Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network

doi:10.11772/j.issn.1001-9081.2023091371

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (9): 2970-2974.DOI: 10.11772/j.issn.1001-9081.2023091371

• Frontier and comprehensive applications • Previous Articles Next Articles

Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network

Jing QIN¹, Zhiguang QIN¹(), Fali LI², Yueheng PENG²

^1.School of Information and Software Engineering，University of Electronic Science and Technology of China，Chengdu Sichuan 610054，China
^2.School of Life Science and Technology，University of Electronic Science and Technology of China，Chengdu Sichuan 610054，China

Received:2023-10-10 Revised:2024-01-09 Accepted:2024-01-12 Online:2024-01-31 Published:2024-09-10
Contact: Zhiguang QIN
About author:QIN Jing， born in 1994， Ph. D. candidate. His research interests include medical image， signal processing.
LI Fali， born in 1990， Ph. D.， associate research fellow. His research interests include brain neural mechanisms， brain network analysis， brain-computer interaction.
PENG Yueheng， born in 1993， Ph. D. candidate. His research interests include brain neural mechanisms， brain network analysis， brain-computer interaction.
Supported by:
National Natural Science Foundation of China(62027827)

基于概率稀疏自注意力神经网络的重性抑郁疾患诊断

秦璟¹, 秦志光¹(), 李发礼², 彭悦恒²

^1.电子科技大学信息与软件工程学院，成都 610054
^2.电子科技大学生命科学与技术学院，成都 610054

通讯作者: 秦志光
作者简介:秦璟（1994—），男，四川成都人，博士研究生，CCF会员，主要研究方向：医学图像、信号处理
李发礼（1990—），男，山东临沂人，副研究员，博士，主要研究方向：脑神经机制、脑网络分析、脑机交互
彭悦恒（1993—），男，四川成都人，博士研究生，主要研究方向：脑神经机制、脑网络分析、脑机交互。
基金资助:
国家自然科学基金资助项目(62027827)

Abstract

Abstract:

The diagnosis of major depressive disorder predominantly relies on subjective methods， including physician consultations and scale assessments， which may lead to misdiagnosis. EEG （ElectroEncephaloGraphy） offers advantages such as high temporal resolution， low cost， ease of setup， and non-invasiveness， making it a potential quantitative measurement tool for psychiatric disorders， including depressive disorder. Recently， deep learning algorithms have been diversely applied to EEG signals， notably in the diagnosis and classification of depressive disorder. Due to significant redundancy is observed when processing EEG signals through a self-attention mechanism， a convolutional neural network leveraging a Probabilistic sparse Self-Attention mechanism （PSANet） was proposed. Firstly， a limited number of pivotal attention points were chosen in the self-attention mechanism based on the sampling factor， addressing the high computational cost and facilitating its application to extensive EEG data sequences； concurrently， EEG data was amalgamated with patients’ physiological scales for a comprehensive diagnosis. Experiments were executed on a dataset encompassing both depressive disorder patients and a healthy control group. Experimental results show that PSANet exhibits superior classification accuracy and a reduced number of parameters relative to alternative methodologies such as EEGNet.

Key words: depression disorder diagnosis, ElectroEncephaloGraphy (EEG), deep learning, self-attention mechanism, convolutional neural network

摘要：

抑郁症的诊断主要依赖于医师的咨询和量表评估等主观方法，可能导致误诊。脑电图（EEG）具有高时间分辨率、低成本、易于设置和无创等优点，因此可以用作精神障碍（如抑郁症）的定量测量工具。深度学习算法目前在EEG信号上有多种应用，其中就包括抑郁症的诊断和分类。EGG信号在通过自注意力机制处理时有大量的冗余部分，因此，提出一种基于概率稀疏自注意力机制的卷积神经网络（PSANet）。首先，根据采样因数在自注意力机制中选取少量最关键的注意力点，在运用自注意力机制的同时克服它计算成本高的缺点，使它可以在脑电长序列数据上应用；同时将脑电图与患者的生理量表进行嵌合，从而进行多维度诊断。在一个包含抑郁症患者和健康对照组的数据集上进行实验评估，实验结果表明，PSANet表现出较高的分类准确性，参数量也低于EEGNet等对比方法。

关键词: 抑郁症诊断, 脑电图, 深度学习, 自注意力机制, 卷积神经网络

CLC Number:

TP389.1

Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network[J]. Journal of Computer Applications, 2024, 44(9): 2970-2974.

秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974.

Figures/Tables 6

Fig. 1 Structure of PSANet

Tab. 1 Network parameters of PSANet

Layer	Filters	Size	Activation	Output
Input				（1 280，21）
Embedding	256	3		（1 280，256）
Prob Attn	256	5	GeLU	（1 280，256）
Dropout			Dropout=0.1	（1 280，256）
Conv 1d	256	3		（1 280，256）
BN 1d	256			（1 280，256）
Activation			ELU	（1 280，256）
Maxpool 1d	256	3	Stride=2	（640，256）
Prob Attn	128	5	GeLU	（640，128）
Dropout			Dropout=0.1	（640，128）
Conv 1d	128	3		（640，128）
BN 1d	128			（640，128）
Activation			ELU	（640，128）
Maxpool 1d	64	3	Stride=2	（320，64）
Prob Attn	64	5	GeLU	（320，64）
Dropout			Dropout=0.1	（320，64）
Conv 1d	64	3		（320，64）
BN 1d	64			（320，64）
Activation			ELU	（320，64）
Maxpool 1d	64	3	Stride=2	（160，64）
Flatten				（10 240，）
Linear				（512，）
Linear			Softmax	（2，）

Fig. 2 Changes in model loss and accuracy on validation set

Tab. 2 Performance comparison among different models in classification of major depressive disorder

模型	准确度	精确度	敏感度	特异度	F1-score
EEGNet	84.58 $±$ 2.26	85.59 $±$ 3.23	94.78 $±$ 2.00	58.43 $±$ 8.32	89.89 $±$ 1.44
DSNet	89.05 $±$ 1.23	90.83 $±$ 1.51	94.40 $±$ 1.29	75.07 $±$ 4.35	92.57 $±$ 0.85
DeprNet	90.03 $±$ 1.77	89.23 $±$ 1.64	95.88 $±$ 0.85	76.77 $±$ 5.24	93.28 $±$ 0.76
PSANet	91.57 $±$ 2.37	90.28 $±$ 2.37	99.06 $±$ 0.91	79.98 $±$ 7.56	94.46 $±$ 1.51

Tab. 2 Performance comparison among different models in classification of major depressive disorder

模型	准确度	精确度	敏感度	特异度	F1-score
EEGNet	84.58 $±$ 2.26	85.59 $±$ 3.23	94.78 $±$ 2.00	58.43 $±$ 8.32	89.89 $±$ 1.44
DSNet	89.05 $±$ 1.23	90.83 $±$ 1.51	94.40 $±$ 1.29	75.07 $±$ 4.35	92.57 $±$ 0.85
DeprNet	90.03 $±$ 1.77	89.23 $±$ 1.64	95.88 $±$ 0.85	76.77 $±$ 5.24	93.28 $±$ 0.76
PSANet	91.57 $±$ 2.37	90.28 $±$ 2.37	99.06 $±$ 0.91	79.98 $±$ 7.56	94.46 $±$ 1.51

Fig. 3 Comparison of each fold accuracy among different models in 10-fold cross validation

Tab. 3 Comparison of parameters of different models in classification of major depressive disorder

