Computer-aided autism diagnosis via second-order difference plot area applied to EEG empirical mode decomposition
Autism spectrum disorder (ASD) is a name for a group of neurodevelopmental conditions that are characterized by some degree of impairment in social interaction, verbal and non-verbal communication, and difficulty in symbolic capacity and repetitive behaviors. The only protocol followed currently for...
Gespeichert in:
Veröffentlicht in: | Neural computing & applications 2020-08, Vol.32 (15), p.10947-10956 |
---|---|
Hauptverfasser: | , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Autism spectrum disorder (ASD) is a name for a group of neurodevelopmental conditions that are characterized by some degree of impairment in social interaction, verbal and non-verbal communication, and difficulty in symbolic capacity and repetitive behaviors. The only protocol followed currently for ASD diagnosis is the qualitative behavioral assessment by experts through internationally established descriptive scaling standards. The assessment can, therefore, be affected by the degree of the evaluator experience as well as by the level of the descriptive standard robustness. This paper presents an EEG-based quantitative approach intended for automatic discrimination between children with typical neurodevelopment and children with ASD. The suggested work relies on second-order difference plot (SODP) area as a discriminative feature: First, every EEG channel in a 64 electrode cap—for every volunteer—is decomposed into intrinsic mode functions (IMFs) by empirical mode decomposition (EMD). Next, the second-order difference plot for the first ten intrinsic mode functions—of every channel—is sketched. Third, the value of the elliptical area —for every plot—is calculated. The 95% confidence ellipse area is used as the discriminative feature. Fourth, paired
t
-student test is applied to the vectors consisting of discriminative feature values for counterpart channels/IMFs (e.g., channel FPz/IMF7 in autistic and neurotypical) for all volunteers. Finally, principal component analysis (PCA) and neural network (NN) are applied to the SODP area feature matrix for two-class classification (ASD and neurotypical). Moreover, the 3D mapping of EEG SODP area values was implemented and analyzed. The obtained results show that the conducted
t
-student tests yield values of less than 0.05, and that the NN two-class classification based on SODP features leads to a 94.4% accuracy, which indicates significant differences between SODP area values of children with neurotypical development and those diagnosed with ASD. The obtained results have also been emphasized by the analysis of the findings of the performed 3D mapping. |
---|---|
ISSN: | 0941-0643 1433-3058 |
DOI: | 10.1007/s00521-018-3738-0 |