Piarulli Andrea, Vanneste Sven, Nemirovsky Idan Efim, Kandeepan Sivayini, Maudoux Audrey, Gemignani Angelo, De Ridder Dirk, Soddu Andrea
Department of Surgical, Medical and Molecular Pathology and Critical Care Medicine, University of Pisa, Pisa 56124, Italy.
Trinity College Institute for Neuroscience & School of Psychology, Trinity College, Dublin D02 PN40, Ireland.
Brain Commun. 2023 Feb 1;5(1):fcad018. doi: 10.1093/braincomms/fcad018. eCollection 2023.
There exist no objective markers for tinnitus or tinnitus disorders, which complicates diagnosis and treatments. The combination of EEG with sophisticated classification procedures may reveal biomarkers that can identify tinnitus and accurately differentiate different levels of distress experienced by patients. EEG recordings were obtained from 129 tinnitus patients and 142 healthy controls. Linear support vector machines were used to develop two classifiers: the first differentiated tinnitus patients from controls, while the second differentiated tinnitus patients with low and high distress levels. The classifier for healthy controls and tinnitus patients performed with an average accuracy of 96 and 94% for the training and test sets, respectively. For the distress classifier, these average accuracies were 89 and 84%. Minimal overlap was observed between the features of the two classifiers. EEG-derived features made it possible to accurately differentiate healthy controls and tinnitus patients as well as low and high distress tinnitus patients. The minimal overlap between the features of the two classifiers indicates that the source of distress in tinnitus, which could also be involved in distress related to other conditions, stems from different neuronal mechanisms compared to those causing the tinnitus pathology itself.
耳鸣或耳鸣障碍不存在客观标志物，这使得诊断和治疗变得复杂。脑电图（EEG）与复杂分类程序相结合可能会揭示出可识别耳鸣并准确区分患者所经历的不同痛苦程度的生物标志物。从129名耳鸣患者和142名健康对照者身上获取了脑电图记录。使用线性支持向量机开发了两个分类器：第一个将耳鸣患者与对照者区分开来，第二个将痛苦程度低和高的耳鸣患者区分开来。健康对照者和耳鸣患者的分类器在训练集和测试集上的平均准确率分别为96%和94%。对于痛苦程度分类器，这些平均准确率分别为89%和84%。两个分类器的特征之间观察到最小重叠。脑电图衍生特征能够准确区分健康对照者和耳鸣患者以及痛苦程度低和高的耳鸣患者。两个分类器特征之间的最小重叠表明，耳鸣中痛苦的来源，这也可能与其他病症相关的痛苦有关，与导致耳鸣病理本身的神经元机制不同。
