|
|
|
| Diagnostic Protocol for Mild Cognitive Impairment Based on Dimensional Transformation of EEG Signals |
| LI Xin1,2,LI Zi-peng1,2,LIU Yi1,2,XIE Ping1,2,3,WANG Yu-lin4 |
1. School of Electrical Engineering, Yanshan University, Qinhuangdao, Hebei 066004,China
2. Measurement Technology and Instrumentation Key Lab of Hebei Province Qinhuangdao, Hebei 066004, China
3. Institute of Health and Wellness Industry Technology, Yanshan University, Qinhuangdao, Hebei 066004, China
4. Qinhuangdao First Hospital, Qinhuangdao, Hebei 066099, China
|
|
|
|
|
Abstract A spectral entropy dimension transformation method matching the convolutional neural network (CNN) was proposed. The EEG data samples of 26 amnestic mild cognitive impairment patients and 20 healthy subjects were compared and analyzed from three aspects: short-time Fourier transform, wavelet transform and spectral entropy.A novel diagnosis scheme of mild cognitive impairment was constructed by using spectrum entropy and CNN.Then, through the comparison of feedforward neural network, k-nearest neighbor, support vector machine, decision tree, naive Bayes, logistic regression and other models, it was verified that the scheme can effectively completed the pattern recognition of EEG in patients with preclinical Alzheimers disease from two aspects of accuracy and stability.Experimental results show that the proposed method can achieve an accuracy of (92.662±1.216)%, and still has high recognition accuracy and generalization ability for EEG signals with noise interference.
|
|
Received: 28 January 2023
Published: 10 October 2023
|
|
|
|
|
|
| ［9］ |
Nunez P L, Srinivasan R, Electric Fields of the Brain: The neurophysics of EEG ［M］. Oxford University Press, 2006.
|
| ［19］ |
Al-Jumeily D, Iram S, Vialatte F B, et al. A novel method of early diagnosis of Alzheimers disease based on EEG signals ［J］. ScientificWorldJournal, 2015: 931387.
|
| ［35］ |
罗志增, 邱志斌. 邻域比较数字滤波与小波变换在脑电信号消噪中的应用 ［J］. 计量学报, 2011, 32 (5): 470-473.
|
| ［8］ |
何群, 杜硕, 王煜文, 等. 基于变分模态分解与深度信念网络的运动想象分类识别研究 ［J］. 计量学报, 2020, 41 (1): 90－99.
|
| ［17］ |
Niedermeyers Electroencephalography: Basic Principles, Clinical Applications, and Related Fields ［M］. Oxford University Press, 2017.
|
| ［2］ |
Gaugler J, James B, Johnson T, et al.2019 Alzheimers disease facts and figures ［J］. Alzheimers & Dementia, 2019, 15 (3): 321-387.
|
| ［5］ |
Ocaa Montoya C M, Montoya Pedrón A, G A. Bolao Díaz, Perfil clínico neuropsicológico del deterioro cognitivo subtipo posible Alzheimer ［J］. MediSan, 2019, 23 (5): 875-891.
|
| ［6］ |
刘晓波, 赵铃铃, 李毅, 等. 基于动作类电子游戏不同水平人群的脑电beta节律频数分析法 ［J］. 中国生物医学工程学报, 2021, 40 (05): 574-581.
|
| ［7］ |
付荣荣, 米瑞甫, 王涵, 等. 基于脑功能网络的脑疲劳状态检测研究 ［J］. 计量学报, 2021, 42 (11): 1528-1533.
|
| ［12］ |
Mittal S H, Salian S J, Devadiga Y, et al.Abnormal Levels of Consciousness and their Electroencephalogram Correlation: A Review ［J］. EC Neurol Rev Article, 2016, 4 (1): 30-35.
|
| ［13］ |
Ya M, Xun W, L Wei, et al.Is the Electroencephalogram Power Spectrum Valuable for Diagnosis of the Elderly with Cognitive Impairment? ［J］. International Journal of Gerontology, 2015, 9 (4): 196-200.
|
| ［43］ |
Kingma D P, Ba J. Adam: A method for stochastic optimization ［J］. Computer Science, 2014, 14 (12): 69-80.
|
| ［3］ |
Petersen R C, Smith G E, Waring S C, et al.Mild cognitive impairment: clinical characterization and outcome［J］. Arch Neurol, 1999, 56 (3): 303-308.
|
| ［10］ |
Gueguen B, Ancri D, Derouesné C, et al. Comparaison des aspects SPECT et EEG quantifié dans les démences de type Alzheimer ［J］. Neurophysiologie Clinique/Clinical Neurophysiology, 1991, 21 (5-6): 377-387.
