Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective study
Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by diverse clinical features. EEG biomarkers such as spectral power and functional connectivity have emerged as potential tools for enhancing early diagnosis and understanding of the neural processes underlying AS...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2024.1330556/full |
| _version_ | 1797347148735447040 |
|---|---|
| author | Si Yang Ke Huiwen Wu Haoqi Sun Haoqi Sun Aiqin Zhou Jianhua Liu Xiaoyun Zheng Kevin Liu Kevin Liu M. Brandon Westover M. Brandon Westover Haiqing Xu Xue-jun Kong Xue-jun Kong |
| author_facet | Si Yang Ke Huiwen Wu Haoqi Sun Haoqi Sun Aiqin Zhou Jianhua Liu Xiaoyun Zheng Kevin Liu Kevin Liu M. Brandon Westover M. Brandon Westover Haiqing Xu Xue-jun Kong Xue-jun Kong |
| author_sort | Si Yang Ke |
| collection | DOAJ |
| description | Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by diverse clinical features. EEG biomarkers such as spectral power and functional connectivity have emerged as potential tools for enhancing early diagnosis and understanding of the neural processes underlying ASD. However, existing studies yield conflicting results, necessitating a comprehensive, data-driven analysis. We conducted a retrospective cross-sectional study involving 246 children with ASD and 42 control children. EEG was collected, and diverse EEG features, including spectral power and spectral coherence were extracted. Statistical inference methods, coupled with machine learning models, were employed to identify differences in EEG features between ASD and control groups and develop classification models for diagnostic purposes. Our analysis revealed statistically significant differences in spectral coherence, particularly in gamma and beta frequency bands, indicating elevated long range functional connectivity between frontal and parietal regions in the ASD group. Machine learning models achieved modest classification performance of ROC-AUC at 0.65. While machine learning approaches offer some discriminative power classifying individuals with ASD from controls, they also indicate the need for further refinement. |
| first_indexed | 2024-03-08T11:43:29Z |
| format | Article |
| id | doaj.art-709937427735410bb97439b09ffc5898 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-03-08T11:43:29Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-709937427735410bb97439b09ffc58982024-01-25T04:25:22ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2024-01-011810.3389/fnins.2024.13305561330556Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective studySi Yang Ke0Huiwen Wu1Haoqi Sun2Haoqi Sun3Aiqin Zhou4Jianhua Liu5Xiaoyun Zheng6Kevin Liu7Kevin Liu8M. Brandon Westover9M. Brandon Westover10Haiqing Xu11Xue-jun Kong12Xue-jun Kong13Anthinoula A. Martinos Center, Massachusetts General Hospital, Charlestown, MA, United StatesHubei Maternity and Child Health Hospital, Wuhan, Hubei, ChinaAnthinoula A. Martinos Center, Massachusetts General Hospital, Charlestown, MA, United StatesDepartment of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, United StatesHubei Maternity and Child Health Hospital, Wuhan, Hubei, ChinaHuangshi Maternity and Child Health Care Hospital, Huangshi, Hubei, ChinaHubei Maternity and Child Health Hospital, Wuhan, Hubei, ChinaAnthinoula A. Martinos Center, Massachusetts General Hospital, Charlestown, MA, United StatesDepartment of Biomedical Informatics, Harvard Medical School, Boston, MA, United StatesDepartment of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, United StatesDepartment of Neurology, Massachusetts General Hospital, Boston, MA, United StatesHubei Maternity and Child Health Hospital, Wuhan, Hubei, ChinaAnthinoula A. Martinos Center, Massachusetts General Hospital, Charlestown, MA, United StatesDepartment of Psychiatry, Beth Israel Deaconess Medical Center, Beth Israel Deaconess Medical Center, Boston, MA, United StatesAutism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by diverse clinical features. EEG biomarkers such as spectral power and functional connectivity have emerged as potential tools for enhancing early diagnosis and understanding of the neural processes underlying ASD. However, existing studies yield conflicting results, necessitating a comprehensive, data-driven analysis. We conducted a retrospective cross-sectional study involving 246 children with ASD and 42 control children. EEG was collected, and diverse EEG features, including spectral power and spectral coherence were extracted. Statistical inference methods, coupled with machine learning models, were employed to identify differences in EEG features between ASD and control groups and develop classification models for diagnostic purposes. Our analysis revealed statistically significant differences in spectral coherence, particularly in gamma and beta frequency bands, indicating elevated long range functional connectivity between frontal and parietal regions in the ASD group. Machine learning models achieved modest classification performance of ROC-AUC at 0.65. While machine learning approaches offer some discriminative power classifying individuals with ASD from controls, they also indicate the need for further refinement.https://www.frontiersin.org/articles/10.3389/fnins.2024.1330556/fullautism spectrum disorderelectroencephalographymachine learningspectral powerfunctional connectivitycoherence |
| spellingShingle | Si Yang Ke Huiwen Wu Haoqi Sun Haoqi Sun Aiqin Zhou Jianhua Liu Xiaoyun Zheng Kevin Liu Kevin Liu M. Brandon Westover M. Brandon Westover Haiqing Xu Xue-jun Kong Xue-jun Kong Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective study Frontiers in Neuroscience autism spectrum disorder electroencephalography machine learning spectral power functional connectivity coherence |
| title | Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective study |
| title_full | Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective study |
| title_fullStr | Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective study |
| title_full_unstemmed | Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective study |
| title_short | Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective study |
| title_sort | classification of autism spectrum disorder using electroencephalography in chinese children a cross sectional retrospective study |
| topic | autism spectrum disorder electroencephalography machine learning spectral power functional connectivity coherence |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2024.1330556/full |
| work_keys_str_mv | AT siyangke classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT huiwenwu classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT haoqisun classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT haoqisun classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT aiqinzhou classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT jianhualiu classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT xiaoyunzheng classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT kevinliu classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT kevinliu classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT mbrandonwestover classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT mbrandonwestover classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT haiqingxu classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT xuejunkong classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy AT xuejunkong classificationofautismspectrumdisorderusingelectroencephalographyinchinesechildrenacrosssectionalretrospectivestudy |