ERG-Graph: Graph Signal Processing of the Electroretinogram for Classification of Neurodevelopmental Disorders
< 0.001; Cliff's delta: large effect sizes), and SHAP analysis revealed that graph-theoretic features dominated the top-ranked predictors. These results demonstrate that graph-based topological features capture discriminative information in the ERG waveform that is inaccessible to conventional signal analysis methods, advancing the development of objective biomarkers for neurodevelopmental disorder screening.
Authors
- Hugo Fernando Posada-Quintero (ORCID: https://orcid.org/0000-0003-4514-4772)
- Luís Roberto Mercado Díaz (ORCID: https://orcid.org/0000-0003-3543-3677)
- Paul A. Constable (ORCID: https://orcid.org/0000-0002-3994-1700)
- Javier O. Pinzón-Arenas (ORCID: https://orcid.org/0000-0001-8521-2077)
- Lynne Loh (ORCID: https://orcid.org/0000-0002-1357-9395)
- Irene O. Lee
Institutions
- University of Connecticut (US)
- Flinders University (AU)
- Great Ormond Street Hospital (GB)
- Great Ormond Street Hospital for Children NHS Foundation Trust (GB)
- Institute of Child Health (IN)
- Institute of Child Health (GR)
- University College London (GB)
Publication Details
- Journal
- Bioengineering
- Published
- 2026-04-11
- DOI
- https://doi.org/10.3390/bioengineering13040446
- Primary Topic
- Autism Spectrum Disorder Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00