LearnAD: Learning Interpretable Rules for Brain Networks in Alzheimer's Disease Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914230980050944 |
|---|---|
| author | Andrews, Thomas Law, Mark Ahmadi-Abhari, Sara Russo, Alessandra |
| author_facet | Andrews, Thomas Law, Mark Ahmadi-Abhari, Sara Russo, Alessandra |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_00877 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LearnAD: Learning Interpretable Rules for Brain Networks in Alzheimer's Disease Classification Andrews, Thomas Law, Mark Ahmadi-Abhari, Sara Russo, Alessandra Machine Learning Artificial Intelligence 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. |
| title | LearnAD: Learning Interpretable Rules for Brain Networks in Alzheimer's Disease Classification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.00877 |