Autism spectrum disorder classification using machine learning with factor analysis

Abstract

Due to the complexity and heterogeneity of autism spectrum disorder (ASD), diagnosis and categorization have attracted a lot of interest. To improve the robustness of ASD classification across the toddler age group, this work proposes an integrated strategy that integrates machine learning approaches with factor analysis and correlation validation. Benchmark dataset representing toddlers used to test this strategy’s efficiency. To first find the latent variables behind the ASD features in each dataset, factor analysis is used. We intend to capture the shared variance between variables and lower the dimensionality of the initial feature space by identifying these latent components. The subsequent machine-learning classification models used the retrieved components as input features. To validate the categorization results, correlation analyses were carried out in addition to factor analysis. The associations between the latent components discovered by factor analysis and the diagnostic labels were examined using Pearson correlation, a measure of linear association. The results highlight the method’s potential to improve diagnostic precision and shed light on the intricate connections between characteristics and diagnostic labels on the autism spectrum for toddlers.