. Further, promising classification performance was achieved with a high accuracy, sensitivity, and specificity in all frequency bands. The best classification performance was observed in the beta2 frequency band with accuracy, sensitivity, and specificity of 100%. The results demonstrate that four graph theory based network measures i.e. node strength, clustering coefficient, local efficiency and characteristic path length could successfully discriminate tinnitus from healthy group.
Conclusion: The results would be interpreted that the tinnitus network is more segregated but has weaker global efficiency compared to healthy group in high frequencies. In addition, tinnitus individuls presented lower segregation and greater integration relative to the healthy group in the theta frequency domain. As a conclusion, the tinnitus group shows a reduction of small-worldness as well as network integration in high-frequency bands. In general, our study provides substantial evidence that the tinnitus network can be successfully detected by consistent measures of the brain networks based on EEG functional connectivity.

Keywords