Cross-Global Attention Graph Kernel Network Prediction of Drug Prescription
This work addresses drug prescription prediction for chronic disease patients, offering improved accuracy and interpretability over existing methods.
The authors tackled the problem of predicting chronic disease drug prescription outcomes by developing an end-to-end deep learning architecture that learns an adaptive graph kernel from Electronic Health Records. Their method outperformed state-of-the-art models in accuracy and interpretability on the Taiwanese National Health Insurance Research Database.
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.