Objective Recognition of Tinnitus Location Using Electroencephalography Connectivity Features.

Zhaobo Li,Jimin Hu,Shiming Yang,Yalun Zhang,Bing Zhang,Haibing Xin,Xihua Li,David Y Zhao,Juan Liu,Xinzui Wang,Houyong Cai,Pengfei Li,Dawei Wang,Weidong Shen,Yueqing Liang

doi:10.3389/fnins.2021.784721

Abstract

Purpose: Tinnitus is a common but obscure auditory disease to be studied. This study will determine whether the connectivity features in electroencephalography (EEG) signals can be used as the biomarkers for an efficient and fast diagnosis method for chronic tinnitus.Methods: In this study, the resting-state EEG signals of tinnitus patients with different tinnitus locations were recorded. Four connectivity features [including the Phase-locking value (PLV), Phase lag index (PLI), Pearson correlation coefficient (PCC), and Transfer entropy (TE)] and two time-frequency domain features in the EEG signals were extracted, and four machine learning algorithms, included two support vector machine models (SVM), a multi-layer perception network (MLP) and a convolutional neural network (CNN), were used based on the selected features to classify different possible tinnitus sources.Results: Classification accuracy was highest when the SVM algorithm or the MLP algorithm was applied to the PCC feature sets, achieving final average classification accuracies of 99.42 or 99.1%, respectively. And based on the PLV feature, the classification result was also particularly good. And MLP ran the fastest, with an average computing time of only 4.2 s, which was more suitable than other methods when a real-time diagnosis was required.Conclusion: Connectivity features of the resting-state EEG signals could characterize the differentiation of tinnitus location. The connectivity features (PCC and PLV) were more suitable as the biomarkers for the objective diagnosing of tinnitus. And the results were helpful for clinicians in the initial diagnosis of tinnitus.

Highlights

Tinnitus refers to patient’s perception of sound in the ear without any external sound or electrical stimulation
The support vector machines (SVM)-10CV classifier based on the PCC feature shows the highest classification accuracy (99.42%), and included the PLV feature achieves an accuracy of 98.9%, at the same time, the multi-layer perception network (MLP) classifier based on the PCC feature achieves an accuracy of 99.1% and included the PLV feature achieves an accuracy of 98.7%
The classification accuracy of MLP was close to SVM, which was more suitable for real-time diagnostic evaluation

Summary

Introduction

Tinnitus refers to patient’s perception of sound in the ear without any external sound or electrical stimulation. Tinnitus is divided into subjective and objective tinnitus, and most patients report subjective tinnitus (Smit et al, 2015). There are 5–15% of people in the world who have experienced tinnitus, among them, 1–3% of tinnitus patients’ everyday life is seriously affected and need medical treatment (Tunkel et al, 2014; Gallus et al, 2015). Because tinnitus is a subjective perception for patients, its clinical detection and treatment are significant challenges (Pan et al, 2009). A multidisciplinary European guideline for tinnitus points out uniformity in the assessment and treatment of adult patients with subjective tinnitus (Cima et al, 2019). For the initial diagnosis of tinnitus, an efficient and objective method for recognizing and diagnosing tinnitus is still urgently needed

Methods

Results

Discussion

Conclusion