Spectral analysis of light-adapted Electroretinograms in neurodevelopmental disorders: Classification with Machine Learning

Paul A Constable, Javier O Pinzon-Arenas, Luis Roberto Mercado Diaz, Irene O Lee, Fernando Marmolejo-Ramos, Lynne Loh, Aleksei Zhdanov, Mikhail Kulyabin, Marek Brabec, David H Skuse, Dorothy A Thompson, Hugo Posada-Quintero

Research output: Contribution to journalArticlepeer-review

25 Downloads (Pure)

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.
Original languageEnglish
Article number15
Number of pages30
JournalBioengineering
Volume12
Issue number1
Early online date28 Dec 2024
DOIs
Publication statusPublished - Jan 2025

Keywords

  • biomarker
  • retina
  • autism
  • attention deficit hyperactivity disorder
  • sex
  • medication
  • feature selection

Fingerprint

Dive into the research topics of 'Spectral analysis of light-adapted Electroretinograms in neurodevelopmental disorders: Classification with Machine Learning'. Together they form a unique fingerprint.

Cite this