模型	参数量	模型	参数量
PSANet	3.74	Transformer-encoder	90.68
EEGNet	8.13

References 30

1	KENNEDY S H. Core symptoms of major depressive disorder： relevance to diagnosis and treatment ［J］. Dialogues in Clinical Neuroscience， 2008， 10（3）： 271-277.
2	CLARK M， DiBENEDETTI D， PEREZ V. Cognitive dysfunction and work productivity in major depressive disorder ［J］. Expert Review of Pharmacoeconomics & Outcomes Research， 2016， 16（4）： 455-463.
3	BECH P， BOLWIG T G， KRAMP P， et al. The Bech-Rafaelsen mania scale and the Hamilton depression scale： evaluation of homogeneity and inter-observer reliability ［J］. Acta Psychiatrica Scandinavica， 1979， 59（4）： 420-430.
4	BUZUG T M. Computed tomography ［M］// Springer Handbook of Medical Technology. Berlin： Springer， 2011： 311-342.
5	BIASIUCCI A， FRANCESCHIELLO B， MURRAY M M. Electroencephalography ［J］. Current Biology， 2019， 29（3）： R80-R85.
6	AL-SAEGH A， DAWWD S A， ABDUL-JABBAR J M. Deep learning for motor imagery EEG-based classification： a review ［J］. Biomedical Signal Processing and Control， 2021， 63： 102172.
7	ZHANG J， YIN Z， CHEN P， et al. Emotion recognition using multi-modal data and machine learning techniques： a tutorial and review ［J］. Information Fusion， 2020， 59： 103-126.
8	ZHANG X， LI J， HOU K， et al. EEG-based depression detection using convolutional neural network with demographic attention mechanism ［C］// Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Piscataway： IEEE， 2020： 128-133.
9	WANG D， LEI C， ZHANG X， et al. Identification of depression with a semi-supervised GCN based on EEG data ［C］// Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine. Piscataway： IEEE， 2021： 2338-2345.
10	SU Y， ZHANG Z X， CAI Q， et al. 3DMKDR： 3D multiscale kernels CNN model for depression recognition based on EEG ［J］. Journal of Beijing Institute of Technology， 2023， 32（2）： 230-241.
11	SONG X W， YAN D D， ZHAO L L， et al. LSDD-EEGNet： an efficient end-to-end framework for EEG-based depression detection［J］. Biomedical Signal Processing and Control， 2022， 75： 103612.
12	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need ［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 6000-6010.
13	ZHOU H， ZHANG S， PENG J， et al. Informer： beyond efficient Transformer for long sequence time-series forecasting ［C］// Proceedings of the 2021 AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2021， 35（12）： 11106-11115.
14	LIU W， ZHANG C， WANG X， et al. Functional connectivity of major depression disorder using ongoing EEG during music perception ［J］. Clinical Neurophysiology， 2020， 131（10）： 2413-2422.
15	MUMTAZ W， ALI S S A， YASIN M A M， et al. A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder （MDD）［J］. Medical & Biological Engineering & Computing， 2018， 56： 233-246.
16	ZHANG B， YAN G， YANG Z， et al. Brain functional networks based on resting-state EEG data for major depressive disorder analysis and classification ［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering， 2021， 29： 215-229.
17	MUMTAZ W， XIA L， MOHD YASIN M A， et al. A wavelet-based technique to predict treatment outcome for major depressive disorder ［J］. PLoS ONE， 2017， 12（2）： e0171409.
18	LAWHERN V J， SOLON A J， WAYTOWICH N R， et al. EEGNet： a compact convolutional neural network for EEG-based brain-computer interfaces ［J］. Journal of Neural Engineering， 2018， 15（5）： 056013.
19	DENG X， ZHANG B， YU N， et al. Advanced TSGL-EEGNet for motor imagery EEG-based brain-computer interfaces ［J］. IEEE Access， 2021， 9： 25118-25130.
20	HUANG W， XUE Y， HU L， et al. S-EEGNet： electroencephalogram signal classification based on a separable convolution neural network with bilinear interpolation ［J］. IEEE Access， 2020， 8： 131636-131646.
21	TSUKAHARA A， ANZAI Y， TANAKA K， et al. A design of EEGNet‐based inference processor for pattern recognition of EEG using FPGA ［J］. Electronics and Communications in Japan， 2021， 104（1）： 53-64.
22	SEAL A， BAJPAI R， AGNIHOTRI J， et al. DeprNet： a deep convolution neural network framework for detecting depression using EEG ［J］. IEEE Transactions on Instrumentation and Measurement， 2021， 70： 2505413.
23	TRIVEDI M H， McGRATH P J， FAVA M， et al. Establishing moderators and biosignatures of antidepressant response in clinical care （EMBARC）： rationale and design ［J］. Journal of Psychiatric Research， 2016， 78： 11-23.
24	XIA M， WU Y， GUO D， et al. DSNet： EEG-based spatial convolutional neural network for detecting major depressive disorder ［C］// Proceedings of the 3rd International Workshop on Human Brain and Artificial Intelligence. Cham： Springer， 2022： 50-59.
25	WANG B， KANG Y， HUO D， et al. Depression signal correlation identification from different EEG channels based on CNN feature extraction ［J］. Psychiatry Research： Neuroimaging， 2023， 328： 111582.
26	LI L， WANG X， LI J， et al. An EEG-based marker of functional connectivity： detection of major depressive disorder ［J］. Cognitive Neurodynamics， 2024， 18： 1671-1687.
27	AFZALI A， KHALEGHI A， HATEF B， et al. Automated major depressive disorder diagnosis using a dual-input deep learning model and image generation from EEG signals ［J/OL］. Waves in Random and Complex Media， 2023： 1-16 ［2023-12-23］. .
28	MAHDI A F， AHMED A K. Major depressive disorder diagnosis based on PSD imaging of electroencephalogram EEG and AI ［J］. Indonesian Journal of Electrical Engineering and Computer Science， 2022， 28（1）： 535-544.
29	RAVAN M， NOROOZI A， SANCHEZ M M， et al. Diagnostic deep learning algorithms that use resting EEG to distinguish major depressive disorder， bipolar disorder， and schizophrenia from each other and from healthy volunteers ［J］. Journal of Affective Disorders， 2024， 346： 285-298.
30	KSIBI A， ZAKARIAH M， MENZLI L J， et al. Electroencephalography-based depression detection using multiple machine learning techniques ［J］. Diagnostics， 2023， 13（10）： 1779.

