药品不良反应信号检测模型优化及应用

Optimized Signal Detection Model in Adverse Drug Reaction Monitoring System

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。

Objective To optimize signal detection model to extract more valuable signals in adverse drug reaction monitoringsystem 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 hadveaducedced the false positive signals. Conclusion Optimized signal detection model can extract more valuable signals fromADR cases database.