Cross-Global Attention Graph Kernel Network Prediction of Drug Prescription

Abstract

We present an end-to-end, interpretable, deep-learning architecture to learn a graph kernel that predicts the outcome of chronic disease drug prescription. This is achieved through a deep metric learning collaborative with a Support Vector Machine objective using a graphical representation of Electronic Health Records. We formulate the predictive model as a binary graph classification problem with an adaptive learned graph kernel through novel cross-global attention node matching between patient graphs, simultaneously computing on multiple graphs without training pair or triplet generation. Results using the Taiwanese National Health Insurance Research Database demonstrate that our approach outperforms current start-of-the-art models both in terms of accuracy and interpretability.

ACM-BCB 2020 (Full paper)

References in corpus (5)

• Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks
• Graph Matching Networks for Learning the Similarity of Graph Structured Objects
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
• Exploiting Convolutional Neural Network for Risk Prediction with Medical Feature Embedding
• Mining Electronic Health Records: A Survey

Cited by in corpus (1)

• The Analysis from Nonlinear Distance Metric to Kernel-based Drug Prescription Prediction System