Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by impairment in sensory modulation. These sensory modulation deficits would ultimately lead them to difficulties in adaptive behavior and intellectual functioning. The purpose of this study was to observe changes in the nervous system with responses to auditory/visual and only audio stimuli in children with autism and typically developing (TD) through electroencephalography (EEG). In this study, 20 children with ASD and 20 children with TD were considered to investigate the difference in the neural dynamics. The neural dynamics could be understood by non-linear analysis of the EEG signal. In this research to reveal the underlying nonlinear EEG dynamics, recurrence quantification analysis (RQA) is applied. RQA measures were analyzed using various parameter changes in RQA computations. In this research, the cosine distance metric was considered due to its capability of information retrieval and the other distance metrics parameters are compared for identifying the best biomarker. Each computational combination of the RQA measure and the responding channel was analyzed and discussed. To classify ASD and TD, the resulting features from RQA were fed to the designed BiLSTM (bi-long short-term memory) network. The classification accuracy was tested channel-wise for each combination. T3 and T5 channels with neighborhood selection as FAN (fixed amount of nearest neighbors) and distance metric as cosine is considered as the best-suited combination to discriminate between ASD and TD with the classification accuracy of 91.86%, respectively.
GuthrieWSwinefordLBNottkeCWetherbyAM. Early diagnosis of autism spectrum disorder: Stability and change in clinical diagnosis and symptom presentation. J Child Psychol Psychiatry. 2013;54(5):582-590.
2.
BrentaniHPaulaCSBordiniD,et al.Autism spectrum disorders: an overview on diagnosis and treatment. Braz J Psychiatry. 2013;35(1):62-72.
3.
ZablotskyBBlackLIBlumbergSJ. Estimated prevalence of children with diagnosed developmental disabilities in the United States, 2014–2016. NCHS Data Brief. 2017;29(1):1-8.
4.
JunejaMSairamS.Autism Spectrum Disorder—An Indian Perspective. In Recent Advances in Autism. Smjournals; 2018.
5.
RudraABelmonteMKSoniPKBanerjeeSMukerjiSChakrabartiB. Prevalence of autism spectrum disorder and autistic symptoms in a school-based cohort of children in Kolkata, India (2017). Autism Res.2017;10(10):1597-1605.
6.
RainaSKChanderVBhardwajAK,et al.Prevalence of autism spectrum disorder among rural, urban, and tribal children (1–10 years of age). J Neurosci Rural Pract.2017;8(3):368-374.
7.
JunejaMMishraDRussellPS, et al.INCLEN diagnostic tool for autism spectrum disorder (INDT-ASD): development and validation. Indian Pediatr. 2014;51(5):359-365.
8.
MukherjeeSBAnejaSSharmaSSharmaM. Diagnostic accuracy of Indian scale for assessment of autism (ISAA) in children aged 2-9 years. Indian Pediatr. 2015;52(3):212-216.
9.
ShihabAIDawoodFAKashmarAH. Data analysis and classification of autism spectrum disorder using principal component analysis. Adv Bioinform. 2020;2020:1-9. Article ID 3407907. https://doi.org/10.1155/2020/3407907
10.
DvornekNCPamelaVKevinAPJamesSD. Identifying autism from resting-state fMRI using long short term memory networks. Mach Learn Med Imaging. 2017;10541:362-370. https://doi.org/10.1007/978-3-319-67389-9_42
CourchesneEPierceKSchumannCM,et al.Mapping early brain development in autism. Neuron. 2007;56(2):399-413.
13.
HazlettHCPoeMDGerigG,et al.Early brain overgrowth in autism associated with an increase in cortical surface area before age 2 years. Arch Gen Psychiatry. 2011;68(5):467-476.
14.
JustMKellerTAMalaveVLKanaRKVarmaS. Autism as a neural systems disorder: a theory of frontal-posterior underconnectivity. Neurosci Biobehav R. 2012;36(4):1292-1313.
