文献速递药物不良反应与药物警戒

药物不良事件关联检测算法比较:频率学派、贝叶斯与机器学习方法

A Comparison Study of Algorithms to Detect Drug-Adverse Event Associations: Frequentist, Bayesian, and Machine-Learning Approaches.
PubMed 文献 · Drug Saf · 2019-01-01

贝叶斯置信传播神经网络总体AUC最高;2018年开发的蒙特卡洛期望最大化AUC第二且Youden指数最高、特异性好;回归校正伽马泊松收缩模型在高敏感性要求下表现最佳。

要点

  • 贝叶斯置信传播神经网络总体AUC最高。
  • 蒙特卡洛期望最大化Youden指数最高且特异性好。
  • 回归校正伽马泊松收缩模型适合高敏感性需求。

核心结论

  • 贝叶斯置信传播神经网络在总体AUC上表现最高。
  • 蒙特卡洛期望最大化AUC第二、Youden指数最高,且特异性表现很好。
  • 回归校正伽马泊松收缩模型在高敏感性要求下表现最佳。
  • 全基因组关联研究文献中的常用方法因数据稀疏表现不佳,需修改后才能用于药物-不良事件关联问题。

研究设计与样本

  • 使用观察性医疗结果合作组织提供的参考标准,含398对药物-不良事件(165阳性对照、233阴性对照)。
  • 采用受试者工作特征曲线、曲线下面积和Youden指数比较性能。

主要发现

  • 贝叶斯置信传播神经网络总体AUC最高。
  • 蒙特卡洛期望最大化AUC第二高、Youden指数最高,在高特异性方面表现很好。
  • 回归校正伽马泊松收缩模型在高敏感性要求下表现最佳。
  • 全基因组关联研究文献常用方法因数据稀疏表现不佳。

临床怎么用

  • 可根据所需的特异性水平选择相应方法:总体AUC优先考虑贝叶斯置信传播神经网络。
  • 需兼顾Youden指数与高特异性时可考虑蒙特卡洛期望最大化。
  • 高敏感性需求下可考虑回归校正伽马泊松收缩模型。
  • 全基因组关联研究文献方法需修改后方可用于药物-不良事件关联检测。

局限性

  • 全基因组关联研究文献常用方法因数据稀疏表现不佳,需修改后才能用于药物-不良事件关联问题。

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: It is important to monitor the safety profile of drugs, and mining for strong associations between drugs and adverse events is an effective and inexpensive method of post-marketing safety surveillance. OBJECTIVE: The objective of our work was to compare the accuracy of both common and innovative methods of data mining for pharmacovigilance purposes. METHODS: We used the reference standard provided by the Observational Medical Outcomes Partnership, which contains 398 drug-adverse event pairs (165 positive controls, 233 negative controls). Ten methods and algorithms were applied to the US FDA Adverse Event Reporting System data to investigate the 398 pairs. The ten methods include popular methods in the pharmacovigilance literature, newly developed pharmacovigilance methods as at 2018, and popular methods in the genome-wide association study literature. We compared their performance using the receiver operating characteristic (ROC) plot, area under the curve (AUC), and Youden's index. RESULTS: The Bayesian confidence propagation neural network had the highest AUC overall. Monte Carlo expectation maximization, a method developed in 2018, had the second highest AUC and the highest Youden's index, and performed very well in terms of high specificity. The regression-adjusted gamma Poisson shrinkage model performed best under high-sensitivity requirements. CONCLUSION: Our results will be useful to help choose a method for a given desired level of specificity. Methods popular in the genome-wide association study literature did not perform well because of the sparsity of data and will need modification before their properties can be used in the drug-adverse event association problem.

来源:Drug Saf,查看原文。版权归原作者所有。

引用

  1. Pham M, Cheng F, Ramachandran K, et al. A Comparison Study of Algorithms to Detect Drug-Adverse Event Associations: Frequentist, Bayesian, and Machine-Learning Approaches. Drug Saf. 2019. PMID: 30762164. doi:10.1007/s40264-018-00792-0

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。