计算机集成制造系统 ›› 2018, Vol. 24 ›› Issue (第7): 1642-1652.DOI: 10.13196/j.cims.2018.07.006

• 当期目次 • 上一篇    下一篇

基于参考模型的临床路径挖掘

黄俊捷,莫天宇,金涛+,王建民   

  1. 清华大学软件学院
  • 出版日期:2018-07-31 发布日期:2018-07-31
  • 基金资助:
    国家科技支撑计划资助项目(2015BAH14F02);国家自然科学基金资助项目(61325008)。

Clinical pathway mining based on reference model

  • Online:2018-07-31 Published:2018-07-31
  • Supported by:
    Project supported by the National Key Technology R & D Program,China(No.2015BAH14F02),and the National Natural Science Foundation,China(No.61325008).

摘要: 鉴于临床诊疗过程的高度动态性和复杂性,目前通过计算机辅助临床路径制定的效果不佳提出一种基于参考模型的临床路径挖掘算法。该算法以时序数据为输入,以国家标准临床路径为参考模型进行临床路径挖掘,生成本地化的临床路径模型。通过同义医嘱数据消解降低医嘱数据维度,通过关键医嘱序列挖掘实现医嘱数据与参考模型的时序对齐,通过多分类的医嘱主题聚类实现医嘱到标准临床路径活动的映射。实验结果表明,所提算法充分考虑了我国临床路径管理模式推广过程中的实际情况,能够有效辅助我国医疗机构进行本地化临床路径的制定。

关键词: 临床路径, 参考模型, 挖掘算法, 医嘱数据

Abstract: Most of the computer aided clinical pathway design could not apply in general cases due to complexity and high level of diversity during the clinical process.Aiming at the situation in China,a clinical pathway mining method named CPMRM algorithm was proposed.Based on time series data,the algorithm took the national standard clinical path as a reference model to achieve local clinical pathway mining.It used synonymous order reduction to reduce the size of order set,key order pattern mining to align the time of order set and the reference model and multi-classification based topic-model clustering to map the orders to clinical pathway activities.Experiments showed that CPMRM algorithm fully considered the actual situation in the process of popularization of clinical pathway management model in China,and could effectively assist the development of local clinical pathways in Chinese medical service provider.

Key words: clinical pathway, reference model, mining algorithm, order set

中图分类号: