AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicine
This addresses the problem of inefficient manual feature selection for graph construction in clinical prediction tasks, offering a scalable solution for complex diseases.
The paper tackles the challenge of automatically selecting edge features for constructing patient similarity graphs in personalized medicine, proposing AdaMedGraph which uses adaptive boosting with multiple graphs to train GNNs and achieves superior performance on two real-world medical scenarios.
Precision medicine tailored to individual patients has gained significant attention in recent times. Machine learning techniques are now employed to process personalized data from various sources, including images, genetics, and assessments. These techniques have demonstrated good outcomes in many clinical prediction tasks. Notably, the approach of constructing graphs by linking similar patients and then applying graph neural networks (GNNs) stands out, because related information from analogous patients are aggregated and considered for prediction. However, selecting the appropriate edge feature to define patient similarity and construct the graph is challenging, given that each patient is depicted by high-dimensional features from diverse sources. Previous studies rely on human expertise to select the edge feature, which is neither scalable nor efficient in pinpointing crucial edge features for complex diseases. In this paper, we propose a novel algorithm named \ours, which can automatically select important features to construct multiple patient similarity graphs, and train GNNs based on these graphs as weak learners in adaptive boosting. \ours{} is evaluated on two real-world medical scenarios and shows superiors performance.