Jiang Guoqian, Wang Liwei, Liu Hongfang, Solbrig Harold R, Chute Christopher G
Department of Health Sciences Research, Division of Biomedical Statistics & Informatics, Mayo Clinic College of Medicine, Rochester, MN, USA.
Stud Health Technol Inform. 2013;192:496-500.
A semantically coded knowledge base of adverse drug events (ADEs) with severity information is critical for clinical decision support systems and translational research applications. However it remains challenging to measure and identify the severity information of ADEs. The objective of the study is to develop and evaluate a semantic web based approach for building a knowledge base of severe ADEs based on the FDA Adverse Event Reporting System (AERS) reporting data. We utilized a normalized AERS reporting dataset and extracted putative drug-ADE pairs and their associated outcome codes in the domain of cardiac disorders. We validated the drug-ADE associations using ADE datasets from SIDe Effect Resource (SIDER) and the UMLS. We leveraged the Common Terminology Criteria for Adverse Event (CTCAE) grading system and classified the ADEs into the CTCAE in the Web Ontology Language (OWL). We identified and validated 2,444 unique Drug-ADE pairs in the domain of cardiac disorders, of which 760 pairs are in Grade 5, 775 pairs in Grade 4 and 2,196 pairs in Grade 3.
一个带有严重程度信息的药物不良事件（ADEs）语义编码知识库对于临床决策支持系统和转化研究应用至关重要。然而，测量和识别药物不良事件的严重程度信息仍然具有挑战性。本研究的目的是开发和评估一种基于语义网的方法，用于基于美国食品药品监督管理局不良事件报告系统（AERS）报告数据构建严重药物不良事件知识库。我们使用了一个标准化的AERS报告数据集，并在心脏疾病领域提取了假定的药物-ADE对及其相关的结果代码。我们使用来自副作用资源（SIDER）和统一医学语言系统（UMLS）的ADE数据集验证了药物-ADE关联。我们利用不良事件通用术语标准（CTCAE）分级系统，并将药物不良事件用网络本体语言（OWL）分类到CTCAE中。我们在心脏疾病领域识别并验证了2444个独特的药物-ADE对，其中760对为5级，775对为4级，2196对为3级。
