Objective: Identification of drugs, associated medication entities and interactions between them are crucial to prevent unwanted effects of drug therapy, known as Adverse Drug Events (ADEs). This paper describes our participation to the n2c2 shared-task in extracting relations between medication-related entities in Electronic Health Records (EHRs).
Materials and Methods: We proposed an ensemble approach for relation extraction and classification between drugs and medication-related entities. We incorporated state-of-the-art NER models based on BiLSTM networks and CRFs for end-to-end extraction. We additionally developed separate models for intra- and inter-sentence relation extraction and combined them using an ensemble method. The intra-sentence models rely on BiLSTMs and attention mechanisms and are able to capture dependencies between multiple related pairs in the same sentence. For the inter-sentence relations, we adopted a neural architecture that utilizes the Transformer network to improve performance in longer sequences.
Results: Our team ranked third with a micro-averaged F1-score of 94.72% and 87.65% for relation and end-to-end relation extraction respectively (Track 2 and 3). Our ensemble effectively takes advantages from our proposed models. Analysis of the reported results indicated that our proposed approach is more generalizable than the top performing system, which employs additional training data and corpus-driven processing techniques.
Conclusions: We proposed a relation extraction system to identify relations between drugs and medication-related entities. The proposed approach is independent of external syntactic tools. Analysis showed that by using latent Drug-Drug interactions we were able to significantly improve the performance of non-Drug–Drug pairs in EHRs.