BioDEX: Large-Scale Biomedical Adverse Drug Event Extraction for Real-World Pharmacovigilance
This work addresses the slow and costly manual extraction of ADEs for drug safety monitoring, though it is incremental as it builds on existing NLP methods applied to a new biomedical dataset.
The authors tackled the problem of extracting Adverse Drug Events (ADEs) from biomedical literature to improve pharmacovigilance, by introducing BioDEX, a large-scale dataset with 65k abstracts and 19k full-text papers, and achieved a model performance of 62.3% F1 compared to an estimated human performance of 72.0% F1.
Timely and accurate extraction of Adverse Drug Events (ADE) from biomedical literature is paramount for public safety, but involves slow and costly manual labor. We set out to improve drug safety monitoring (pharmacovigilance, PV) through the use of Natural Language Processing (NLP). We introduce BioDEX, a large-scale resource for Biomedical adverse Drug Event Extraction, rooted in the historical output of drug safety reporting in the U.S. BioDEX consists of 65k abstracts and 19k full-text biomedical papers with 256k associated document-level safety reports created by medical experts. The core features of these reports include the reported weight, age, and biological sex of a patient, a set of drugs taken by the patient, the drug dosages, the reactions experienced, and whether the reaction was life threatening. In this work, we consider the task of predicting the core information of the report given its originating paper. We estimate human performance to be 72.0% F1, whereas our best model achieves 62.3% F1, indicating significant headroom on this task. We also begin to explore ways in which these models could help professional PV reviewers. Our code and data are available: https://github.com/KarelDO/BioDEX.