|
| ［15］ |
Houmani N, Vialatte F, Gallego-Jutgla E, et al.Diagnosis of Alzheimers disease with Electroencephalography in a differential framework ［J］. PLoS One, 2018, 13 (3): e0193607.
|
| ［20］ |
Schoffelen J M, Gross J, Source connectivity analysis with MEG and EEG ［J］. Hum Brain Mapp, 2009, 30 (6): 1857-1865.
|
| ［22］ |
Triggiani A I, Bevilacqua V, Brunetti A, et al. Classification of Healthy Subjects and Alzheimers Disease Patients with Dementia from Cortical Sources of Resting State EEG Rhythms: A Study Using Artificial Neural Networks ［J］. Front Neurosci, 2017, 10: 604.
|
| ［23］ |
Ieracitano C, Mammone N, Bramanti A, et al. A Time-Frequency based Machine Learning System for Brain States Classification via EEG Signal Processing［C］// International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 2019.
|
| ［25］ |
Toural J E S, Pedrón A M, Maraón E J, A Wavelet Entropy Based Methodology for Classification Among Healthy, Mild Cognitive Impairment and Alzheimers Disease People［C］//24th Iberoamerican Congress on Pattern Recognition (CIARP), Havana, Cuba, 2019.
|
| ［27］ |
Ruiz-Gómez S J, Gómez C, Poza J, et al. Automated multiclass classification of spontaneous EEG activity in Alzheimers disease and mild cognitive impairment ［J］. Entropy, 2018, 20 (1): 35.
|
| ［29］ |
Tzimourta K D, Christou V, Tzallas A T, et al. Machine learning algorithms and statistical approaches for Alzheimers disease analysis based on resting-state EEG recordings: A systematic review ［J］. International journal of neural systems, 2021, 31 (05): 2130002.
|
| ［30］ |
Simfukwe C, Youn Y C, Kim M J, et al. CNN for a Regression Machine Learning Algorithm for Predicting Cognitive Impairment Using qEEG ［J］. Neuropsychiatric Disease and Treatment, 2023: 851-863.
|
| ［38］ |
J.M. Lilly, jLab: A data analysis package for Matlab, version 1.6.2 ［EB］. http: //www.jmlilly.net/jmlsoft.html.
|
| ［1］ |
Dua T, Seeher M K, Sivananthan S, et al. Global action plan on the public health response to dementia 2017-2025［J］. lzheimer's & Dementia: The Journal of the Alzheimer's Association, 2017,13 (7).
|
| ［4］ |
Petersen R C, Lopez O, Armstrong M J, et al.Practice guideline update summary: Mild cognitive impairment: Report of the Guideline Development, Dissemination, and Implementation Subcommittee of the American Academy of Neurology ［J］. Neurology, 2018, 90 (3): 126-135.
|
|
He Q,Du S,Wang Y W,et al. The Classification of EEG Induced by Motor Imagery Based on VariationalMode Decomposition and Deep Belief Network ［J］. Acta Metrologica Sinica, 2020, 41 (1): 90－99.
|
| ［11］ |
Wang R, Wang J, Li S, et al. Multiple feature extraction and classification of electroencephalograph signal for Alzheimers with spectrum and bispectrum ［J］. Chaos: An Interdisciplinary Journal of Nonlinear Science, 2015, 21 (1): 013110.
|
| ［18］ |
Dauwels J, Srinivasan K, Ramasubba Reddy M, et al. Slowing and Loss of Complexity in Alzheimers EEG: Two Sides of the Same Coin? ［J］. Int J Alzheimers Dis, 2011: 539621.
|
| ［21］ |
Bevilacqua V, Salatino A A, Leo C D, et al. Advanced classification of Alzheimers disease and healthy subjects based on EEG markers［C］// International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland, 2015.
|
| ［28］ |
Jelic V, Kowalski J. Evidence-based evaluation of diagnostic accuracy of resting EEG in dementia and mild cognitive impairment ［J］. Clinical EEG and Neuroscience, 2009, 40 (2): 129-142.
|
| ［31］ |
金海龙, 邬霞, 樊凤杰, 等. 基于GST-ECNN的运动想象脑电信号识别方法 ［J］. 计量学报, 2022, 43 (10): 1341-1347.
|
| ［32］ |
Ieracitano C, Mammone N, Hussain A, et al. A Convolutional Neural Network based self-learning approach for classifying neurodegenerative states from EEG signals in dementia［C］//2020 International Joint Conference on Neural Networks (IJCNN).Shanghai, China, 2020.
