In our recent publication in the Journal of Autism and Developmental Disorders which can be accessed here: Article we explored the potential of using 2 flash strengths to classify ASD, ADHD and control participants.
Manjur, S. M., Diaz, L. R. M., Lee, I. O., Skuse, D. H., Thompson, D. A., Marmolejos-Ramos, F., Constable, P. A., & Posada-Quintero, H. F. (2024). Detecting Autism Spectrum Disorder and Attention Deficit Hyperactivity Disorder Using Multimodal Time-Frequency Analysis with Machine Learning Using the Electroretinogram from Two Flash Strengths. Journal of Autism and Developmental Disorders.
By exploring different energies within frequency bands differences between the groups were evaluated using machine learning models. The overall best accurracy of 70% was achieved between the 3 groups using the stronger flash strength in the values from the right eye with features from variable frequency complex demodulation prooving superior, in this case, to DWT or time domain based features.
Further work will explore using a wider range of flash strengths to improve classification
Comments