Cross-Global Attention Graph Kernel Network Prediction of Drug Prescription

TL;DR

This paper introduces a deep learning model that predicts drug prescriptions for chronic diseases by learning an interpretable graph kernel from electronic health records, outperforming existing models.

Contribution

It proposes a novel cross-global attention graph kernel network that enables adaptive graph matching and prediction without pairwise training, enhancing accuracy and interpretability.

Findings

Outperforms state-of-the-art models in accuracy.

Provides interpretable predictions for drug prescriptions.

Effective on Taiwanese National Health Insurance data.

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.