Altered brainstem-cortex activation and interaction in migraine patients: somatosensory evoked EEG responses with machine learning.

IF 7.3 1区 医学 Q1 CLINICAL NEUROLOGY
Fu-Jung Hsiao, Wei-Ta Chen, Hung-Yu Liu, Yu-Te Wu, Yen-Feng Wang, Li-Ling Hope Pan, Kuan-Lin Lai, Shih-Pin Chen, Gianluca Coppola, Shuu-Jiun Wang
{"title":"Altered brainstem-cortex activation and interaction in migraine patients: somatosensory evoked EEG responses with machine learning.","authors":"Fu-Jung Hsiao, Wei-Ta Chen, Hung-Yu Liu, Yu-Te Wu, Yen-Feng Wang, Li-Ling Hope Pan, Kuan-Lin Lai, Shih-Pin Chen, Gianluca Coppola, Shuu-Jiun Wang","doi":"10.1186/s10194-024-01892-2","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>To gain a comprehensive understanding of the altered sensory processing in patients with migraine, in this study, we developed an electroencephalography (EEG) protocol for examining brainstem and cortical responses to sensory stimulation. Furthermore, machine learning techniques were employed to identify neural signatures from evoked brainstem-cortex activation and their interactions, facilitating the identification of the presence and subtype of migraine.</p><p><strong>Methods: </strong>This study analysed 1,000-epoch-averaged somatosensory evoked responses from 342 participants, comprising 113 healthy controls (HCs), 106 patients with chronic migraine (CM), and 123 patients with episodic migraine (EM). Activation amplitude and effective connectivity were obtained using weighted minimum norm estimates with spectral Granger causality analysis. This study used support vector machine algorithms to develop classification models; multimodal data (amplitude, connectivity, and scores of psychometric assessments) were applied to assess the reliability and generalisability of the identification results from the classification models.</p><p><strong>Results: </strong>The findings revealed that patients with migraine exhibited reduced amplitudes for responses in both the brainstem and cortical regions and increased effective connectivity between these regions in the gamma and high-gamma frequency bands. The classification model with characteristic features performed well in distinguishing patients with CM from HCs, achieving an accuracy of 81.8% and an area under the curve (AUC) of 0.86 during training and an accuracy of 76.2% and an AUC of 0.89 during independent testing. Similarly, the model effectively identified patients with EM, with an accuracy of 77.5% and an AUC of 0.84 during training and an accuracy of 87% and an AUC of 0.88 during independent testing. Additionally, the model successfully differentiated patients with CM from patients with EM, with an accuracy of 70.5% and an AUC of 0.73 during training and an accuracy of 72.7% and an AUC of 0.74 during independent testing.</p><p><strong>Conclusion: </strong>Altered brainstem-cortex activation and interaction are characteristic of the abnormal sensory processing in migraine. Combining evoked activity analysis with machine learning offers a reliable and generalisable tool for identifying patients with migraine and for assessing the severity of their condition. Thus, this approach is an effective and rapid diagnostic tool for clinicians.</p>","PeriodicalId":16013,"journal":{"name":"Journal of Headache and Pain","volume":null,"pages":null},"PeriodicalIF":7.3000,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11514809/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Headache and Pain","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s10194-024-01892-2","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Background: To gain a comprehensive understanding of the altered sensory processing in patients with migraine, in this study, we developed an electroencephalography (EEG) protocol for examining brainstem and cortical responses to sensory stimulation. Furthermore, machine learning techniques were employed to identify neural signatures from evoked brainstem-cortex activation and their interactions, facilitating the identification of the presence and subtype of migraine.

Methods: This study analysed 1,000-epoch-averaged somatosensory evoked responses from 342 participants, comprising 113 healthy controls (HCs), 106 patients with chronic migraine (CM), and 123 patients with episodic migraine (EM). Activation amplitude and effective connectivity were obtained using weighted minimum norm estimates with spectral Granger causality analysis. This study used support vector machine algorithms to develop classification models; multimodal data (amplitude, connectivity, and scores of psychometric assessments) were applied to assess the reliability and generalisability of the identification results from the classification models.

