Next Article in Journal
Bi-Temporal Anodal Transcranial Direct Current Stimulation during Slow-Wave Sleep Boosts Slow-Wave Density but Not Memory Consolidation
Next Article in Special Issue
The Effect of Acceptance and Commitment Therapy for Improving Psychological Well-Being in Parents of Individuals with Autism Spectrum Disorders: A Randomized Controlled Trial
Previous Article in Journal
Paediatricians’ Views on Pain in Children with Profound Intellectual and Multiple Disabilities
Previous Article in Special Issue
Documentary Analysis of the Scientific Literature on Autism and Technology in Web of Science
Article

Use of Empirical Mode Decomposition in ERP Analysis to Classify Familial Risk and Diagnostic Outcomes for Autism Spectrum Disorder

1
Montreal Neurological Institute, McGill University, Montreal, QC H3A 2B4, Canada
2
Cognitive and Affective Neuroscience Lab, Brock University, St. Catharines, ON L2S 3A1, Canada
*
Author to whom correspondence should be addressed.
Academic Editor: Antonio Narzisi
Brain Sci. 2021, 11(4), 409; https://doi.org/10.3390/brainsci11040409
Received: 16 February 2021 / Revised: 17 March 2021 / Accepted: 18 March 2021 / Published: 24 March 2021
(This article belongs to the Special Issue Advances in Autism Research: Series II)
Event-related potentials (ERPs) activated by faces and gaze processing are found in individuals with autism spectrum disorder (ASD) in the early stages of their development and may serve as a putative biomarker to supplement behavioral diagnosis. We present a novel approach to the classification of visual ERPs collected from 6-month-old infants using intrinsic mode functions (IMFs) derived from empirical mode decomposition (EMD). Selected features were used as inputs to two machine learning methods (support vector machines and k-nearest neighbors (k-NN)) using nested cross validation. Different runs were executed for the modelling and classification of the participants in the control and high-risk (HR) groups and the classification of diagnosis outcome within the high-risk group: HR-ASD and HR-noASD. The highest accuracy in the classification of familial risk was 88.44%, achieved using a support vector machine (SVM). A maximum accuracy of 74.00% for classifying infants at risk who go on to develop ASD vs. those who do not was achieved through k-NN. IMF-based extracted features were highly effective in classifying infants by risk status, but less effective by diagnostic outcome. Advanced signal analysis of ERPs integrated with machine learning may be considered a first step toward the development of an early biomarker for ASD. View Full-Text
Keywords: autism spectrum disorder; event-related potential; empirical mode decomposition; intrinsic mode functions; support vector machine; k-nearest neighbor autism spectrum disorder; event-related potential; empirical mode decomposition; intrinsic mode functions; support vector machine; k-nearest neighbor
Show Figures

Figure 1

MDPI and ACS Style

Abou-Abbas, L.; van Noordt, S.; Desjardins, J.A.; Cichonski, M.; Elsabbagh, M. Use of Empirical Mode Decomposition in ERP Analysis to Classify Familial Risk and Diagnostic Outcomes for Autism Spectrum Disorder. Brain Sci. 2021, 11, 409. https://doi.org/10.3390/brainsci11040409

AMA Style

Abou-Abbas L, van Noordt S, Desjardins JA, Cichonski M, Elsabbagh M. Use of Empirical Mode Decomposition in ERP Analysis to Classify Familial Risk and Diagnostic Outcomes for Autism Spectrum Disorder. Brain Sciences. 2021; 11(4):409. https://doi.org/10.3390/brainsci11040409

Chicago/Turabian Style

Abou-Abbas, Lina, Stefon van Noordt, James A. Desjardins, Mike Cichonski, and Mayada Elsabbagh. 2021. "Use of Empirical Mode Decomposition in ERP Analysis to Classify Familial Risk and Diagnostic Outcomes for Autism Spectrum Disorder" Brain Sciences 11, no. 4: 409. https://doi.org/10.3390/brainsci11040409

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop