Estimating a Brain Network Predictive of Stress and Genotype with Supervised Autoencoders
This work addresses the challenge of improving brain stimulation treatments for mental illnesses like bipolar disorder, though it appears incremental as it builds on existing latent factor modeling with supervised autoencoders.
The authors tackled the problem of designing targeted brain stimulation protocols by identifying electrical dynamics across brain regions that relate to mental illness states, using supervised autoencoders to find a network associated with stress that characterizes a genotype linked to bipolar disorder, with the discovered network aligning with a previously used stimulation technique for experimental validation.
Targeted stimulation of the brain has the potential to treat mental illnesses. We propose an approach to help design the stimulation protocol by identifying electrical dynamics across many brain regions that relate to illness states. We model multi-region electrical activity as a superposition of activity from latent networks, where the weights on the latent networks relate to an outcome of interest. In order to improve on drawbacks of latent factor modeling in this context, we focus on supervised autoencoders (SAEs), which can improve predictive performance while maintaining a generative model. We explain why SAEs yield improved predictions, describe the distributional assumptions under which SAEs are an appropriate modeling choice, and provide modeling constraints to ensure biological relevance of the learned network. We use the analysis strategy to find a network associated with stress that characterizes a genotype associated with bipolar disorder. This discovered network aligns with a previously used stimulation technique, providing experimental validation of our approach.