Results: The findings revealed that patients with migraine exhibited reduced amplitudes for responses in both the brainstem and cortical regions and increased effective connectivity between these regions in the gamma and high-gamma frequency bands. The classification model with characteristic features performed well in distinguishing patients with CM from HCs, achieving an accuracy of 81.8% and an area under the curve (AUC) of 0.86 during training and an accuracy of 76.2% and an AUC of 0.89 during independent testing. Similarly, the model effectively identified patients with EM, with an accuracy of 77.5% and an AUC of 0.84 during training and an accuracy of 87% and an AUC of 0.88 during independent testing. Additionally, the model successfully differentiated patients with CM from patients with EM, with an accuracy of 70.5% and an AUC of 0.73 during training and an accuracy of 72.7% and an AUC of 0.74 during independent testing.

Conclusion: Altered brainstem-cortex activation and interaction are characteristic of the abnormal sensory processing in migraine. Combining evoked activity analysis with machine learning offers a reliable and generalisable tool for identifying patients with migraine and for assessing the severity of their condition. Thus, this approach is an effective and rapid diagnostic tool for clinicians.

偏头痛患者脑干-皮层激活和相互作用的改变:利用机器学习的体感诱发脑电图反应。
背景:为了全面了解偏头痛患者感觉处理过程的改变,我们在本研究中开发了一种脑电图(EEG)方案,用于检查脑干和皮层对感觉刺激的反应。此外,我们还利用机器学习技术从诱发的脑干-皮层激活及其相互作用中识别神经特征,从而帮助识别偏头痛的存在和亚型:这项研究分析了342名参与者的1000个时序平均体感诱发反应,其中包括113名健康对照组(HC)、106名慢性偏头痛患者(CM)和123名发作性偏头痛患者(EM)。利用加权最小规范估计和频谱格兰杰因果关系分析获得了激活振幅和有效连通性。该研究使用支持向量机算法开发分类模型;应用多模态数据(振幅、连通性和心理测评得分)评估分类模型识别结果的可靠性和通用性:研究结果表明,偏头痛患者脑干和皮质区域的反应振幅减小,而这些区域之间在伽马和高伽马频段的有效连接性增强。带有特征性特征的分类模型在区分偏头痛患者和脑干性偏头痛患者方面表现良好,在训练过程中准确率达到 81.8%,曲线下面积(AUC)为 0.86;在独立测试过程中准确率达到 76.2%,曲线下面积(AUC)为 0.89。同样,该模型也能有效识别出 EM 患者,训练期间的准确率为 77.5%,AUC 为 0.84;独立测试期间的准确率为 87%,AUC 为 0.88。此外,该模型还成功地将 CM 患者与 EM 患者区分开来,训练期间的准确率为 70.5%,AUC 为 0.73;独立测试期间的准确率为 72.7%,AUC 为 0.74:结论:脑干-皮层激活和相互作用的改变是偏头痛患者感觉处理异常的特征。将诱发活动分析与机器学习相结合,为识别偏头痛患者和评估其病情严重程度提供了可靠、可推广的工具。因此,这种方法是临床医生有效而快速的诊断工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Headache and Pain
Journal of Headache and Pain 医学-临床神经学
CiteScore
11.80
自引率
13.50%
发文量
143
审稿时长
6-12 weeks
期刊介绍: The Journal of Headache and Pain, a peer-reviewed open-access journal published under the BMC brand, a part of Springer Nature, is dedicated to researchers engaged in all facets of headache and related pain syndromes. It encompasses epidemiology, public health, basic science, translational medicine, clinical trials, and real-world data. With a multidisciplinary approach, The Journal of Headache and Pain addresses headache medicine and related pain syndromes across all medical disciplines. It particularly encourages submissions in clinical, translational, and basic science fields, focusing on pain management, genetics, neurology, and internal medicine. The journal publishes research articles, reviews, letters to the Editor, as well as consensus articles and guidelines, aimed at promoting best practices in managing patients with headaches and related pain.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信