Automated identification for autism severity level: EEG analysis using empirical mode decomposition and second order difference plot

Publication date: Available online 11 January 2019

Source: Behavioural Brain Research

Author(s): Hikmat Hadoush, Maha Alafeef, Enas Abdulhay

Abstract

Background

Previous automated EEG-based diagnosis of autism spectrum disorders (ASD) using various nonlinear EEG analysis methods were limited to distinguish only children with ASD from those normally developed without approaching their autistic features severity.

Objectives

Identifying potential differences between children with mild and sever ASD based on EEG analysis using empirical mode decomposition (EMD) and second-order difference plot (SODP) models, and determining the accuracy of such model outcome measures to distinguish ASD severity levels.

Methods

Resting-state EEG data recorded for 36 children, who divided equally into two matched groups of mild and sever ASD. EMD analysis was applied to their EEG data to identify intrinsic mode functions (IMFs) features, SODP patterns, elliptical area and central tendency measure (CTM) values. Artificial neural network then used to determine the accuracy of this models outcome measures in distinguishing between the two ASD groups.

Results

Children with sever ASD showed smaller, less twitches and oscillation of IMFs features, more stochastic SODP plotting, less CTM values, and higher ellipse area values compared to the children with mild ASD, which indicates their greater EEG variabilities and their greater inability to suppress their improper behavior. ANN ended with model sensitivity and specificity of 100% and 94.7%, respectively, and 97.2% overall accuracy of distinguishing between ASD groups.

Conclusion

Children with sever and mild ASD had different IMFs features, SODP plotting, elliptical area and CTM values. In addition, these EMD outcome measures could serve as a sensitive automated tool to distinguish different severity levels in children with ASD.

from A via a.sfakia on Inoreader http://bit.ly/2VO0AD2