文献速递药物不良反应与药物警戒

文献衍生分布式表示补充观察性信号用于上市后药物监测

Complementing Observational Signals with Literature-Derived Distributed Representations for Post-Marketing Drug Surveillance.
PubMed 文献 · Drug Saf · 2020-01-01

本研究探讨将自发报告系统(SRS)的观察性信号与文献衍生的分布式表示(概念嵌入)直接或间接结合为单一特征向量或集成方法,用于下游机器学习(逻辑回归)。基于两种参考标准(阳性可能因果配对与阴性无因果证据配对),使用ROC AUC评估性能。结果表明,复合模型的ROC AUC较仅基于SRS的不比例分析指标提升最高约20%,且超过文献中报告的最佳先前结果。

要点

  • 文献与SRS信息联合使用优于单独使用任一来源。
  • 复合模型ROC AUC较SRS不比例分析指标提升最高约20%。
  • 结果支持文献知识与SRS方法互补用于上市后药物监测。

核心结论

  • 文献提取的知识可增强基于SRS的方法性能,反之亦然,两者互补。

研究设计与样本

  • 利用文献中提取的关系连接生成概念嵌入,表示药物与相关不良反应,基于两种参考标准(阳性可能因果配对与阴性无因果证据配对)构建特征,输入逻辑回归模型,以ROC AUC评估性能。

主要发现

  • 复合模型(文献嵌入与SRS观察性信号结合)的ROC AUC较仅基于SRS的不比例分析指标提升最高约20%。
  • 当模型同时利用文献与SRS两种信息时,性能超过文献中报告的最佳先前结果。
  • 跨参考集,文献与SRS信息联合使用均优于单独使用任一来源。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

INTRODUCTION: As a result of the well documented limitations of data collected by spontaneous reporting systems (SRS), such as bias and under-reporting, a number of authors have evaluated the utility of other data sources for the purpose of pharmacovigilance, including the biomedical literature. Previous work has demonstrated the utility of literature-derived distributed representations (concept embeddings) with machine learning for the purpose of drug side-effect prediction. In terms of data sources, these methods are complementary, observing drug safety from two different perspectives (knowledge extracted from the literature and statistics from SRS data). However, the combined utility of these pharmacovigilance methods has yet to be evaluated. OBJECTIVE: This research investigates the utility of directly or indirectly combining an observational signal from SRS with literature-derived distributed representations into a single feature vector or in an ensemble approach for downstream machine learning (logistic regression). METHODS: Leveraging a recently developed representation scheme, concept embeddings were generated from relational connections extracted from the literature and composed to represent drug and associated adverse reactions, as defined by two reference standards of positive (likely causal) and negative (no causal evidence) pairs. Embeddings were presented with and without common measures of observational signal from SRS sources to logistic regressors, and performance was evaluated with the receiver operating characteristic (ROC) area under the curve (AUC) metric. RESULTS: ROC AUC performance with these composite models improves up to ≈ 20% over SRS-based disproportionality metrics alone and exceeds the best prior results reported in the literature when models leverage both sources of information. CONCLUSIONS: Results from this study support the hypothesis that knowledge extracted from the literature can enhance the performance of SRS-based methods (and vice versa). Across reference sets, using literature and SRS information together performed better than using either source alone, providing strong support for the complementary nature of these approaches to post-marketing drug surveillance.

来源:Drug Saf,查看原文。版权归原作者所有。

引用

  1. Mower J, Cohen T, Subramanian D, et al. Complementing Observational Signals with Literature-Derived Distributed Representations for Post-Marketing Drug Surveillance. Drug Saf. 2020. PMID: 31646442. doi:10.1007/s40264-019-00872-9

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。