Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders: Classification with Machine Learning

Constable P, Pinzon-Arenas JO, Mercado Diaz LR, Lee I, Marmolejo-Ramos F, Loh L, Zhdanov A, Kulyabin M, Brabec M, Skuse D, Thompson DA, Posada-Quintero HF (2025)

Publication Language: English

Publication Type: Journal article, Original article

Publication year: 2025

Journal

Bioengineering MDPI

Book Volume: 12

Pages Range: 15

Article Number: 15

Journal Issue: 1

DOI: 10.3390/bioengineering12010015

Open Access Link: https://www.mdpi.com/2306-5354/12/1/15

Abstract

Electroretinograms (ERGs) show differences between typically developing populations and those with a diagnosis of autism spectrum disorder (ASD) or attention deficit/hyperactivity disorder (ADHD). In a series of ERGs collected in ASD (n = 77), ADHD (n = 43), ASD + ADHD (n = 21), and control (n = 137) groups, this analysis explores the use of machine learning and feature selection techniques to improve the classification between these clinically defined groups. Standard time domain and signal analysis features were evaluated in different machine learning models. For ASD classification, a balanced accuracy (BA) of 0.87 was achieved for male participants. For ADHD, a BA of 0.84 was achieved for female participants. When a three-group model (ASD, ADHD, and control) the BA was lower, at 0.70, and fell further to 0.53 when all groups were included (ASD, ADHD, ASD + ADHD, and control). The findings support a role for the ERG in establishing a broad two-group classification of ASD or ADHD, but the model’s performance depends upon sex and is limited when multiple classes are included in machine learning modeling.

Authors with CRIS profile

Mikhail Kulyabin Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

University College London (UCL) GB United Kingdom (GB) Flinders University AU Australia (AU) Ural Federal University B.N. Yeltsin RU Russian Federation (RU) University of Connecticut US United States (USA) (US) National Institute of Public Health (SZU) CZ Czech Republic (CZ)

How to cite

APA:

Constable, P., Pinzon-Arenas, J.O., Mercado Diaz, L.R., Lee, I., Marmolejo-Ramos, F., Loh, L.,... Posada-Quintero, H.F. (2024). Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders: Classification with Machine Learning. Bioengineering, 12(1), 15. https://doi.org/10.3390/bioengineering12010015

MLA:

Constable, Paul, et al. "Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders: Classification with Machine Learning." Bioengineering 12.1 (2024): 15.

BibTeX: Download