中国药物警戒 ›› 2016, Vol. 13 ›› Issue (7): 408-409.

• 法规与管理研究 • 上一篇    下一篇

药品不良反应信号检测模型优化及应用

侯永芳, 刘翠丽, 宋海波, 王亚丽, 王丹, 邹箴蕾, 吴桂芝   

  1. 国家食品药品监督管理总局药品评价中心，北京 100045
  • 收稿日期:2016-06-01 修回日期:2018-07-17 出版日期:2016-07-20 发布日期:2018-07-17
  • 通讯作者: 吴桂芝，女，博士，主任药师，药品不良反应监测。E-mail: wuguizhi@cdr-adr.org.cn
  • 作者简介:侯永芳，男，硕士，高级工程师，药品不良反应监测。

Optimized Signal Detection Model in Adverse Drug Reaction Monitoring System

HOU Yong-fang, LIU Cui-li, SONG Hai-bo, WANG Ya-li, WANG Dan, ZOU Zhen-lei, WU Gui-zhi   

  1. Center for Drug Reevaluation, CFDA, Beijing 100045, China
  • Received:2016-06-01 Revised:2018-07-17 Online:2016-07-20 Published:2018-07-17

PDF (PC)

228

摘要： 目的 解决我国药品不良反应监测系统中信号检测模型生成过多信号问题。方法 通过控制数据质量、精简优化检测方法、建立信号筛选策略对模型进行优化。结果 信号检测模型中引入重复病例鉴别方法，信号检测方法进行压缩估计优化，利用筛选策略对信号结果进行分类过滤，假阳性信号有所减少。结论 优化后的信号检测模型能够从药品不良反应病例报告数据库中提取更有价值信号。

关键词: 药品不良反应, 信号检测, 优化

Abstract: Objective To optimize signal detection model to extract more valuable signals in adverse drug reaction monitoring system in china. Methods By data quality controlling, optimizing signal detection methods, building signal screening strategy, the signal detection model was optimized. Results The variable matching method was built to find and delete duplicate cases. Signal detection methods have been optimized by Shrinkage. Signal screening strategy was built to rank signals, which had veaducedced the false positive signals. Conclusion Optimized signal detection model can extract more valuable signals from ADR cases database.

Key words: adverse drug reaction, signal detection, optimizing

中图分类号: