Chazard Emmanuel, Preda Cristian, Merlin Béatrice, Ficheur Grégoire, Beuscart Régis
Medical Information and Records Department EA2694, University Hospital, 59000 Lille, France.
Stud Health Technol Inform. 2009;150:552-6.
Every year adverse drug events (ADEs) are known to be responsible for 98,000 deaths in the USA. Classical methods rely on report statements, expert knowledge, and staff operated record review. One of our objectives, in the PSIP project framework, is to use data mining (e.g., decision trees) to electronically identify situations leading to risk of ADEs. 10,500 hospitalization records from Denmark and France were used. 500 rules were automatically obtained, which are currently being validated by experts. A decision support system to prevent ADEs is then to be developed. The article examines a decision tree and the rules in the field of vitamin K antagonists.
众所周知，在美国，每年药物不良事件（ADEs）导致98,000人死亡。传统方法依赖于报告声明、专家知识以及工作人员进行的记录审查。在PSIP项目框架中，我们的目标之一是使用数据挖掘（例如决策树）来电子识别导致药物不良事件风险的情况。我们使用了来自丹麦和法国的10,500份住院记录。自动获取了500条规则，目前正由专家进行验证。随后将开发一个预防药物不良事件的决策支持系统。本文研究了维生素K拮抗剂领域的决策树和规则。
