LearnAD: Learning Interpretable Rules for Brain Networks in Alzheimer's Disease Classification

TL;DR

LearnAD is a neuro-symbolic approach that predicts Alzheimer's disease from MRI data using interpretable rules, combining statistical models and rule learning to enhance understanding and maintain competitive accuracy.

Contribution

It introduces a novel neuro-symbolic method that learns fully interpretable rules for Alzheimer's classification from brain MRI data, bridging statistical models and symbolic rule learning.

Findings

Outperforms Decision Trees in accuracy

Matches SVM performance, close to Random Forests and GNNs

Enhances interpretability without sacrificing accuracy

Abstract

We introduce LearnAD, a neuro-symbolic method for predicting Alzheimer's disease from brain magnetic resonance imaging data, learning fully interpretable rules. LearnAD applies statistical models, Decision Trees, Random Forests, or GNNs to identify relevant brain connections, and then employs FastLAS to learn global rules. Our best instance outperforms Decision Trees, matches Support Vector Machine accuracy, and performs only slightly below Random Forests and GNNs trained on all features, all while remaining fully interpretable. Ablation studies show that our neuro-symbolic approach improves interpretability with comparable performance to pure statistical models. LearnAD demonstrates how symbolic learning can deepen our understanding of GNN behaviour in clinical neuroscience.