A fusion framework to extract typical treatment patterns from electronic medical records

作者：

Highlights：

• Temporal and content information of patient treatments is analysed in depth.

• A fusion framework based on multi-view similarity fusion method is proposed.

• Three similarity measures from content, sequence, and duration are designed.

• The fusion method is applied on real EMRs to extract typical treatment patterns.

摘要

•Temporal and content information of patient treatments is analysed in depth.•A fusion framework based on multi-view similarity fusion method is proposed.•Three similarity measures from content, sequence, and duration are designed.•The fusion method is applied on real EMRs to extract typical treatment patterns.

论文关键词：Electronic medical records,Similarity network fusion,Clustering analysis,Treatment pattern extraction

论文评审过程：Received 16 July 2018, Revised 18 November 2019, Accepted 26 December 2019, Available online 28 December 2019, Version of Record 7 January 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2019.101782