Integrating Causal Inference with Graph Neural Networks for Alzheimer's Disease Analysis
This work addresses the challenge of distinguishing causal from correlational features in Alzheimer's disease analysis for medical researchers, representing an incremental improvement by adding causal adjustment to existing graph-based methods.
The paper tackled the problem of confounding factors in Alzheimer's disease classification from MRI data by developing Causal-GCN, a framework that integrates causal inference with graph neural networks to identify brain regions with stable causal influence on disease progression, achieving performance comparable to baseline GNNs on 484 subjects from the ADNI cohort.
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.