Study on Multi-Feature Fusion of EEG to Evaluate Children with Autism
Zhao Jie1, Jin Yajuan1, Zhang Zhiming1, Wan Lingyan1, Li Xiaoli2, Kang Jiannan1*
1(Institute of Electronic Information Engineering, Hebei University, Baoding 071000, Hebei, China) 2(State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing 100875, China)
Abstract Autism is a complex neurodevelopmental brain disease, early detection and accurate diagnosis are very important. This paper extracted power spectrum, entropy, bispectral coherence, and coherence from the EEG signals of 54 autistic and 50 normal children for analysis and research and conducted independent sample t test for each group of characteristics to analyze the differences between the groups. To improve the classification performance, the fusion of multi-feature EEG was proposed for the analysis, and the maximum correlation minimum redundancy algorithm was further used for the feature selection, and at last the support vector machine was used to establish the classification model. Results showed that the classification accuracy rate obtained by single feature classification was 64%, the sensitivity was 68.25%, the specificity was 65.25%, and the F1 score was 69.19%. The single feature was established and showed poor performance. When fusing multiple features for classification, the first 25 features were selected to build a model that had a high classification accuracy of 93.45%, the sensitivity was 91.73%, the specificity was 84.01%, and the F1 score was 92.54%, and the AUC reached 0.96, which had better performance than the single feature classification model. The results of this study provided a scientific and objective basis for the auxiliary diagnosis of autism, as well as a reliable reference for the later rehabilitation of autistic children.
Zhao Jie,Jin Yajuan,Zhang Zhiming, et al. Study on Multi-Feature Fusion of EEG to Evaluate Children with Autism[J]. Chinese Journal of Biomedical Engineering, 2021, 40(5): 550-558.
[1] Fadi T, Firuz K, Khairan R. A new computational intelligence approach to detect autistic features for autism screening [J]. International Journal of Medical Informatics, 2018, 81(1):112-124. [2] Baum SH, Stevenson RA, Wallace MT. Behavioral, perceptual, and neural alterations in sensory and multisensory function in autism spectrum disorder [J]. Progress in Neurobiology, 2015, 7(2):140-160. [3] He H, Thomson DJ. Canonical bicoherence analysis of dynamic EEG data [J]. Comput Neurosci, 2010, 29(1-2): 23-34. [4] Volkmar FR, Cicchetti DV, Dykens E, et al. An evaluation of the autism behavior checklist [J]. Journal of Autism and Developmental Disorders, 1988, 18(1): 81-87. [5] Schopler E, Reichler RJ, Devellis RF, et al. Toward objective classification of childhood autism: Childhood Autism Rating Scale (CARS) [J]. Journal of Autism and Developmental Disorders, 1980, 10(1): 91-103. [6] Islam MK, Rastegarnia A, Yang Z. Methods for artifact detection and removal from scalp EEG: A review [J]. Neurophysiologie Clinique, 2016, 46(4-5): 287-305. [7] Diessen EV, Senders J, Jansen FE, et al. Increased power of resting-state gamma oscillations in autism spectrum disorder detected by routine electroencephalography [J]. European Archives of Psychiatry and Clinical Neuroscience, 2014, 265(6): 537-540. [8] Murias M, Webb SJ, Greenson J, et al. Resting state cortical connectivity reflected in EEG coherence in individuals with autism [J]. Biological Psychiatry, 2007, 62(3): 270-273. [9] Cook IA, Wilson AC, Peters JM, et al. EEG spectral features in sleep of autism spectrum disorders in children with tuberous sclerosis complex [J]. Journal of Autism and Developmental Disorders, 2020, 50(3): 916-923. [10] Distefano C, Dickinson A, Baker E, et al. EEG data collection in children with ASD: The role of state in data quality and spectral power [J]. Research in Autism Spectrum Disorders, 2019, 57:132-144. [11] Wang Jun, Barstein J, Ethridge LE, et al. Resting state EEG abnormalities in autism spectrum disorders [J]. Journal of Neurodevelopmental Disorders, 2013, 5(1): 24-27. [12] Schack B, Vath N, Petsche H, et al. Phase-coupling of theta-gamma EEG rhythms during short-term memory processing [J]. International Journal of Psychophysiology, 2002, 44(2):143-163. [13] Okazaki R, Takahashi T, Ueno K, et al. Changes in EEG complexity with electroconvulsive therapy in a patient with autism spectrum disorders: A multiscale entropy approach [J]. Front Hum Neurosci, 2015, 9(7):368-401. [14] Catarino A, Churches O, Baron S, et al. Atypical EEG complexity in autism spectrum conditions: a multiscale entropy analysis. [J].Clinical Neurophysiology, 2011, 122:2375-2383. [15] Bosl W, Tierney A, Tager-Flusberg H, et al. EEG complexity as a biomarker for autism spectrum disorder risk [J]. BMC Medicine, 2011, 9(1):18. [16] Sohn H, Kim I, Lee W, et al. Linear and non-linear EEG analysis of adolescents with attention-deficit/hyperactivity disorder during a cognitive task [J]. Clinical Neurophysiology, 2010,25(1-2):1863-1870. [17] Chandran V. Time-varying bispectral analysis of visually evoked multi-channel EEG [J]. Journal of Psychophysiology, 2012, 12(7):23-25. [18] Bullock T, Achimowicz J, Duckrow R, et al. Bicoherence of intracranial EEG in sleep wakefulness and seizures [J]. Electroencephalography and Clinical Neurophysiology, 1997,103: 661-678. [19] Schack B, Vath N, Petsche H, et.al. Phase-coupling of theta-gamma EEG rhythms during short-term memory processing [J]. International Journal of Psychophysiology,2002,44:143-163. [20] Hayashi K, Fujikawa M, Sawa T. Hyperventilation-induced hypocapnia changes the pattern of electroencephalographic bicoherence growth during sevoflurane anaesthesia [J].British Journal of Aanesthesia, 2008, 101(5): 666-672. [21] Eldridge J, Lane AE, Belkin M, et al. Robust features for the automatic identification of autism spectrum disorder in children [J]. Neurodev Disord, 2014, 6(1): 12-15. [22] Durka PJ, Klekowicz H Blinowska K, et al. A simple system for detection of EEG artifacts in polysomnographic recordings [J]. Biomedical Engineering, 2003, 11:526-528. [23] Jacob JE, Nair GK. EEG entropies as estimators for the diagnosis of encephalopathy [J]. Analog Integrated Circuits and Signal Processing, 2019, 101(3): 463-474. [24] Aydin S, Saraoglu HM, Kara S. Log energy entropy-based EEG classification with multilayer neural networks in seizure [J]. Annals of Biomedical Engineering, 2009, 37(12):2626-2630. [25] Zhou Yujuan, Wang Lei, Jia Jintai, et al. Application of back propagation neural network and information entropy in deep detection of anesthesia [J]. Journal of Medical Imaging and Health Informatics, 2020,82(7):518-520. [26] Tylov L, Kukal J, Hubata V, et al. Unbiased estimation of permutation entropy in EEG analysis for Alzheimer's disease classification [J]. Biomedical Signal Processing and Control, 2018, 39(1):424-430. [27] Senders J. Complexity Analysis of EEG in AD Patients with Fractional Permutation Entropy [J]. Chinese Journal of Medical Physics, 2015,52(1):521-550. [28] Quiroga RQ, Rosso OA, Basar E, et al. Wavelet entropy in event-related potentials: A new method shows ordering of EEG oscillations [J]. Biol Cybern, 2001,84(4): 291-299. [29] Zhang Sheng, Qiao Shini, Wang Wei. Melancholia's EEG complexity analysis based on wavelet entropy [J].Computer Engineering and Application, 2012, 48(4):143-145. [30] Zhang Meiyun, Zhang Benshu, Chen Ying. Wavelet entropy analysis of spontaneous EEG signals in Alzheimer's disease [J]. Journal of Biomedical Engineering,2014,31(4):755-761. [31] 白洋.意识障碍的脑电分析与神经调控评估 [D].秦皇岛:燕山大学,2017. [32] Schack B, Grieszbach G, Nowak H, et al. The sensitivity of instantaneous coherence for considering elementary comparison processing [J]. International Journal of Psychophysiology, 1999,31(3): 241-259. [33] Srinivasan R, Winter WR, Ding J, et al. EEG and MEG coherence: Measures of functional connectivity at distinct spatial scales of neocortical dynamics [J]. Neurosci Methods,2007,16(1):41-52. [34] Elaal SA, Ramadan RA, Ghali N, et al. Classification of EEG signals for motor imagery based on mutual information and adaptive neuro fuzzy inference system [J].International Journal of System Dynamics Applications, 2016, 5(4):64-82. [35] Jacob JE, Nair GK, Iype T, et al. Diagnosis of encephalopathy based on energies of EEG subbands using discrete wavelet transform and support vector machine [J]. Neurology Research International, 2018,9(2):25-30. [36] Jahmunah V, Oh SL, Rajinikanth V, et al. Automated detection of schizophrenia using nonlinear signal processing methods [J]. Artificial Intelligence in Medicine, 2019,100(1):7-22. [37] Kulisek R, Hrncir Z, Hrdlicka M, et al. Nonlinear analysis of the sleep EEG in children with pervasive developmental disorder [J]. Neuro Endocrinol Lett, 2008, 29(4):512-517. [38] 赵杰,丁萌,佟祯,等.基于熵算法的孤独症谱系障碍儿童脑电特征提取与分类[J]. 生物医学工程学杂志, 2019, 36:183-188. [39] Lushchekina EA, Podreznaya ED, Lushchekin VS, et al. A comparative EEG study in normal and autistic children [J]. Neuroscience and Behavioral Physiology, 2012, 42:236-243.