[1]	Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877.
[2]	Yun LI, Fuyou WANG, Peiguang JING, Su WANG, Ao XIAO. Uncertainty-based frame associated short video event detection method [J]. Journal of Computer Applications, 2024, 44(9): 2903-2910.
[3]	Jinjin LI, Guoming SANG, Yijia ZHANG. Multi-domain fake news detection model enhanced by APK-CNN and Transformer [J]. Journal of Computer Applications, 2024, 44(9): 2674-2682.
[4]	Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703.
[5]	Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969.
[6]	Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918.
[7]	Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738.
[8]	Hong CHEN, Bing QI, Haibo JIN, Cong WU, Li’ang ZHANG. Class-imbalanced traffic abnormal detection based on 1D-CNN and BiGRU [J]. Journal of Computer Applications, 2024, 44(8): 2493-2499.
[9]	Chunxue ZHANG, Liqing QIU, Cheng’ai SUN, Caixia JING. Purchase behavior prediction model based on two-stage dynamic interest recognition [J]. Journal of Computer Applications, 2024, 44(8): 2365-2371.
[10]	Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557.
[11]	Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625.
[12]	Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650.
[13]	Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263.
[14]	Dongwei WANG, Baichen LIU, Zhi HAN, Yanmei WANG, Yandong TANG. Deep network compression method based on low-rank decomposition and vector quantization [J]. Journal of Computer Applications, 2024, 44(7): 1987-1994.
[15]	Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072.

Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network

基于概率稀疏自注意力神经网络的重性抑郁疾患诊断

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References 30

Related Articles 15

Recommended Articles

Metrics