Robust features for the automatic identification of autism spectrum disorder in children

Journal of Neurodevelopmental Disorders

Simon Dennis¹  Mikhail Belkin²  Alison E Lane³  Justin Eldridge² 

[1] School of Psychology, University of Newcastle, University Drive, Callaghan NSW 2308, Australia;Department of Computer Science and Engineering, The Ohio State University, 395 Dreese Laboratories, 2015 Neil Avenue, Columbus OH, USA;School of Health Sciences, University of Newcastle, University Drive, Callaghan NSW 2308, Australia

关键词: Classification;    EEG;    Event-related potential;    Autism spectrum disorder;   

Others  :  803411
DOI  :  10.1186/1866-1955-6-12

 received in 2013-11-05, accepted in 2014-05-02,  发布年份 2014

【 摘 要 】

Background

It is commonly reported that children with autism spectrum disorder (ASD) exhibit hyper-reactivity or hypo-reactivity to sensory stimuli. Electroencephalography (EEG) is commonly used to study neural sensory reactivity, suggesting that statistical analysis of EEG recordings is a potential means of automatic classification of the disorder. EEG recordings taken from children, however, are frequently contaminated with large amounts of noise, making analysis difficult. In this paper, we present a method for the automatic extraction of noise-robust EEG features, which serve to quantify neural sensory reactivity. We show the efficacy of a system for the classification of ASD using these features.

Methods

An oddball paradigm was used to elicit event-related potentials from a group of 19 ASD children and 30 typically developing children. EEG recordings were taken and robust features were extracted. A support vector machine, logistic regression, and a naive Bayes classifier were used to classify the children as having ASD or being typically developing.

Results

A classification accuracy of 79% was achieved, making our method competitive with other automatic diagnosis methods based on EEG. Additionally, we found that classification performance is reduced if eye blink artifacts are removed during preprocessing.

Conclusions

This study shows that robust EEG features that quantify neural sensory reactivity are useful for the classification of ASD. We showed that noise-robust features are crucial for our analysis, and observe that traditional preprocessing methods may lead to poor classification performance in the face of a large amount of noise. Further exploration of alternative preprocessing methods is warranted.

【 授权许可】

   
2014 Eldridge et al.; licensee BioMed Central Ltd.

【 图 表 】

Figure 1.

Figure 2.

Figure 3.

Figure 4.

