IA-GCN: Interpretable Attention Based Graph Convolutional Network for Disease Prediction
Authors:
- 15 October 2023
- book chapter
- Published by Springer Nature
- Vol. 14348, 382-392
Abstract
Interpretability in Graph Convolutional Networks (GCNs) has been explored to some extent in general in computer vision; yet, in the medical domain, it requires further examination. Most of the interpretability approaches for GCNs, especially in the medical domain, focus on interpreting the output of the model in a post-hoc fashion. In this paper, we propose an interpretable attention module (IAM) that explains the relevance of the input features to the classification task on a GNN Model. The model uses these interpretations to improve its performance. In a clinical scenario, such a model can assist the clinical experts in better decision-making for diagnosis and treatment planning. The main novelty lies in the IAM, which directly operates on input features. IAM learns the attention for each feature based on the unique interpretability-specific losses. We show the application of our model on two publicly available datasets, Tadpole and the UK Biobank (UKBB). For Tadpole we choose the task of disease classification, and for UKBB, age, and sex prediction. The proposed model achieves an increase in an average accuracy of 3.2% for Tadpole and 1.6% for UKBB sex and 2% for the UKBB age prediction task compared to the state-of-the-art. Further, we show exhaustive validation and clinical interpretation of our results. Keywords Interpretability Graph Convolutional Network Disease predictionKeywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Interpretability of machine learning‐based prediction models in healthcareWIREs Data Mining and Knowledge Discovery, 2020
- BrainGNN: Interpretable Brain Graph Neural Network for fMRI AnalysisbioRxiv, 2020
- Predicting Brain Age of Healthy Adults Based on Structural MRI Parcellation Using Convolutional Neural NetworksFrontiers in Neurology, 2020
- Development of a targeted client communication intervention to women using an electronic maternal and child health registry: a qualitative studyBMC Medical Informatics and Decision Making, 2020
- Dynamic Graph CNN for Learning on Point CloudsACM Transactions on Graphics, 2019
- Spectral Graph Convolutions for Population-Based Disease Prediction2017
- Multimodal population brain imaging in the UK Biobank prospective epidemiological studyNature Neuroscience, 2016
- Biomarker Modeling of Alzheimer’s DiseaseNeuron, 2013
- Staging Dementia Using Clinical Dementia Rating Scale Sum of Boxes ScoresArchives of Neurology, 2008
- Ridge Regression: Biased Estimation for Nonorthogonal ProblemsTechnometrics, 1970