基于 PDMS-Carbon 材料的脑电信号传感及 ADHD 自动分类方法研究

注意力缺陷多动障碍(Attention Deficit /Hyperactivity Disorder，ADHD)是儿 童与青少年间最常见的神经发育障碍疾病, 会严重损伤患儿的注意力功能与认知 功能，全球范围内患病率约 5%，国内患病率约为 6.3%。现阶段 ADHD 疾病的诊 断基于行为、心理等量表，且由于医生经验水平差异，容易造成漏诊现象的发生。
脑电图(Electroencephalogram，EEG)中包含大量认知信息，因此利用 EEG 数据信息能够实现 ADHD 的疾病分类。EEG 信号微弱，信号采集过程中容易受到 外界噪声、眼部等肌肉运动伪迹的影响;且 EEG 实验需要完成长时期采集任务， 传统凝胶湿电极会出现变干硬化现象导致信号失真;同时，EEG 具有时间关联性， 包含大量的时间信息，而现有分类算法主要针对卷积神经网(Convolutional Neural Network，CNN)络进行模型架构，无法提取时间信号特征，造成分类准确率较低， 无法满足临床与科研需求。
针对 EEG 信号采集、分类任务中无法长期采集与模型分类性能较低等问题， 本文提出了可以进行长期稳定信号监测的 PDMS-Carbon Paste 电极，针对 EEG 信 号分类任务创新性提出 EEG-Transformer 深度学习模型。本研究中 PDMS-Carbon Paste 电极与凝胶电极互为实验对照组，相邻两天实验模拟信号长期采集情况，通 过皮肤-阻抗分析实验初步验证电极性能，同时采集生理信号(心电信号与肌电信 号)进行信号质量分析实验，结果验证 PDMS-Carbon Paste 电极具有长期 EEG 信 号采集可行性;最终针对脑电信号采集分析，设计睁闭眼实验，在相邻两天采集中 能够采集波形清晰稳定的 EEGα 波，证明本文提出的 PDMS-Carbon Paste 电极能够 在长期生理信号采集任务保持稳定高质量采集信号性能。EEG 信号分类算法研究 中，通过构建三类常见 CNN 模型结果与 EEG-Transformer 模型进行性能对比，结 果证明 EEG-Transformer 具有快速稳定收敛能力，EEG 分类准确度高于其他模型， 达到 98.85% 的分类准确率。利用消融实验分析模型作用，提高深度学习模型内部 可解释性;通过注意力机制调整，实现信号分类最优性能，最终利用脑网络连接分 析进一步可视化不同人群脑连接差异，证明 EEG-Transformer 能够针对 EEG 信号 进行特征提取与分类处理，同时模型结构清晰具有较强的可解释性。

[1] SONG P, ZHA M, YANG Q, et al. The prevalence of adult attention-deficit hyperactivity dis- order: A global systematic review and meta-analysis[J]. Journal of Global Health, 2021, 11.
[2] FARAONE S V, BIEDERMAN J, MICK E. The age-dependent decline of attention deficit hyperactivity disorder: a meta-analysis of follow-up studies[J]. Psychological Medicine, 2006, 36(2): 159-165.
[3] LOH H W, OOI C P, BARUA P D, et al. Automated detection of ADHD: Current trends and future perspective[J]. Computers in Biology and Medicine, 2022: 105525.
[4] WOLRAICH M L, CHAN E, FROEHLICH T, et al. ADHD diagnosis and treatment guidelines: a historical perspective[J]. Pediatrics, 2019, 144(4).
[5] SAYAL K, PRASAD V, DALEY D, et al. ADHD in children and young people: prevalence, care pathways, and service provision[J]. The lancet psychiatry, 2018, 5(2): 175-186.
[6] BRIARS L, TODD T. A review of pharmacological management of attention- deficit/hyperactivity disorder[J]. The Journal of Pediatric Pharmacology and Therapeutics, 2016, 21(3): 192-206.
[7] MAK A D, CHAN A K, CHAN P K, et al. Diagnostic outcomes of childhood ADHD in Chinese adults[J]. Journal of Attention Disorders, 2020, 24(1): 126-135.
[8] 罗学荣, 汪贝妮. 注意缺陷多动障碍共患病的诊断与治疗[J]. 中国儿童保健杂志, 2018, 26 (7): 4.
[9] ELEFANTE C, BRANCATI G E, BACCIARDI S, et al. Prevalence and clinical correlates of comorbid anxiety and panic disorders in patients with Parkinson’s disease[J]. Journal of Clinical Medicine, 2021, 10(11): 2302.
[10] VOGT B A. Cingulate impairments in ADHD: Comorbidities, connections, and treatment[J]. Handbook of Clinical Neurology, 2019, 166: 297-314.