【 参考文献 】

• [1]Center for Disease Control and Prevention: Prevalence of autism spectrum disorders – autism and developmental disabilities monitoring network, 14 sites, United States, 2008. Surveill Summ 2008, 61(SS03):1-19.
• [2]Anderson KA, Shattuck PT, Cooper BP, Roux AM, Wagner M: Prevalence and correlates of postsecondary residential status among young adults with an autism spectrum disorder. Autism 2013. [http://aut.sagepub.com/content/early/2013/08/30/1362361313481860.full.pdf+html webcite]
• [3]Ben-Sasson A, Carter A, Briggs-Gowan M: Sensory over-responsivity in elementary school: prevalence and social-emotional correlates. J Abnorm Child Psychol 2009, 37(5):705-716.
• [4]Baker AE, Lane A, Angley MT, Young RL: The relationship between sensory processing patterns and behavioural responsiveness in autistic disorder: a pilot study. J Autism Dev Disord 2008, 38(5):867-875.
• [5]Klintwall L, Holm A, Eriksson M, Carlsson LH, Olsson MB, Hedvall Å, Gillberg C, Fernell E: Sensory abnormalities in autism: a brief report. Res Dev Disabil 2011, 32(2):795-800.
• [6]Tomchek SD, Dunn W: Sensory processing in children with and without autism: a comparative study using the short sensory profile. Am J Occup Ther 2007, 61(2):190-200.
• [7]Lane AE, Dennis SJ, Geraghty ME: Brief report: Further evidence of sensory subtypes in autism. J Autism Dev Disord 2011, 41(6):826-831.
• [8]Lane AE, Young RL, Baker AE, Angley MT: Sensory processing subtypes in autism: association with adaptive behavior. J Autism Dev Disord 2010, 40(1):112-122.
• [9]Lane A, Molloy C, Bishop S: Classification of children with autism spectrum disorder by sensory subtype: a case for sensory-based phenotypes. Autism Res 2014. [http://onlinelibrary.wiley.com/doi/10.1002/aur.1368/full webcite]
• [10]Jeste SS, Nelson III CA: Event related potentials in the understanding of autism spectrum disorders: an analytical review. J Autism Dev Disord 2009, 39(3):495-510.
• [11]Marco EJ, Hinkley LB, Hill SS, Nagarajan SS: Sensory processing in autism: a review of neurophysiologic findings. Pediatr Res 2011, 69:48-54.
• [12]Duffy FH, Als H: A stable pattern of EEG spectral coherence distinguishes children with autism from neuro-typical controls – a large case control study. BMC Med 2012, 10(1):64. BioMed Central Full Text
• [13]Murias M, Webb SJ, Greenson J, Dawson G: Resting state cortical connectivity reflected in EEG coherence in individuals with autism. Biol Psychiatry 2007, 62(3):270-273.
• [14]Coben R, Clarke AR, Hudspeth W, Barry RJ: EEG power and coherence in autistic spectrum disorder. Clin Neurophysiol 2008, 119(5):1002-1009.
• [15]Isler J, Martien K, Grieve P, Stark R, Herbert M: Reduced functional connectivity in visual evoked potentials in children with autism spectrum disorder. Clin Neurophysiol 2010, 121(12):2035-2043.
• [16]Bosl W, Tierney A, Tager-Flusberg H, Nelson C: EEG complexity as a biomarker for autism spectrum disorder risk. BMC Med 2011, 9(1):18. BioMed Central Full Text
• [17]Luck SJ: An Introduction to the Event-related Potential Technique. Cognitive Neuroscience . Boston: MIT Press; 2005.
• [18]Handy TC: Event-related Potentials: A Methods Handbook . Boston: MIT Press; 2005.
• [19]Junghöfer M, Elbert T, Tucker DM, Rockstroh B: Statistical control of artifacts in dense array EEG/MEG studies. Psychophysiology 2000, 37(4):523-532.
• [20]Jung T-P, Makeig S, Humphries C, Lee T-W, Mckeown MJ, Iragui V, Sejnowski TJ: Removing electroencephalographic artifacts by blind source separation. Psychophysiology 2000, 37(2):163-178.
• [21]Cruz AA, Garcia DM, Pinto CT, Cechetti SP: Spontaneous eyeblink activity. Ocul Surf 2011, 9(1):29-41.
• [22]Goldberg TE, Maltz A, Bow JN, Karson CN, Leleszi JP: Blink rate abnormalities in autistic and mentally retarded children relationship to dopaminergic activity. J Am Acad Child Adolesc Psychiatry 1987, 26(3):336-338.
• [23]Caplan R, Guthrie D, Komo S: Blink rate in children with attention-deficit-hyperactivity disorder. Biol Psychiatry 1996, 39(12):1032-1038.
• [24]ResearchMatch [https://www.researchmatch.org webcite]
• [25]Lord C, Risi S, Lambrecht L, Leventhal BL, DiLavore PC, Pickles A, Rutter M, Cook, EH Jr: The autism diagnostic observation schedule – generic: a standard measure of social and communication deficits associated with the spectrum of autism. J Autism Dev Disord 2000, 30(3):205-223.
• [26]Schopler E, Wellman GJ, Love SR, Van Bourgondien, ME: Childhood Autism Rating Scale, Second Edition (CARS2) . Los Angeles: WPS; 2010.
• [27]Garfin DG, McCallon D: Validity and reliability of the childhood autism rating scale with autistic adolescents. J Autism Dev Disord 1988, 18(3):367-378.
• [28]Schopler E, Reichler R, Renner B: Child Autism Rating Scale . Los Angeles: WPS; 1988.
• [29]Eaves RC, Milner B: The criterion-related validity of the childhood autism rating scale and the autism behavior checklist. J Abnorm Child Psychol 1993, 21(5):481-491.
• [30]Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E: Scikit-learn: machine learning in Python. J Mach Learn Res 2011, 12:2825-2830.
• [31]Theodoridis S, Koutroumbas K: Pattern Recognition . Burlington: Academic Press; 2008.
• [32]Gotham K, Risi S, Pickles A, Lord C: The autism diagnostic observation schedule: revised algorithms for improved diagnostic validity. J Autism Dev Disord 2007, 37(4):613-627.
• [33]Hand DJ: Classifier technology and the illusion of progress. Stat Sci 2006, 21(1):1-14.