文献速递药物不良反应与药物警戒

利用自然语言处理技术从韩国不良事件报告系统的不良事件叙述中自动提取全面药物安全信息

Automatic Extraction of Comprehensive Drug Safety Information from Adverse Drug Event Narratives in the Korea Adverse Event Reporting System Using Natural Language Processing Techniques.
PubMed 文献 · Drug Saf · 2023-06-17

本研究将从不良事件(ADE)叙述中提取全面药物安全信息定义为自然语言处理(NLP)任务,基于ICH E2B(R3)指南制定标注规范并人工标注3723条ADE叙述,开发了韩国领域特定的KAERS-BERT模型。KAERS-BERT在命名实体识别(NER)和句子提取任务上的F1分数分别为83.81%和76.62%,利用NER模型提取药物安全信息使KAERS结构化数据字段的数据完整性平均提高3.24%。

要点

  • KAERS-BERT在NER任务F1达83.81%,句子提取任务F1达76.62%。
  • 从ADE叙述提取信息可使结构化数据完整性平均提高3.24%。
  • 基于ICH E2B(R3)指南定义了21类词实体、6类实体标签和49类关系。

核心结论

  • 将ADE叙述信息提取定义为NLP任务,并开发了标注语料库和强基线模型,可提高自发报告系统数据库的数据质量。

主要发现

  • 定义了21种词实体类型、6种实体标签类型和49种关系类型,从人工标注叙述中获得86,750个实体、81,828个实体标签和45,107个关系。
  • KAERS-BERT在NER和句子提取任务上的F1分数分别为83.81%和76.62%,除句子提取任务外,在所有定义的NLP任务上均优于其他基线模型。
  • 利用NER模型从ADE叙述中提取药物安全信息,使KAERS结构化数据字段的数据完整性平均提高3.24%。

临床怎么用

  • 可利用NLP模型从ADE叙述中自动提取药物安全信息,补充结构化字段,提升自发报告系统数据完整性。

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

INTRODUCTION: Concerns have been raised over the quality of drug safety information, particularly data completeness, collected through spontaneous reporting systems (SRS), although regulatory agencies routinely use SRS data to guide their pharmacovigilance programs. We expected that collecting additional drug safety information from adverse event (ADE) narratives and incorporating it into the SRS database would improve data completeness. OBJECTIVE: The aims of this study were to define the extraction of comprehensive drug safety information from ADE narratives reported through the Korea Adverse Event Reporting System (KAERS) as natural language processing (NLP) tasks and to provide baseline models for the defined tasks. METHODS: This study used ADE narratives and structured drug safety information from individual case safety reports (ICSRs) reported through KAERS between 1 January 2015 and 31 December 2019. We developed the annotation guideline for the extraction of comprehensive drug safety information from ADE narratives based on the International Conference on Harmonisation (ICH) E2B(R3) guideline and manually annotated 3723 ADE narratives. Then, we developed a domain-specific Korean Bidirectional Encoder Representations from Transformers (KAERS-BERT) model using 1.2 million ADE narratives in KAERS and provided baseline models for the task we defined. In addition, we performed an ablation experiment to investigate whether named entity recognition (NER) models were improved when a training dataset contained more diverse ADE narratives. RESULTS: We defined 21 types of word entities, six types of entity labels, and 49 types of relations to formulate the extraction of comprehensive drug safety information as NLP tasks. We obtained a total of 86,750 entities, 81,828 entity labels, and 45,107 relations from manually annotated ADE narratives. The KAERS-BERT model achieved F1-scores of 83.81 and 76.62% on the NER and sentence extraction tasks, respectively, while outperforming other baseline models on all the NLP tasks we defined except the sentence extraction task. Finally, utilizing the NER model for extracting drug safety information from ADE narratives resulted in an average increase of 3.24% in data completeness for KAERS structured data fields. CONCLUSIONS: We formulated the extraction of comprehensive drug safety information from ADE narratives as NLP tasks and developed the annotated corpus and strong baseline models for the tasks. The annotated corpus and models for extracting comprehensive drug safety information can improve the data quality of an SRS database.

来源:Drug Saf,查看原文。版权归原作者所有。

引用

  1. Kim S, Kang T, Chung TK, et al. Automatic Extraction of Comprehensive Drug Safety Information from Adverse Drug Event Narratives in the Korea Adverse Event Reporting System Using Natural Language Processing Techniques. Drug Saf. 2023. PMID: 37330415. doi:10.1007/s40264-023-01323-2

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。