Adversarial Factor Models for the Generation of Improved Autism Diagnostic Biomarkers
This work addresses the need for more reliable biomarkers for autism spectrum disorder diagnosis, which is incremental in applying adversarial methods to this domain.
The paper tackled the problem of improving autism diagnostic biomarkers by using adversarial linear factor models to remove confounding information and learn disentangled multimodal representations, resulting in increased predictive performance.
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.