文献速递药物不良反应与药物警戒

利用文本挖掘工具主动识别电子健康记录中的不良事件以加强信号检测

Strengthening Signal Detection by Proactive Adverse Event Case Identification in Electronic Health Records Using a Text-Mining Tool.
PubMed 文献 · Drug Saf · 2026-10-20

本研究在两家荷兰医院约275万份电子健康记录中,使用文本挖掘工具主动检索特定药物-不良事件关联,共报告147例电子健康记录来源的病例,涉及41种药物-不良事件关联,贡献34项信号检测分析并支持7个安全信号的评估;75%病例中临床记录记载了疑似因果关系,电子健康记录来源病例在7个检出信号中占比最高达73%。

要点

  • 电子健康记录可作为药品不良反应个体病例报告的补充来源,弥补自发报告漏报。
  • 文本挖掘工具可结合结构化和非结构化数据主动检索潜在不良反应。
  • 检出的电子健康记录病例在部分安全信号中占比可达73%。

核心结论

  • 电子健康记录可作为常规药物警戒中个体病例安全报告的补充来源,支持对选定潜在安全信号的进一步评估。
  • 该主动方法虽有效率限制,但有望应对漏报并补充自发报告系统,加强信号检测。

研究设计与样本

  • 2022年8月至2025年8月,在两家荷兰医院约2,750,000份电子健康记录中,使用数据收集文本挖掘工具开展针对性药物不良反应检索。
  • 检索标准源自特定药物-不良事件关联的自发报告信息,利用结构化数据(如实验室结果、药物处方)和非结构化数据(如临床笔记、出院信)识别潜在药物不良反应。
  • 识别病例经人工核实,相关病例报告至荷兰药物警戒中心Lareb,并与自发报告一起用于信号检测分析。

主要发现

  • 共报告147例电子健康记录来源病例,涉及41种药物-不良事件关联。
  • 这些病例贡献34项信号检测分析,支持7个安全信号的评估。
  • 75%的病例中,医疗专业人员在临床笔记中记录了疑似因果关系。
  • 电子健康记录来源病例在7个检出信号所纳入报告中占比最高达73%。

临床怎么用

  • 可在常规药物警戒中引入电子健康记录文本挖掘主动检索,作为自发报告系统的补充以加强信号检测。
  • 对文本挖掘识别的潜在药物不良反应病例应进行人工核实,并将相关病例报告至药物警戒中心。

局限性

  • 该方法在效率方面存在局限性。

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

BACKGROUND: The spontaneous reporting system is the cornerstone of pharmacovigilance but is limited by substantial underreporting, which may delay safety signal detection. OBJECTIVE: The aim of this study was to evaluate the electronic health record-adverse event search method for identifying and reporting additional potential adverse drug reactions in electronic health records to strengthen routine signal detection. METHODS: Between August 2022 and August 2025, targeted searches for adverse drug reactions were conducted in approximately 2,750,000 electronic health records from two Dutch hospitals using a data collection text-mining tool. Search criteria were derived from information in spontaneous reports of specific drug-adverse event associations. Structured (e.g. laboratory results, medication prescriptions) and unstructured (e.g. clinical notes, hospital discharge letters) data were used to identify potential adverse drug reactions. Identified cases were manually verified and, when relevant, reported to the Netherlands Pharmacovigilance Centre Lareb and analysed alongside spontaneous reports for signal detection. RESULTS: A total of 147 electronic health record-derived cases were reported for 41 drug-adverse event associations. These contributed to 34 signal detection analyses, supporting the assessment of seven safety signals. In 75% of the cases, a suspected causal relationship was documented by healthcare professionals in clinical notes. Electronic health record-derived cases accounted for up to 73% of the reports included in the seven detected signals. CONCLUSIONS: This study demonstrates that electronic health records can be used as an additional source of individual case safety reports in routine pharmacovigilance practice, supporting the further assessment of selected potential safety signals. Despite limitations related to efficiency, this proactive approach has potential to address underreporting and complement the spontaneous reporting system, strengthening signal detection.

来源:Drug Saf,查看原文。版权归原作者所有。

引用

  1. von Kreijfelt G, Zwaveling J, van Lint JA, et al. Strengthening Signal Detection by Proactive Adverse Event Case Identification in Electronic Health Records Using a Text-Mining Tool. Drug Saf. 2026. PMID: 42900349. doi:10.1007/s40264-026-01739-6

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。