[11] BANASCHEWSKI T, DOEPFNER M. DMS-5-attention-deficit/hyperactivity disorder[J]. Zeitschrift fur Kinder-Und Jugendpsychiatrie Und Psychotherapie, 2014, 42(4): 271-5.
[12] PODOLSKI C L, NIGG J T. Parent stress and coping in relation to child ADHD severity and associated child disruptive behavior problems[J]. Journal of Clinical Child Psychology, 2001, 30(4): 503-513.
[13] GOMEZ R, VANCE A, WATSON S D. Structure of the wechsler intelligence scale for children– fourth edition in a group of children with ADHD[J]. Frontiers in Psychology, 2016, 7: 737.
[14] HUANG Y, XU H, AU W, et al. Involvement of family environmental, behavioral, and so- cial functional factors in children with attention-deficit/hyperactivity disorder[J]. Psychology Research and Behavior Management, 2018: 447-457.
[15] 谭光明, 李金柳, 邱亿腾, 等. conners 父母症状量表问卷在儿童多动症诊断中的应用研究 [J]. 国际医药卫生导报, 2019, 25(23): 2.
[16] CHARACH A, CHEN S, HOGG-JOHNSON S, et al. Using the Conners’ Teacher Rating Scale- Revised in School Children Referred for Assessment[J]. Canadian Journal of Psychiatry. Revue canadienne de psychiatrie, 2009, 54(4): 232-241.
[17] ADESMAN A R. The diagnosis and management of attention-deficit/hyperactivity disorder in pediatric patients[J]. Primary Care companion to the Journal of Clinical Psychiatry, 2001, 3(2): 66.
[18] WHITNEY D G, PETERSON M D. US national and state-level prevalence of mental health disorders and disparities of mental health care use in children[J]. JAMA Pediatrics, 2019, 173 (4): 389-391.
[19] HNAZAEE M F, WITTEVRONGEL B, KHACHATRYAN E, et al. Localization of deep brain activity with scalp and subdural EEG[J]. NeuroImage, 2020, 223: 117344.
[20] HNAZAEE M F, VERWOERT M, FREUDENBURG Z V, et al. Towards predicting ECoG-BCI performance: assessing the potential of scalp-EEG[J]. Journal of Neural Engineering, 2022, 19 (4): 046045.
[21] BABAYAN A, ERBEY M, KUMRAL D, et al. A mind-brain-body dataset of MRI, EEG, cognition, emotion, and peripheral physiology in young and old adults[J]. Scientific Data, 2019, 6(1): 1-21.
[22] VÄRBU K, MUHAMMAD N, MUHAMMAD Y. Past, present, and future of EEG-based BCI applications[J]. Sensors, 2022, 22(9): 3331.
[23] VAID S, SINGH P, KAUR C. EEG signal analysis for BCI interface: A review[C]//2015 Fifth International Conference on Advanced Computing & Communication Technologies. IEEE, 2015: 143-147.
[24] MENG J, ZHANG S, BEKYO A, et al. Noninvasive electroencephalogram based control of a robotic arm for reach and grasp tasks[J]. Scientific Reports, 2016, 6(1): 38565.
[25] 王晓韡, 石立臣, 吕宝粮. 干电极脑电采集技术综述[J]. 中国生物医学工程学报, 2010, 29 (5): 8.
[26] SUFFCZYNSKI P, CRONE N E, FRANASZCZUK P J. Afferent inputs to cortical fast-spiking interneurons organize pyramidal cell network oscillations at high-gamma frequencies (60–200 Hz)[J]. Journal of Neurophysiology, 2014, 112(11): 3001-3011.
[27] PAN X, ZHANG Z, QU J, et al. Enjoy driving from thought in a virtual city[C]//2017 36th Chinese Control Conference (CCC). IEEE, 2017: 11034-11040.
[28] RAMAKURI S K, GHOSH S, GUPTA B. Behaviour state analysis through brain computer interface using wearable EEG devices: A review[J]. Electronic Government, an International Journal, 2017, 13(4): 377-390.
[29] LI G, ZHANG D, WANG S, et al. Novel passive ceramic based semi-dry electrodes for recording electroencephalography signals from the hairy scalp[J]. Sensors and Actuators B: Chemical, 2016, 237: 167-178.
[30] HINRICHS H, SCHOLZ M, BAUM A K, et al. Comparison between a wireless dry electrode EEG system with a conventional wired wet electrode EEG system for clinical applications[J]. Scientific Reports, 2020, 10(1): 1-14.
[31] LI G L, WU J T, XIA Y H, et al. Review of semi-dry electrodes for EEG recording[J]. Journal of Neural Engineering, 2020, 17(5): 051004.
[32] MOTA A R, DUARTE L, RODRIGUES D, et al. Development of a quasi-dry electrode for EEG recording[J]. Sensors and Actuators A: Physical, 2013, 199: 310-317.
[33] YANG L, LIU Q, ZHANG Z, et al. Materials for dry electrodes for the electroencephalography: advances, challenges, perspectives[J]. Advanced Materials Technologies, 2022, 7(3): 2100612.
[34] RAKHMATULIN I, GAN Y. Review Dry and Non-contact EEG Electrodes for 2010-2021 years[J]. Available at SSRN 3811052, 2021: 126-135.
[35] WANG R, JIANG X, WANG W, et al. A microneedle electrode array on flexible substrate for long-term EEG monitoring[J]. Sensors and Actuators B: Chemical, 2017, 244: 750-758.
[36] YU B, KANG S Y, AKTHAKUL A, et al. An elastic second skin[J]. Nature Materials, 2016, 15(8): 911-918.
[37] WANG F, LIU S, SHU L, et al. Low-dimensional carbon based sensors and sensing network for wearable health and environmental monitoring[J]. Carbon, 2017, 121: 353-367.
[38] WANG D, ZHANG Y, LU X, et al. Chemical formation of soft metal electrodes for flexible and wearable electronics[J]. Chemical Society Reviews, 2018, 47(12): 4611-4641.
[39] YANG J C, MUN J, KWON S Y, et al. Electronic skin: recent progress and future prospects for skin-attachable devices for health monitoring, robotics, and prosthetics[J]. Advanced Materials, 2019, 31(48): 1904765.
[40] WANG B, FACCHETTI A. Mechanically flexible conductors for stretchable and wearable e- skin and e-textile devices[J]. Advanced Materials, 2019, 31(28): 1901408.
[41] ZHONG Z, LEE S H, KO P, et al. Control of thermal deformation with photonic sintering of ultrathin nanowire transparent electrodes[J]. Nanoscale, 2020, 12(4): 2366-2373.
[42] MÜLLER K R, TANGERMANN M, DORNHEGE G, et al. Machine learning for real-time single-trial EEG-analysis: from brain–computer interfacing to mental state monitoring[J]. Jour- nal of Neuroscience Methods, 2008, 167(1): 82-90.
[43] STEWART A X, NUTHMANN A, SANGUINETTI G. Single-trial classification of EEG in a visual object task using ICA and machine learning[J]. Journal of Neuroscience Methods, 2014, 228: 1-14.
[44] MOGHADDARI M, LIGHVAN M Z, DANISHVAR S. Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG[J]. Computer Meth- ods and Programs in Biomedicine, 2020, 197: 105738.
[45] DUBREUIL-VALL L, RUFFINI G, CAMPRODON J A. Deep learning convolutional neu- ral networks discriminate adult ADHD from healthy individuals on the basis of event-related spectral EEG[J]. Frontiers in Neuroscience, 2020, 14: 251.
[46] CHEN H, SONG Y, LI X. A deep learning framework for identifying children with ADHD using an EEG-based brain network[J]. Neurocomputing, 2019, 356: 83-96.
[47] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.
[48] ALIYU I, LIM Y B, LIM C G. Epilepsy detection in EEG signal using recurrent neural network [C]//Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuris- tics & Swarm Intelligence. 2019: 50-53.
[49] YU C, MA X, REN J, et al. Spatio-temporal graph transformer networks for pedestrian trajec- tory prediction[C]//Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XII 16. Springer, 2020: 507-523.
[50] DHAMIJA T, GUPTA A, GUPTA S, et al. Semantic segmentation in medical images through transfused convolution and transformer networks[J]. Applied Intelligence, 2023, 53(1): 1132- 1148.
[51] CLAUWAERT J, WAEGEMAN W. Novel transformer networks for improved sequence labeling in genomics[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2020, 19(1): 97-106.
[52] EDUOK U, FAYE O, SZPUNAR J. Recent developments and applications of protective silicone coatings: A review of PDMS functional materials[J]. Progress in Organic Coatings, 2017, 111: 124-163.
[53] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, 30.
[54] 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.
[55] SCHIRRMEISTER R T, SPRINGENBERG J T, FIEDERER L D J, et al. Deep learning with convolutional neural networks for EEG decoding and visualization[J]. Human Brain Mapping, 2017, 38(11): 5391-5420.
[56] VAHID A, BLUSCHKE A, ROESSNER V, et al. Deep learning based on event-related EEG differentiates children with ADHD from healthy controls[J]. Journal of Clinical Medicine, 2019, 8(7): 1055.