Mining drug-drug interactions for healthcare professionals

Abstract

The fourth leading cause of death in the US are Adverse Drug Reactions (ADRs)1 that can be brought about through Drug-Drug Interactions (DDIs). In this paper, we propose medicX, a system that can detect DDIs in biomedical texts by leveraging on different machine learning techniques. The main components within medicX are the Drug Named Entity Recognition (DNER) component and the DDI Identification component. The DNER component was evaluated using the CHEMDNER and the DDIExtraction 2013 (DDI2013) challenge corpora. On the other hand, the DDI Identification component was evaluated using the DDI2013 challenge corpus. The DNER component is implemented using an approach based on LSTM-CRF. This method achieves an F1-score of 84.89% when it is trained and evaluated on the DDI2013 corpus, which is 1.43% higher than the system that placed first in the DDI2013 challenge. On the other hand, the DDI Identification component is implemented using a two-stage rich feature-based linear-kernel SVM. This classifier achieves an F1-score of 66.18%, as compared to the SVM state-of-the-art DDI system that reported an F1-score of 71.79%.