Traceable Drug Recommendation over Medical Knowledge Graphs
This addresses the need for interpretable drug recommendations for healthcare professionals, though it is incremental in improving transparency over existing deep learning methods.
The paper tackles the problem of drug recommendation systems lacking transparency by proposing TraceDR, a system that uses a medical knowledge graph to predict drug recommendations and related evidence simultaneously, achieving traceability and releasing a new large-scale testbed called DrugRec.
Drug recommendation (DR) systems aim to support healthcare professionals in selecting appropriate medications based on patients' medical conditions. State-of-the-art approaches utilize deep learning techniques for improving DR, but fall short in providing any insights on the derivation process of recommendations -- a critical limitation in such high-stake applications. We propose TraceDR, a novel DR system operating over a medical knowledge graph (MKG), which ensures access to large-scale and high-quality information. TraceDR simultaneously predicts drug recommendations and related evidence within a multi-task learning framework, enabling traceability of medication recommendations. For covering a more diverse set of diseases and drugs than existing works, we devise a framework for automatically constructing patient health records and release DrugRec, a new large-scale testbed for DR.