Demographic-Guided Attention in Recurrent Neural Networks for Modeling Neuropathophysiological Heterogeneity

TL;DR

This paper introduces a demographic-guided attention mechanism in recurrent neural networks to better model individual differences in brain functional networks from fMRI data, improving classification accuracy and interpretability.

Contribution

It presents a novel demographic-guided attention mechanism for RNNs that enhances modeling of heterogeneity in neurological disorder data from fMRI scans.

Findings

Improved classification accuracy on ABIDE I dataset subsets.

Enhanced generalizability through leave-one-site-out validation.

Ability to interpret functional network differences based on demographics.

Abstract

Heterogeneous presentation of a neurological disorder suggests potential differences in the underlying pathophysiological changes that occur in the brain. We propose to model heterogeneous patterns of functional network differences using a demographic-guided attention (DGA) mechanism for recurrent neural network models for prediction from functional magnetic resonance imaging (fMRI) time-series data. The context computed from the DGA head is used to help focus on the appropriate functional networks based on individual demographic information. We demonstrate improved classification on 3 subsets of the ABIDE I dataset used in published studies that have previously produced state-of-the-art results, evaluating performance under a leave-one-site-out cross-validation framework for better generalizeability to new data. Finally, we provide examples of interpreting functional network differences based on individual demographic variables.