Adversarial Factor Models for the Generation of Improved Autism Diagnostic Biomarkers

TL;DR

This paper introduces adversarial linear factor models to enhance autism biomarkers by removing confounds and learning disentangled representations, leading to improved diagnostic accuracy.

Contribution

It presents a novel application of adversarial linear factor models for confound removal and representation learning in ASD biomarker development.

Findings

Confound removal from biomarkers using adversarial models

Disentangled multimodal biomarker representations

Improved predictive performance for ASD diagnosis

Abstract

Discovering reliable measures that inform on autism spectrum disorder (ASD) diagnosis is critical for providing appropriate and timely treatment for this neurodevelopmental disorder. In this work we present applications of adversarial linear factor models in the creation of improved biomarkers for ASD diagnosis. First, we demonstrate that an adversarial linear factor model can be used to remove confounding information from our biomarkers, ensuring that they contain only pertinent information on ASD. Second, we show this same model can be used to learn a disentangled representation of multimodal biomarkers that results in an increase in predictive performance. These results demonstrate that adversarial methods can address both biomarker confounds and improve biomarker predictive performance.