|
| ［34］ |
Sharma N, Kolekar M H, Chandra S. The role of EEG signal processing in detection of neurocognitive disorders ［J］. International Journal of Behavioural and Healthcare Research, 2016, 6 (1): 15-27.
|
|
Liu X B, Zhao L L, Li Y, et al. EEG beta rhythm frequency analysis method based on different levels of action video games ［J］. Chinese Journal of Biomedical Engineering, 2021, 40 (05): 574-581.
|
|
Fu R R, Mi R F, Wang H,et al. Research on FatigueDriving Recognition Based on Brain Function Network ［J］. Acta Metrologica Sinica, 2021, 42 (11): 1528－1533.
|
| ［14］ |
Cassani R, Estarellas M, San-Martin R, et al.Systematic Review on Resting-State EEG for Alzheimers Disease Diagnosis and Progression Assessment ［J］. Disease Markers, 2018: 5174815.
|
| ［16］ |
Musaeus C S, Engedal K, Hogh P, et al. EEG Theta Power Is an Early Marker of Cognitive Decline in Dementia due to Alzheimers Disease ［J］. Alzheimers Dis, 2018, 64 (4): 1359-1371.
|
| ［24］ |
Santos Toural J E, Montoya Pedrón A, Maraón Reyes E J, Classification among healthy, mild cognitive impairment and Alzheimers disease subjects based on wavelet entropy and relative beta and theta power ［J］. Pattern Analysis and Applications, 2020, 24 (2): 413-422.
|
| ［26］ |
Torrents-Barrena J, Lazar P, Jayapathy R, et al. Complex wavelet algorithm for computer-aided diagnosis of Alzheimers disease ［J］. Electronics Letters, 2015, 51 (20): 1566-1568.
|
| ［33］ |
Clerc M, Bougrain L, Lotte F, Brain-Computer Interfaces 1: Foundations and Methods［M］. Oxford University Press, 2016.
|
| ［36］ |
Akahin M F, Burcu O, Karaca B K. Kalp seslerini kaydeden ve otomatik S1-S2 dalgasｌ belirleyen sistem tasarｌmｌ ［J］. Gazi üniversitesi Mühendislik Mimarlik Fakültesi Dergisi, 2019, 35 (1): 61-70.
|
| ［39］ |
Inouye T, Shinosaki K, Sakamoto H, et al. Quantification of EEG irregularity by use of the entropy of the power spectrum ［J］. Electroencephalography and clinical neurophysiology, 1991, 79 (3): 204-210.
|
| ［41］ |
Hossin M, Sulaiman M N. A review on evaluation metrics for data classification evaluations ［J］. International journal of data mining & knowledge management process, 2015, 5 (2): 1.
|
| ［42］ |
Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks［C］//Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 2010: 249-256.
|
| ［44］ |
Zhang H, Geng X, Wang Y, et al. The significance of EEG alpha oscillation spectral power and beta Oscillation phase synchronization for diagnosing probable Alzheimer disease ［J］. Frontiers in Aging Neuroscience, 2021, 13: 631587.
|
|
Jin H L, Wu X, Fan F J, et al. Recognition method of motor imaging EEG signal based on GST-ECNN ［J］. Acta Metrologica Sinica, 2022, 43 (10): 1341-1347.
|
| ［37］ |
Rangayyan R M. Biomedical signal analysis［M］. John Wiley & Sons, 2015.
|
| ［40］ |
Sokolova M, Japkowicz N, Szpakowicz S. Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation［C］//Australasian joint conference on artificial intelligence. Berlin, Heidelberg, 2006.
|
| ［46］ |
Abdulhay E, Alafeef M, Hadoush H, et al. Resting state EEG-based diagnosis of Autism via elliptic area of continuous wavelet transform complex plot ［J］. Journal of Intelligent & Fuzzy Systems, 2020, 39 (6): 8599-8607.
|
| ［47］ |
LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition ［J］. Proceedings of the IEEE, 1998, 86 (11): 2278-2324.
|
|
Luo Z Z, Qiu Z B. Application of Neighborhood Comparison Digital Filter and Wavelet Transform in Noise Cancellation of EEG Signals ［J］. Acta Metrologica Sinica, 2011, 32 (5): 470-473.
|
| ［45］ |
Su R, Li X, Liu Y, et al. Evaluation of the brain function state during mild cognitive impairment based on weighted multiple multiscale entropy ［J］. Frontiers in Aging Neuroscience, 2021, 13: 625081.
|
| ［48］ |
Li X, Yang C, Xie P, et al. The diagnosis of amnestic mild cognitive impairment by combining the characteristics of brain functional network and support vector machine classifier ［J］. Journal of Neuroscience Methods, 2021, 363: 109334.
|
|
|
|
2023, Vol. 44 
