Integrating Causal Inference with Graph Neural Networks for Alzheimer's Disease Analysis

TL;DR

This paper introduces Causal-GCN, a graph neural network framework that incorporates causal inference techniques to identify brain regions causally influencing Alzheimer's disease progression from MRI data.

Contribution

It integrates do-calculus-based causal adjustment into GNNs for more interpretable AD analysis, highlighting stable causal brain regions.

Findings

Achieves comparable classification performance to baseline GNNs.

Provides causal effect rankings consistent with known AD pathology.

Identifies posterior, cingulate, and insular regions as key causal hubs.

Abstract

Deep graph learning has advanced Alzheimer's (AD) disease classification from MRI, but most models remain correlational, confounding demographic and genetic factors with disease specific features. We present Causal-GCN, an interventional graph convolutional framework that integrates do-calculus-based back-door adjustment to identify brain regions exerting stable causal influence on AD progression. Each subject's MRI is represented as a structural connectome where nodes denote cortical and subcortical regions and edges encode anatomical connectivity. Confounders such as age, sec, and APOE4 genotype are summarized via principal components and included in the causal adjustment set. After training, interventions on individual regions are simulated by serving their incoming edges and altering node features to estimate average causal effects on disease probability. Applied to 484 subjects from the ADNI cohort, Causal-GCN achieves performance comparable to baseline GNNs while providing interpretable causal effect rankings that highlight posterior, cingulate, and insular hubs consistent with established AD neuropathology.