Spectral Graph Sample Weighting for Interpretable Sub-cohort Analysis in Predictive Models for Neuroimaging

TL;DR

This paper introduces a spectral graph-based sample weighting method to improve interpretability and identify sub-cohorts in neuroimaging predictive models, addressing heterogeneity in brain disorder data.

Contribution

It proposes a novel spectral graph approach to model sample weights as a linear combination of eigenbases, enhancing interpretability and sub-cohort analysis in neuroimaging models.

Findings

Improved interpretability of sub-cohorts with distinct characteristics.

Enhanced model accuracy across different subgroups.

Effective identification of heterogeneity in neuroimaging data.

Abstract

Recent advancements in medicine have confirmed that brain disorders often comprise multiple subtypes of mechanisms, developmental trajectories, or severity levels. Such heterogeneity is often associated with demographic aspects (e.g., sex) or disease-related contributors (e.g., genetics). Thus, the predictive power of machine learning models used for symptom prediction varies across subjects based on such factors. To model this heterogeneity, one can assign each training sample a factor-dependent weight, which modulates the subject's contribution to the overall objective loss function. To this end, we propose to model the subject weights as a linear combination of the eigenbases of a spectral population graph that captures the similarity of factors across subjects. In doing so, the learned weights smoothly vary across the graph, highlighting sub-cohorts with high and low predictability. Our proposed sample weighting scheme is evaluated on two tasks. First, we predict initiation of heavy alcohol drinking in young adulthood from imaging and neuropsychological measures from the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA). Next, we detect Dementia vs. Mild Cognitive Impairment (MCI) using imaging and demographic measurements in subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Compared to existing sample weighting schemes, our sample weights improve interpretability and highlight sub-cohorts with distinct characteristics and varying model accuracy.