Adverse drug events and medication relation extraction in electronic health records with ensemble deep learning methods

• Published in: Journal of the American Medical Informatics Association : JAMIA 2020-01, Vol.27 (1), p.39-46
• Main Authors: Christopoulou, Fenia, Tran, Thy Thy, Sahu, Sunil Kumar, Miwa, Makoto, Ananiadou, Sophia
• Format: Article
• Language: English
• Subjects: Deep Learning; Drug Interactions; Drug-Related Side Effects and Adverse Reactions; Electronic Health Records; Humans; Information Storage and Retrieval - methods; Natural Language Processing; Neural Networks, Computer; Research and Applications
• ISSN: 1527-974X; 1067-5027; 1527-974X
• DOI: 10.1093/jamia/ocz101

Abstract Objective Identification of drugs, associated medication entities, and interactions among them are crucial to prevent unwanted effects of drug therapy, known as adverse drug events. This article describes our participation to the n2c2 shared-task in extracting relations between medication-related entities in electronic health records. 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 named-entity recognition (NER) models based on bidirectional long short-term memory (BiLSTM) networks and conditional random fields (CRF) 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 bidirectional long short-term memory networks 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 (Tracks 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.