1
|
Zhao S, Dai G, Li J, Zhu X, Huang X, Li Y, Tan M, Wang L, Fang P, Chen X, Yan N, Liu H. An interpretable model based on graph learning for diagnosis of Parkinson's disease with voice-related EEG. NPJ Digit Med 2024; 7:3. [PMID: 38182737 PMCID: PMC10770376 DOI: 10.1038/s41746-023-00983-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Accepted: 11/29/2023] [Indexed: 01/07/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Shuzhi Zhao
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
- School of Biomedical Engineering, Sun Yat-sen University, Shenzhen, China
- CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Guangyan Dai
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Jingting Li
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Xiaoxia Zhu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Xiyan Huang
- Department of Rehabilitation Medicine, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Yongxue Li
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Mingdan Tan
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Lan Wang
- CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
- Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Peng Fang
- CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
- Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Xi Chen
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
| | - Nan Yan
- CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
- Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
| | - Hanjun Liu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
- Guangdong Provincial Key Laboratory of Brain Function and Disease, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China.
| |
Collapse
|
2
|
Liu D, Chang Y, Dai G, Guo Z, Jones JA, Li T, Chen X, Chen M, Li J, Wu X, Liu P, Liu H. Right, but not left, posterior superior temporal gyrus is causally involved in vocal feedback control. Neuroimage 2023; 278:120282. [PMID: 37468021 DOI: 10.1016/j.neuroimage.2023.120282] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Revised: 06/25/2023] [Accepted: 07/16/2023] [Indexed: 07/21/2023] Open
Abstract
The posterior superior temporal gyrus (pSTG) has been implicated in the integration of auditory feedback and motor system for controlling vocal production. However, the question as to whether and how the pSTG is causally involved in vocal feedback control is currently unclear. To this end, the present study selectively stimulated the left or right pSTG with continuous theta burst stimulation (c-TBS) in healthy participants, then used event-related potentials to investigate neurobehavioral changes in response to altered auditory feedback during vocal pitch regulation. The results showed that, compared to control (vertex) stimulation, c-TBS over the right pSTG led to smaller vocal compensations for pitch perturbations accompanied by smaller cortical N1 and larger P2 responses. Enhanced P2 responses received contributions from the right-lateralized temporal and parietal regions as well as the insula, and were significantly correlated with suppressed vocal compensations. Surprisingly, these effects were not found when comparing c-TBS over the left pSTG with control stimulation. Our findings provide evidence, for the first time, that supports a causal relationship between right, but not left, pSTG and auditory-motor integration for vocal pitch regulation. This lends support to a right-lateralized contribution of the pSTG in not only the bottom-up detection of vocal feedback errors but also the involvement of driving motor commands for error correction in a top-down manner.
Collapse
Affiliation(s)
- Dongxu Liu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Yichen Chang
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Guangyan Dai
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Zhiqiang Guo
- School of Computer, Zhuhai College of Science and Technology, Zhuhai, China
| | - Jeffery A Jones
- Department of Psychology and Laurier Centre for Cognitive Neuroscience, Wilfrid Laurier University, Waterloo, Ontario N2L 3C5, Canada
| | - Tingni Li
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China; Centre for Eye and Vision Research, 17W Science Park, Hong Kong SAR, China
| | - Xi Chen
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Mingyun Chen
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Jingting Li
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Xiuqin Wu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
| | - Peng Liu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
| | - Hanjun Liu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China; Guangdong Provincial Key Laboratory of Brain Function and Disease, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China.
| |
Collapse
|
3
|
Zhu X, Dai G, Wang M, Tan M, Li Y, Xu Z, Lei D, Chen L, Chen X, Liu H. Continuous theta burst stimulation over right cerebellum for speech impairment in Parkinson's disease: study protocol for a randomized, sham-controlled, clinical trial. Front Aging Neurosci 2023; 15:1215330. [PMID: 37655339 PMCID: PMC10465698 DOI: 10.3389/fnagi.2023.1215330] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Accepted: 08/03/2023] [Indexed: 09/02/2023] Open
Abstract
Background Speech impairment is a common symptom of Parkinson's disease (PD) that worsens with disease progression and affects communication and quality of life. Current pharmacological and surgical treatments for PD have inconsistent effects on speech impairment. The cerebellum is an essential part of sensorimotor network that regulates speech production and becomes dysfunctional in PD. Continuous theta-burst stimulation (cTBS) is a non-invasive brain stimulation technique that can modulate the cerebellum and its connections with other brain regions. Objective To investigate whether cTBS over the right cerebellum coupled with speech-language therapy (SLT) can improve speech impairment in PD. Methods In this randomized controlled trial (RCT), 40 patients with PD will be recruited and assigned to either an experimental group (EG) or a control group (CG). Both groups will receive 10 sessions of standard SLT. The EG will receive real cTBS over the right cerebellum, while the CG will receive sham stimulation. Blinded assessors will evaluate the treatment outcome at three time points: pre-intervention, post-intervention, and at a 12-week follow-up. The primary outcome measures are voice/speech quality and neurobehavioral parameters of auditory-vocal integration. The secondary outcome measures are cognitive function, quality of life, and functional connectivity determined by resting-state functional magnetic resonance imaging (fMRI). Significance This trial will provide evidence for the efficacy and safety of cerebellar cTBS for the treatment of speech impairment in PD and shed light on the neural mechanism of this intervention. It will also have implications for other speech impairment attributed to cerebellar dysfunctions. Clinical trial registration www.chictr.org.cn, identifier ChiCTR2100050543.
