Portanova Jake, Murray Nathan, Mower Justin, Subramanian Devika, Cohen Trevor
University of Washington, Seattle, WA.
Hofstra University, East Garden City, New York.
AMIA Annu Symp Proc. 2020 Mar 4;2019:717-726. eCollection 2019.
Adverse event report (AER) data are a key source of signal for post marketing drug surveillance. The standard methodology to analyze AER data applies disproportionality metrics, which estimate the strength of drug/side-effect associations from discrete counts of their occurrence at report level. However, in other domains, improvements in predictive modeling accuracy have been obtained through representation learning, where discrete features are replaced by distributed representations learned from unlabeled data. This paper describes aer2vec, a novel representational approach for AER data in which concept embeddings emerge from neural networks trained to predict drug/side-effect co-occurrence. Trained models are evaluated for their utility in identifying drug/side-effect relationships, with improvements over disproportionality metrics in most cases. In addition, we evaluate the utility of an otherwise-untapped resource in the Food and Drug Administration (FDA) AER system - reporter designations of suspected causality - and find that incorporating this information enhances performance of all models evaluated.
不良事件报告（AER）数据是药品上市后监测信号的关键来源。分析AER数据的标准方法应用了不成比例度量，该方法从报告层面上药物/副作用发生的离散计数来估计药物/副作用关联的强度。然而，在其他领域，通过表征学习提高了预测建模的准确性，其中离散特征被从未标记数据中学习到的分布式表示所取代。本文介绍了aer2vec，这是一种针对AER数据的新颖表示方法，其中概念嵌入来自经过训练以预测药物/副作用共现情况的神经网络。对训练好的模型在识别药物/副作用关系方面的效用进行了评估，在大多数情况下，其性能优于不成比例度量。此外，我们评估了美国食品药品监督管理局（FDA）AER系统中一种尚未利用的资源——疑似因果关系的报告者指定——的效用，并发现纳入此信息可提高所有评估模型的性能。
