Attention-based multi-scale convolution and conformer for EEG-based depression detection

Depression is a common mental health issue, and early detection is crucial for timely intervention. This study proposes an end-to-end EEG-based depression recognition model, AMCCBDep, which combines Attention-based Multi-scale Parallel Convolution (AMPC), Conformer, and Bidirectional Gated Recurrent...

Full description

Saved in:
Bibliographic Details
Main Authors: Ze Yan, Yumei Wan, Xin Pu, Xiaolin Han, Mingming Zhao, Haiyan Wu, Wentao Li, Xueying He, Yunshao Zheng
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Psychiatry
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1584474/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849707444495712256
author Ze Yan
Ze Yan
Ze Yan
Yumei Wan
Xin Pu
Xiaolin Han
Mingming Zhao
Haiyan Wu
Wentao Li
Xueying He
Yunshao Zheng
author_facet Ze Yan
Ze Yan
Ze Yan
Yumei Wan
Xin Pu
Xiaolin Han
Mingming Zhao
Haiyan Wu
Wentao Li
Xueying He
Yunshao Zheng
author_sort Ze Yan
collection DOAJ
description Depression is a common mental health issue, and early detection is crucial for timely intervention. This study proposes an end-to-end EEG-based depression recognition model, AMCCBDep, which combines Attention-based Multi-scale Parallel Convolution (AMPC), Conformer, and Bidirectional Gated Recurrent Unit (BiGRU). The AMPC module captures temporal features through multiscale convolutions and extracts spatial features using depthwise separable convolutions, while applying the ECA attention mechanism to weigh key channels, enhancing the model’s focus on crucial electrode channels. The Conformer module further captures both global and local temporal dependencies in EEG signals to ensure the capture of long-range dependencies and local patterns. The BiGRU module improves the model’s ability to recognize depressive states by utilizing bidirectional modeling. We used the 128-channel resting-state EEG signals from the MODMA dataset, which includes data from 24 depression patients (13 males, 11 females, aged 16 to 56) and 29 healthy individuals (20 males, 9 females, aged 18 to 55). Experimental results show that the AMCCBDep model achieved an accuracy of 98.68% ± 0.45% on the MODMA dataset. The model evaluation results for both 128-channel and 16-channel configurations demonstrate that reducing the number of electrodes has a minimal impact on performance, suggesting that electrode reduction could be considered in practical applications. This model showcases strong potential in advancing depression detection in neuroscience, providing an efficient and scalable solution for clinical and practical applications. Future research will further optimize model performance and explore the impact of reducing the number of electrodes on clinical practice.
format Article
id doaj-art-e209dbd3f83749089a011aabc636b5d2
institution DOAJ
issn 1664-0640
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Psychiatry
spelling doaj-art-e209dbd3f83749089a011aabc636b5d22025-08-20T03:15:54ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402025-07-011610.3389/fpsyt.2025.15844741584474Attention-based multi-scale convolution and conformer for EEG-based depression detectionZe Yan0Ze Yan1Ze Yan2Yumei Wan3Xin Pu4Xiaolin Han5Mingming Zhao6Haiyan Wu7Wentao Li8Xueying He9Yunshao Zheng10Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, ChinaShandong Engineering Research Center of Big Data Applied Technology, Faculty of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, ChinaShandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Jinan, ChinaDepartment of Psychiatry, Shandong Mental Health Center, Shandong University, Jinan, ChinaDepartment of Psychiatry, Shandong Mental Health Center, Shandong University, Jinan, ChinaDepartment of Psychiatry, Shandong Mental Health Center, Shandong University, Jinan, ChinaDepartment of Psychiatry, Shandong Mental Health Center, Shandong University, Jinan, ChinaDepartment of Psychiatry, Shandong Mental Health Center, Shandong University, Jinan, ChinaDepartment of Psychiatry, Shandong Mental Health Center, Shandong University, Jinan, ChinaSchool of Medical Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, ChinaDepartment of Psychiatry, Shandong Mental Health Center, Shandong University, Jinan, ChinaDepression is a common mental health issue, and early detection is crucial for timely intervention. This study proposes an end-to-end EEG-based depression recognition model, AMCCBDep, which combines Attention-based Multi-scale Parallel Convolution (AMPC), Conformer, and Bidirectional Gated Recurrent Unit (BiGRU). The AMPC module captures temporal features through multiscale convolutions and extracts spatial features using depthwise separable convolutions, while applying the ECA attention mechanism to weigh key channels, enhancing the model’s focus on crucial electrode channels. The Conformer module further captures both global and local temporal dependencies in EEG signals to ensure the capture of long-range dependencies and local patterns. The BiGRU module improves the model’s ability to recognize depressive states by utilizing bidirectional modeling. We used the 128-channel resting-state EEG signals from the MODMA dataset, which includes data from 24 depression patients (13 males, 11 females, aged 16 to 56) and 29 healthy individuals (20 males, 9 females, aged 18 to 55). Experimental results show that the AMCCBDep model achieved an accuracy of 98.68% ± 0.45% on the MODMA dataset. The model evaluation results for both 128-channel and 16-channel configurations demonstrate that reducing the number of electrodes has a minimal impact on performance, suggesting that electrode reduction could be considered in practical applications. This model showcases strong potential in advancing depression detection in neuroscience, providing an efficient and scalable solution for clinical and practical applications. Future research will further optimize model performance and explore the impact of reducing the number of electrodes on clinical practice.https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1584474/fulldepression detectionelectroencephalography (EEG)attentiondeep learning (DL)AMCCBDep
spellingShingle Ze Yan
Ze Yan
Ze Yan
Yumei Wan
Xin Pu
Xiaolin Han
Mingming Zhao
Haiyan Wu
Wentao Li
Xueying He
Yunshao Zheng
Attention-based multi-scale convolution and conformer for EEG-based depression detection
Frontiers in Psychiatry
depression detection
electroencephalography (EEG)
attention
deep learning (DL)
AMCCBDep
title Attention-based multi-scale convolution and conformer for EEG-based depression detection
title_full Attention-based multi-scale convolution and conformer for EEG-based depression detection
title_fullStr Attention-based multi-scale convolution and conformer for EEG-based depression detection
title_full_unstemmed Attention-based multi-scale convolution and conformer for EEG-based depression detection
title_short Attention-based multi-scale convolution and conformer for EEG-based depression detection
title_sort attention based multi scale convolution and conformer for eeg based depression detection
topic depression detection
electroencephalography (EEG)
attention
deep learning (DL)
AMCCBDep
url https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1584474/full
work_keys_str_mv AT zeyan attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT zeyan attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT zeyan attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT yumeiwan attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT xinpu attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT xiaolinhan attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT mingmingzhao attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT haiyanwu attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT wentaoli attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT xueyinghe attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection
AT yunshaozheng attentionbasedmultiscaleconvolutionandconformerforeegbaseddepressiondetection