Related Experiment Video
Updated: Jan 16, 2026
11:15
Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
Published on: June 27, 2013
34.4K
Entropy and Complexity in QEEG Reveal Visual Processing Signatures in Autism: A Neurofeedback-Oriented and Clinical
Aleksandar Tenev1, Silvana Markovska-Simoska2, Andreas Müller3
1Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University of Skopje, 1000 Skopje, North Macedonia.
Brain Sciences
|September 27, 2025
Summary
Nonlinear quantitative EEG (qEEG) metrics effectively distinguish children with autism spectrum disorder (ASD) from typically developing peers. These findings highlight potential neurophysiological biomarkers for guiding personalized neurofeedback interventions in ASD.
Area of Science:
- Neuroscience
- Biomarkers
- Quantitative Electroencephalography (qEEG)
Background:
- Quantitative EEG (qEEG) shows promise for identifying neurophysiological biomarkers in psychiatric disorders.
- Nonlinear qEEG metrics may offer objective measures for guiding neurofeedback interventions.
Purpose of the Study:
- To determine if nonlinear qEEG metrics (Lempel-Ziv Complexity, Tsallis Entropy, Renyi Entropy) can differentiate children with autism spectrum disorder (ASD) from typically developing (TD) peers.
- To assess the relevance of these metrics for neurofeedback targeting in ASD.
Main Methods:
- EEG data from 19 scalp channels were analyzed in children with ASD and TD.
- Three nonlinear qEEG metrics were computed, and group differences were statistically evaluated.
- Machine learning classifiers and t-distributed Stochastic Neighbor Embedding (t-SNE) were used for discriminative analysis and visualization.
Main Results:
- All nonlinear metrics demonstrated significant group differences across multiple EEG channels.
- Machine learning classifiers achieved over 90% accuracy in distinguishing ASD from TD.
- t-SNE visualization revealed distinct clustering for ASD and TD groups, with visual processing channels being key contributors.
Conclusions:
- Nonlinear qEEG metrics, especially from visual processing regions, accurately differentiate ASD from TD.
- These metrics show potential as objective biomarkers for neurofeedback in ASD.
- Integrating complexity and entropy measures with machine learning offers a framework for ASD diagnosis and personalized intervention planning.