15.
JesteSSFrohlichJLooSK. Electrophysiological biomarkers of diagnosis and outcome in neurodevelopmental disorders.Curr Opin Neurol. 2015;28(2):110-116.
16.
ZwaigenbaumLPennerM. Autism spectrum disorder: advances in diagnosis and evaluation. BMJ. 2018;361(8155):1-16. https://doi.org/10.1136/bmj.k1674
17.
BoslWJTager-FlusbergHNelsonCA. EEG analytics for early detection of autism spectrum disorder: A data-driven approach. Sci Rep. 2018;6828(2018):1-20.
18.
HeunisTAldrichCPetersJM,et al.Recurrence quantification analysis of resting state EEG signals in autism spectrum disorder – a systematic methodological exploration of technical and demographic confounders in the search for biomarkers. BMC Med. 2018;101(2018):1-17.
19.
TripathyRKAcharyaUR. Use of features from RR-time series and EEG signals for automated classification of sleep stages in deep neural network framework. BBE. 2018;38(4):890-902.
20.
NgamgaEJBialonskibSMarwanaNKurthsJGeierCLehnertzK. Evaluation of selected recurrence measures in discriminating pre-ictal and inter-ictal periods from epileptic EEG data. Phys. Lett. A. 2016;380(16):1419-1425.
21.
AbdossalehiMNasrabadiAM. Evaluating the determinism of brain signals using recurrence chaotic features in positive, negative and neutral emotional states in the sources achieved from ICA algorithm. ICNSJ. 2017;4(2):63-71.
22.
LiangZWangYRenY,et al.Detection of burst suppression patterns in EEG using recurrence rate. Sci. World J. 2014;2014:1-11. Article ID 295070. https://doi.org/10.1155/2014/295070
23.
BoslWJLoddenkemperTNelsonCA. Nonlinear EEG biomarker profiles for autism and absence epilepsy. Neuropsychiatr Electrophysiol2017;3(1):1-17. https://doi.org/10.1186/s40810-017-0023-x
24.
Al-nuaimiAHJammehESunLIfeachorE. Higuchi fractal dimension of the electroencephalogram as a biomarker for early detection of Alzheimer's disease. Annu Int Conf IEEE Eng Med Biol Soc. 2017;2017:2320-2324.
25.
OweisRJAbdulhayEW. Seizure classification in EEG signals utilizing Hilbert-Huang transform. BioMed Eng OnLine. 2011;38(2011):1-15.
26.
MirandaIMAranhaCLadeiraM. Classification of EEG signals using genetic programming for feature construction. GECCO. 2019;2019:1275-1283.
27.
SainiNBhardwajSAgarwalR. Classification of EEG signals using hybrid combination of features for lie detection. Neural Comput & Appl. 2020;32(1):3777-3787.
WebberCLMarwanN. Recurrence quantification analysis theory and best practices. Springer; 2015.
30.
WebberCLZbilutJP. Recurrence quantification analysis of nonlinear dynamical systems. In: RileyMAOrdenGC, eds. Tutorials in contemporary nonlinear methods for the behavioral sciences. Springer; 2014:26-95.
31.
AcharyaURVinithaSSChattopadhyaySYuWAlvinAPC. Application of recurrence quantification analysis for the automated identification of epileptic EEG signals. Int J Neural Syst. 2011;21(3):199-211.
32.
AkbarianBErfanianA. Automatic seizure detection based on nonlinear dynamical analysis of EEG signals and mutual information. Basic Clin Neurosci. 2018;9(4):227-240.
33.
LiXOuyangBGYaoXGuanX. Dynamical characteristics of pre-epileptic seizures in rats with recurrence quantification analysis. Phys Lett A. 2004;333(1):164-171.
34.
GruszczyńskaaIMosdorfaRSobaniecbPŻochowska-SobanieccM.Epilepsy identification based on EEG signal using RQA method. Adv Med Sci. 2019; 64(1):58-64.