Collapse
Affiliation(s)
- Xiaoxia Zhu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Guangyan Dai
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Meng Wang
- Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Mingdan Tan
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Yongxue Li
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Zhiqin Xu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Di Lei
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Ling Chen
- Department of Neurology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Xi Chen
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Hanjun Liu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Brain Function and Disease, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
| |
Collapse
|
4
|
Hu H, Li J, He S, Zhao Y, Liu P, Liu H. Aging-related decline in the neuromotor control of speech production: current and future. Front Aging Neurosci 2023; 15:1172277. [PMID: 37151845 PMCID: PMC10156980 DOI: 10.3389/fnagi.2023.1172277] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2023] [Accepted: 04/05/2023] [Indexed: 05/09/2023] Open
Affiliation(s)
- Huijing Hu
- Institute of Medical Research, Northwestern Polytechnical University, Xi'an, China
| | - Jingting Li
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Sixuan He
- Institute of Medical Research, Northwestern Polytechnical University, Xi'an, China
| | - Yan Zhao
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Peng Liu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
| | - Hanjun Liu
- Department of Rehabilitation Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Brain Function and Disease, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
- *Correspondence: Hanjun Liu
| |
Collapse
|
5
|
Li T, Chang Y, Zhao S, Jones JA, Chen X, Gan C, Wu X, Dai G, Li J, Shen Y, Liu P, Liu H. The left inferior frontal gyrus is causally linked to vocal feedback control: evidence from high-definition transcranial alternating current stimulation. Cereb Cortex 2022; 33:5625-5635. [PMID: 36376991 DOI: 10.1093/cercor/bhac447] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2022] [Revised: 10/18/2022] [Accepted: 10/19/2022] [Indexed: 11/16/2022] Open
Abstract
Abstract
Current models of speech motor control propose a role for the left inferior frontal gyrus (IFG) in feedforward control of speech production. There is evidence, however, that has implicated the functional relevance of the left IFG for the neuromotor processing of vocal feedback errors. The present event-related potential (ERP) study examined whether the left IFG is causally linked to auditory feedback control of vocal production with high-definition transcranial alternating current stimulation (HD-tACS). After receiving active or sham HD-tACS over the left IFG at 6 or 70 Hz, 20 healthy adults vocalized the vowel sounds while hearing their voice unexpectedly pitch-shifted by ±200 cents. The results showed that 6 or 70 Hz HD-tACS over the left IFG led to larger magnitudes and longer latencies of vocal compensations for pitch perturbations paralleled by larger ERP P2 responses than sham HD-tACS. Moreover, there was a lack of frequency specificity that showed no significant differences between 6 and 70 Hz HD-tACS. These findings provide first causal evidence linking the left IFG to vocal pitch regulation, suggesting that the left IFG is an important part of the feedback control network that mediates vocal compensations for auditory feedback errors.
Collapse
Affiliation(s)
- Tingni Li
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
| | - Yichen Chang
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
| | - Shuzhi Zhao
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
| | - Jeffery A Jones
- Wilfrid Laurier University Psychology Department and Laurier Centre for Cognitive Neuroscience, , Waterloo, Ontario N2L 3C5 , Canada
| | - Xi Chen
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
| | - Chu Gan
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
| | - Xiuqin Wu
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
| | - Guangyan Dai
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
| | - Jingting Li
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
| | - Ying Shen
- The First Affiliated Hospital of Nanjing Medical University Rehabilitation Medicine Center, , Nanjing 210029 , China
| | - Peng Liu
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
| | - Hanjun Liu
- The First Affiliated Hospital, Sun Yat-sen University Department of Rehabilitation Medicine, , Guangzhou 510080 , China
- Zhongshan School of Medicine, Sun Yat-sen University Guangdong Provincial Key Laboratory of Brain Function and Disease, , Guangzhou 510080 , China
| |
Collapse
|