An interpretable model based on graph learning for diagnosis of Parkinson's disease with voice-related EEG.
An interpretable model based on graph learning for diagnosis of Parkinson's disease with voice-related EEG.
复制标题
基于图形学习的语音相关脑电帕金森病可解释模型。
DOI：
10.1038/s41746-023-00983-9
复制
发表时间：
2024-01-05
影响因子：
15.2
通讯作者：
中科院分区：
文献类型：
--
作者：
帕金森病 (PD) 表现出显着的临床异质性，给识别可靠的脑电图 (EEG) 生物标志物带来了挑战。机器学习技术已与静息态脑电图相结合用于帕金森病诊断，但其实用性受到静息态脑电图的可解释特征和随机性的限制。本研究提出了一种新颖且可解释的深度学习模型，即图信号处理图卷积网络（GSP-GCN），该模型使用从涉及音高调节的特定任务中获得的事件相关脑电图数据来进行 PD 诊断。通过结合来自单跳和多跳网络的本地和全局信息，我们提出的 GSP-GCN 模型实现了 90.2% 的平均分类精度，比其他深度学习模型显着提高了 9.5%。此外，可解释性分析揭示了我们的模型学习到的大规模脑电图网络和微状态 MS5 的地形图的判别性分布，主要位于与 PD 相关的言语障碍有关的左腹侧前运动皮层、颞上回和布罗卡区，这反映了我们的 GSP-GCN 模型能够提供可解释的见解，从大规模网络中识别独特的脑电图生物标志物。这些发现证明了可解释的深度学习模型与声音相关的脑电图信号相结合的潜力，可以准确地区分帕金森病患者与健康对照，并阐明潜在的神经生物学机制。
Parkinson’s disease (PD) exhibits significant clinical heterogeneity, presenting challenges in the identification of reliable electroencephalogram (EEG) biomarkers. Machine learning techniques have been integrated with resting-state EEG for PD diagnosis, but their practicality is constrained by the interpretable features and the stochastic nature of resting-state EEG. The present study proposes a novel and interpretable deep learning model, graph signal processing-graph convolutional networks (GSP-GCNs), using event-related EEG data obtained from a specific task involving vocal pitch regulation for PD diagnosis. By incorporating both local and global information from single-hop and multi-hop networks, our proposed GSP-GCNs models achieved an averaged classification accuracy of 90.2%, exhibiting a significant improvement of 9.5% over other deep learning models. Moreover, the interpretability analysis revealed discriminative distributions of large-scale EEG networks and topographic map of microstate MS5 learned by our models, primarily located in the left ventral premotor cortex, superior temporal gyrus, and Broca’s area that are implicated in PD-related speech disorders, reflecting our GSP-GCN models’ ability to provide interpretable insights identifying distinctive EEG biomarkers from large-scale networks. These findings demonstrate the potential of interpretable deep learning models coupled with voice-related EEG signals for distinguishing PD patients from healthy controls with accuracy and elucidating the underlying neurobiological mechanisms.
登录
查看更多内容
影响因子：
5.7
作者：
Behroozmand R;Shebek R;Hansen DR;Oya H;Robin DA;Howard MA 3rd;Greenlee JD
通讯作者：
Greenlee JD
影响因子：
4.8
作者：
通讯作者：
--
影响因子：
11
作者：
HUGHES, AJ;DANIEL, SE;LEES, AJ
通讯作者：
LEES, AJ
帕金森氏病的遗传结构。
DOI：
10.1016/s1474-4422(19)30287-x
发表时间：
2020-02
期刊：
The Lancet. Neurology
影响因子：
--
作者：
Blauwendraat C;Nalls MA;Singleton AB
通讯作者：
Singleton AB
影响因子：
2.7
作者：
Jouen AL;Lancheros M;Laganaro M
通讯作者：
Laganaro M