A team of Jordan University of Science & Technology (JUST) has proposed a new method based on empirical mode decomposition (EMD), second-order difference plotting (SODP) introduced and applied to analyze the nonlinear and nonstationary resting-state EEG data recorded for 36 children with mild and severe ASD. Artificial neural network (ANN) then used to determine the accuracy of this models outcome measures in distinguishing between the two ASD groups.
Several EMD & SODP outcome measures were obtained from children EEG data including intrinsic mode functions (IMFs) features, SODP patterns, elliptical area, and central tendency measure (CTM) values.
Our results showed that children with severe 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.
In addition, the Artificial Neuronal Network (ANN) ended with model sensitivity and specificity of 100% and 94.7%, respectively, and 97.2% overall accuracy of distinguishing between ASD groups.
In conclusion, this study introduced a new EMD model application that could serve as a promising and a sensitive automated diagnostic tool to distinguish between and to identify the ASD severity levels in children with ASD.
This research was carried out by Dr. Hikmat Hadoush, Dr. Maha Alafeef, and Dr. Enas Abdulhay.
Here is the link to “Automated identification for autism severity level: EEG analysis using empirical mode decomposition and second order difference plot”: https://www.sciencedirect.com/science/article/pii/S0166432818313251