Fiszman Marcelo, Rindflesch Thomas C, Kilicoglu Halil
Graduate School of Medicine, University of Tennessee, Knoxville, TN, USA.
AMIA Annu Symp Proc. 2006;2006:254-8.
Adverse drug events and drug-drug interactions are a major concern in patient care. Although databases exist to provide information about drugs, they are not always up-to-date and complete (particularly regarding pharmacogenetics). We propose a methodology based on automatic summarization to identify drug information in Medline citations and present results to the user in a convenient form. We evaluate the method on a selection of citations discussing ten drugs ranging from the proton pump inhibitor lansoprazole to the vasoconstrictor sumatriptan. We suggest that automatic summarization can provide a valuable adjunct to curated drug databases in supporting quality patient care.
药物不良事件和药物相互作用是患者护理中的主要关注点。尽管存在提供药物信息的数据库，但它们并不总是最新且完整的（尤其是在药物遗传学方面）。我们提出一种基于自动摘要的方法，以在医学在线数据库（Medline）引用中识别药物信息，并以方便的形式向用户呈现结果。我们在一组讨论从质子泵抑制剂兰索拉唑到血管收缩剂舒马曲坦等十种药物的引用文献上评估了该方法。我们认为自动摘要可为经过整理的药物数据库提供有价值的辅助，以支持高质量的患者护理。
