| Autor: |
Kim M; Department of Artificial Intelligence, Catholic University of Korea, Bucheon, South Korea., Kim J; Department of Computer Engineering, Ajou University, Suwon, South Korea., Qu J; School of Engineering and Applied Sciences, University of Pennsylvania, Philadelphia, USA., Huang H; Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, USA., Long Q; Department of Biostatistics, Epidemiology & Informatics, University of Pennsylvania, Philadelphia, USA., Sohn KA; Department of Artificial Intelligence, Ajou University, Suwon, South Korea., Kim D; Department of Biostatistics, Epidemiology & Informatics, University of Pennsylvania, Philadelphia, USA., Shen L; Department of Biostatistics, Epidemiology & Informatics, University of Pennsylvania, Philadelphia, USA. |
| Abstrakt: |
Alzheimer's disease (AD) is a progressive neurodegenerative brain disorder characterized by memory loss and cognitive decline. Early detection and accurate prognosis of AD is an important research topic, and numerous machine learning methods have been proposed to solve this problem. However, traditional machine learning models are facing challenges in effectively integrating longitudinal neuroimaging data and biologically meaningful structure and knowledge to build accurate and interpretable prognostic predictors. To bridge this gap, we propose an interpretable graph neural network (GNN) model for AD prognostic prediction based on longitudinal neuroimaging data while embracing the valuable knowledge of structural brain connectivity. In our empirical study, we demonstrate that 1) the proposed model outperforms several competing models (i.e., DNN, SVM) in terms of prognostic prediction accuracy, and 2) our model can capture neuroanatomical contribution to the prognostic predictor and yield biologically meaningful interpretation to facilitate better mechanistic understanding of the Alzheimer's disease. Source code is available at https://github.com/JaesikKim/temporal-GNN. |
