Raeisi Zahra, Sodagartojgi Abolfazl, Sharafkhani Fahimeh, Roshanzamir Amirsadegh, Najafzadeh Hossein, Bashiri Omid, Golkarieh Alireza
Department of Computer Science, University of Fairleigh Dickinson, Vancouver Campus, Vancouver, Canada.
Department of Statistics, Rutgers University, New Brunswick, NJ, USA.
Sci Rep. 2025 May 7;15(1):15959. doi: 10.1038/s41598-025-01129-5.
This study aims to deepen the understanding and classification of tinnitus through a comprehensive analysis of EEG signals utilizing innovative microstate analysis techniques and cutting-edge machine learning approaches. EEG data were collected from two datasets: a primary dataset with 36 participants (16 healthy, 20 tinnitus) and a public dataset with 37 participants (15 healthy, 22 tinnitus). Signals were decomposed into five frequency bands (delta, theta, alpha, beta, gamma) using Daubechies 4 wavelet at five decomposition levels. Microstate features (Duration, Occurrence, Mean Global Field Power, and Coverage) were extracted across four microstate configurations (4-state to 7-state) under both eyes-closed and eyes-open conditions. Classification was performed using SVM, Decision Tree, Random Forest, and Deep Neural Networks. Additionally, pre-trained models (VGG16, ResNet50, Xception) were used with a novel feature-to-image transformation approach for validation. Analysis revealed significant alterations in beta band microstates, with microstate A showing increased duration (+ 7.8% to + 11.2%) and microstate B showing decreased duration (- 9.0% to - 13.8%) in tinnitus patients. Occurrence rates were markedly elevated (~ 28-29% higher) in the tinnitus group. Transition probability analysis identified distinctive patterns between groups, with the most pronounced differences observed in gamma band (6-state configuration) during eyes-closed condition (healthy: F → B = 0.143; tinnitus: C → D = 0.153) and beta band (7-state configuration) also during eyes-closed condition (healthy: E → A = 0.091; tinnitus: C → E = 0.082). In the eyes-open condition, gamma band with 7 microstates showed substantial differences in transition patterns (healthy: E → A = 0.149; tinnitus: C → G = 0.157). Classification performance was exceptional, with DNN achieving 100% accuracy in the gamma frequency band during eyes-open condition with 5-state configuration. Frequency band analysis demonstrated that gamma band performed best for open eyes (99.89% accuracy) and beta band excelled for closed eyes (96.46% accuracy). Validation with pre-trained models showed ResNet50 with SVM classifier using 6-state configurations provided optimal discrimination (100% accuracy). EEG microstate dynamics in beta and gamma bands serve as reliable markers for distinguishing tinnitus patients. These findings provide insights into tinnitus-related neural alterations and highlight microstate analysis as a potential objective diagnostic tool for guiding personalized neuromodulation therapies.
本研究旨在通过利用创新的微状态分析技术和前沿的机器学习方法对脑电图（EEG）信号进行全面分析，加深对耳鸣的理解和分类。EEG数据来自两个数据集：一个主要数据集有36名参与者（16名健康者，20名耳鸣患者），一个公共数据集有37名参与者（15名健康者，22名耳鸣患者）。使用Daubechies 4小波在五个分解级别将信号分解为五个频段（δ、θ、α、β、γ）。在闭眼和睁眼条件下，跨四种微状态配置（4状态至7状态）提取微状态特征（持续时间、出现率、平均全局场功率和覆盖率）。使用支持向量机（SVM）、决策树、随机森林和深度神经网络进行分类。此外，预训练模型（VGG16、ResNet50、Xception）与一种新颖的特征到图像转换方法一起用于验证。分析显示，耳鸣患者β频段微状态有显著变化，微状态A的持续时间增加（+7.8%至+11.2%），微状态B的持续时间减少（-9.0%至-13.8%）。耳鸣组的出现率明显升高（高出约28 - 29%）。转移概率分析确定了两组之间的独特模式，在闭眼条件下，γ频段（6状态配置）观察到最明显的差异（健康者：F→B = 0.143；耳鸣患者：C→D = 0.153），β频段（7状态配置）在闭眼条件下也有差异（健康者：E→A = 0.091；耳鸣患者：C→E = 0.082）。在睁眼条件下，具有7个微状态的γ频段在转移模式上有显著差异（健康者：E→A = 0.149；耳鸣患者：C→G = 0.157）。分类性能出色，在睁眼条件下5状态配置时，深度神经网络在γ频段的准确率达到100%。频段分析表明，γ频段在睁眼时表现最佳（准确率99.89%），β频段在闭眼时表现出色（准确率96.46%）。使用预训练模型进行验证表明，采用6状态配置的ResNet50与SVM分类器提供了最佳区分效果（准确率100%）。β和γ频段的EEG微状态动力学可作为区分耳鸣患者的可靠标志物。这些发现为耳鸣相关的神经改变提供了见解，并突出了微状态分析作为指导个性化神经调节治疗的潜在客观诊断工具。
