Bayesian Models of Functional Connectomics and Behavior
This work addresses the problem of predicting behavior from connectivity data in data-starved clinical settings, such as for rare disorders, but it appears incremental as it builds on existing Bayesian methods.
The authors tackled the challenge of jointly analyzing functional connectomics and behavioral data in clinical rs-fMRI studies with limited samples, such as in Autism Spectrum Disorder, by developing a Bayesian modeling approach for joint representation learning and prediction, showing preliminary results on a public dataset.
The problem of jointly analysing functional connectomics and behavioral data is extremely challenging owing to the complex interactions between the two domains. In addition, clinical rs-fMRI studies often have to contend with limited samples, especially in the case of rare disorders. This data-starved regimen can severely restrict the reliability of classical machine learning or deep learning designed to predict behavior from connectivity data. In this work, we approach this problem from the lens of representation learning and bayesian modeling. To model the distributional characteristics of the domains, we first examine the ability of approaches such as Bayesian Linear Regression, Stochastic Search Variable Selection after performing a classical covariance decomposition. Finally, we present a fully bayesian formulation for joint representation learning and prediction. We present preliminary results on a subset of a publicly available clinical rs-fMRI study on patients with Autism Spectrum Disorder.