Suppr超能文献

将不良事件报告数据的向量表示形式改造为结构化知识以改进药物警戒信号检测。

Retrofitting Vector Representations of Adverse Event Reporting Data to Structured Knowledge to Improve Pharmacovigilance Signal Detection.

作者信息

Ding Xiruo, Cohen Trevor

机构信息

University of Washington, Seattle, WA, USA.

出版信息

AMIA Annu Symp Proc. 2021 Jan 25;2020:383-392. eCollection 2020.

Abstract

Adverse drug events (ADE) are prevalent and costly. Clinical trials are constrained in their ability to identify potential ADEs, motivating the development of spontaneous reporting systems for post-market surveillance. Statistical methods provide a convenient way to detect signals from these reports but have limitations in leveraging relationships between drugs and ADEs given their discrete count-based nature. A previously proposed method, aer2vec, generates distributed vector representations of ADE report entities that capture patterns of similarity but cannot utilize lexical knowledge. We address this limitation by retrofitting aer2vec drug embeddings to knowledge from RxNorm and developing a novel retrofitting variant using vector rescaling to preserve magnitude. When evaluated in the context of a pharmacovigilance signal detection task, aer2vec with retrofitting consistently outperforms disproportionality metrics when trained on minimally preprocessed data. Retrofitting with rescaling results in further improvements in the larger and more challenging of two pharmacovigilance reference sets used for evaluation.

摘要

药物不良事件(ADE)普遍存在且代价高昂。临床试验在识别潜在ADE方面能力有限,这推动了用于上市后监测的自发报告系统的发展。统计方法提供了一种从这些报告中检测信号的便捷方式,但鉴于其基于离散计数的性质,在利用药物与ADE之间的关系方面存在局限性。先前提出的方法aer2vec生成了ADE报告实体的分布式向量表示,可捕捉相似性模式,但无法利用词汇知识。我们通过将aer2vec药物嵌入与RxNorm中的知识进行适配,并开发一种使用向量重缩放来保留幅度的新型适配变体,来解决这一局限性。在药物警戒信号检测任务的背景下进行评估时,经过适配的aer2vec在对最少预处理数据进行训练时,始终优于不成比例性指标。在用于评估的两个药物警戒参考集中,规模更大且更具挑战性的参考集中,采用重缩放的适配会带来进一步的改进。

相似文献

2
Augmenting aer2vec: Enriching distributed representations of adverse event report data with orthographic and lexical information.
J Biomed Inform. 2021 Jul;119:103833. doi: 10.1016/j.jbi.2021.103833. Epub 2021 Jun 8.
3
Mining association patterns of drug-interactions using post marketing FDA's spontaneous reporting data.
J Biomed Inform. 2016 Apr;60:294-308. doi: 10.1016/j.jbi.2016.02.009. Epub 2016 Feb 20.
4
Leveraging MEDLINE indexing for pharmacovigilance - Inherent limitations and mitigation strategies.
J Biomed Inform. 2015 Oct;57:425-35. doi: 10.1016/j.jbi.2015.08.022. Epub 2015 Sep 2.
10

引用本文的文献

2
Augmenting aer2vec: Enriching distributed representations of adverse event report data with orthographic and lexical information.
J Biomed Inform. 2021 Jul;119:103833. doi: 10.1016/j.jbi.2021.103833. Epub 2021 Jun 8.

本文引用的文献

3
Indexed Pain Journals.
J Pain Palliat Care Pharmacother. 2008;22(1):45-46. doi: 10.1080/15360280801989377.
4
A time-indexed reference standard of adverse drug reactions.
Sci Data. 2014 Nov 11;1:140043. doi: 10.1038/sdata.2014.43.
5
Zoo or savannah? Choice of training ground for evidence-based pharmacovigilance.
Drug Saf. 2014 Sep;37(9):655-9. doi: 10.1007/s40264-014-0198-z.
6
Defining a reference set to support methodological research in drug safety.
Drug Saf. 2013 Oct;36 Suppl 1:S33-47. doi: 10.1007/s40264-013-0097-8.
8
Pharmacovigilance in the 21st century: new systematic tools for an old problem.
Pharmacotherapy. 2004 Sep;24(9):1099-104. doi: 10.1592/phco.24.13.1099.38090.
9
The reporting odds ratio and its advantages over the proportional reporting ratio.
Pharmacoepidemiol Drug Saf. 2004 Aug;13(8):519-23. doi: 10.1002/pds.1001.
10
The Unified Medical Language System (UMLS): integrating biomedical terminology.
Nucleic Acids Res. 2004 Jan 1;32(Database issue):D267-70. doi: 10.1093/nar/gkh061.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验