Temporal tree representation for similarity computation between medical patients
作者：
Highlights：
• Temporal Tree explicitly models EHRs properties such as temporality, multivariaty.
• Temporal Tree captures the compound information based on temporal co-occurrence.
• Temporal Tree is useful to compute the similarity between patients.
• The effectiveness of Temporal Tree is evaluated on task of diagnosis prediction.
• Temporal Tree is valuable for representation learning and embedded representations.
摘要
•Temporal Tree explicitly models EHRs properties such as temporality, multivariaty.•Temporal Tree captures the compound information based on temporal co-occurrence.•Temporal Tree is useful to compute the similarity between patients.•The effectiveness of Temporal Tree is evaluated on task of diagnosis prediction.•Temporal Tree is valuable for representation learning and embedded representations.
论文关键词：Patient similarity,Temporal Tree
论文评审过程：Received 25 September 2019, Revised 15 May 2020, Accepted 3 June 2020, Available online 11 June 2020, Version of Record 12 August 2020.
论文官网地址：https://doi.org/10.1016/j.artmed.2020.101900