35.
ShabaniHMikailiMNooriSMR. Assessment of recurrence quantification analysis (RQA) of EEG for development of a novel drowsiness detection system. Biomed Eng Lett. 2016;6(1):196-204.
36.
GómezGHInfanteOMartínez-GarcíaPLermaC. Analysis of diagonals in cross recurrence plots between heart rate and systolic blood pressure during supine position and active standing in healthy adults. Chaos. 2018;28(8):085704.
37.
AlmeidaTPSchlindweinFSSalinetJ, et al.Characterization of human persistent atrial fibrillation electrograms using recurrence quantification analysis. Chaos. 2018;28(8):085710.
38.
GroßekathöferUManyakovNVMihajlovicV, et al.Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis. Front. Neuroinform. 2017;11(9):1-16.
39.
MarhonSACameronCJFKremerSC. Recurrent Neural Networks. In: BianchiniMMagginiMJainL, eds. Handbook on Neural Information Processing. Intelligent Systems Reference Library. Springer; 2013. ISBN: 978-3-642-36657-4.
40.
LinY-SGauSS-FLeeC-C. An interlocutor-modulated attentional LSTM for differentiating between subgroups of autism spectrum disorder. Interspeech. 2018;1:1-6.
41.
CaretteRCiliaFDequenGBoscheJGuerinJLVandrommeL. Automatic Autism Spectrum Disorder Detection Thanks to Eye-Tracking and Neural Network-Based Approach. In: AhmedMBegumSFasquelJB, eds. Internet of Things (IoT) Technologies for HealthCare. Springer; 2018:75-81.
42.
MamunMAl-KadiMMarufuzzamanM. Effectiveness of wavelet denoising on electroencephalogram signals. JART. 2013;11(1):156-160.
43.
ChourasiaVSMittraAK. Selection of mother wavelet and denoising algorithm for analysis of foetal phonocardiographic signals. J Med Eng Technol. 2009;33(6):442-448.
44.
EckmannJPKamphorstSORuelleD. Recurrence plots of dynamical systems. EPL. 1987;4(9):973-977.
ZhengXChenWYouYJiangYLiMZhangT. Ensemble deep learning for automated visual classification using EEG signals. Pattern Recognit. 2020;102(7):107147. https://doi.org/10.1016/j.patcog.2019.107147
50.
MoinnereauM-ABrienneTBrodeurSRouatJWhittingstallKPlourdeE. Classification of auditory stimuli from EEG signals with a regulated recurrent neural network reservoir. ECSE. 2018;1:1-5. https://arxiv.org/pdf/1804.10322.pdf
51.
AlhagrySFahmyAAEl-KhoribiRA. Emotion recognition based on EEG using LSTM recurrent neural network. IJACSA. 2017;8(10):1-4.
52.
MichielliNAcharyaURMolinariF. Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals. Comput. Biol. Med. 2019;106(10):71-81. https://doi.org/10.1016/j.compbiomed.2019.01.013
53.
MarchiEFerroniGEybenFGabrielliLSquartiniSSchullerB. Multi-resolution linear prediction based features for audio onset detection with bidirectional LSTM neural networks. ICASSP. 2014;1:2164-2168. https://doi.org/10.1109/ICASSP.2014.6853982
54.
DonahueJHendricksLARohrbachM,et al.Long-term recurrent convolutional networks for visual recognition and description. CVPR. 2014;1(4):1-14. https://arxiv.org/pdf/1411.4389.pdf
GravesASchmidhuberJ. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. NNET. 2005;18(5):602-610.
57.
GlorotXBengioY. Understanding the difficulty of training deep feedforward neural networks. Proceedings of the thirteenth international conference on artificial intelligence and statistics. 2010;9:249-256. http://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf
58.
CuiZKeRPuZWangY. Stacked bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction. Machine Learning. 2020;1(118):1-24. https://arxiv.org/pdf/2005.11627.pdf
