Biomarker Discovery for Autism Prediction Using Massive Feature Extraction Based on EEG Signals
Open Access
Abstract
Autism spectrum disorder (ASD) is a heterogeneous neurodevelopmental disorder that requires early diagnosis for better intervention. However, current clinical behavioural examinations are time-consuming and prone to human error. Objective and effective biomarkers are essential for the diagnosis and prognosis of the disorder. Electroencephalography (EEG) is a non-invasive and inexpensive brain-imaging technique that is widely applied in the diagnosis of ASD. Feature-based methods have shown better performance in EEG-based applications. Here, we present a prediction framework based on massive feature extraction using the highly comparative time-series analysis (HCTSA) method and a hybrid feature selection method for the classification of ASD from resting-state EEG. Machine-learning models are trained and tested on a different number of selected features. Our models demonstrated 100% accuracy with ≥50 features on a balanced dataset of 56 participants. The most discriminating EEG channels and features were used in the prediction process, as well as those using Shapley values to provide explainability of our framework. Whilst these results are promising, we acknowledge the limitations of a single small-scale dataset and emphasise the need for validation on larger independent cohorts before clinical translation.Keywords
This publication has 45 references indexed in Scilit:
- Synergizing DeepSeek's artificial intelligence innovations with brain–computer interfacesBrain‐X, 2025
- A hybrid graph network model for ASD diagnosis based on resting-state EEG signalsBrain Research Bulletin, 2023
- Autism spectrum disorder prediction using bidirectional stacked gated recurrent unit with time-distributor wrapper: an EEG studyNeural Computing and Applications, 2023
- A novel automated autism spectrum disorder detection systemComplex & Intelligent Systems, 2021
- Establishment of Best Practices for Evidence for PredictionJAMA Psychiatry, 2020
- hctsa : A Computational Framework for Automated Time-Series Phenotyping Using Massive Feature ExtractionCell Systems, 2017
- The Influence of Demographic Factors on the Identification of Autism Spectrum Disorder: A Review and Call for ResearchReview Journal of Autism and Developmental Disorders, 2015
- Altered white matter connectivity as a neural substrate for social impairment in Autism Spectrum DisorderCortex, 2015
- Review of advanced techniques for the estimation of brain connectivity measured with EEG/MEGComputers in Biology and Medicine, 2011
- Spherical splines for scalp potential and current density mappingElectroencephalography and Clinical Neurophysiology, 1989