期刊
JOURNAL OF BIOMEDICAL INFORMATICS
卷 104, 期 -, 页码 -出版社
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.jbi.2020.103394
关键词
Time series data; Clinical informatics; Laboratory test reduction; Recurrent neural network; Combinatorial optimization
资金
- UTHealth startup funding
- National Institute of General Medical Sciences [R01GM124111]
- CPRIT Rising Stars Award [RR180012]
- Center for Clinical and Translational Sciences (NCATS) [1 U54 TR002804-01, U01 TR002062]
- National Library of Medicine [R01LM011829]
- Christopher Sarofim Family Professorship
- PCORI [CDRN-130604608]
- Reynolds and Reynolds Professorship in Clinical Informatics
- Cancer Prevention Research Institute of Texas (CPRIT) Data Science and Informatics Core for Cancer Research [RP170668]
- Tsinghua Scholarship for Overseas Graduate Studies
Serial laboratory testing is common, especially in Intensive Care Units (ICU). Such repeated testing is expensive and may even harm patients. However, identifying specific tests that can be omitted is challenging. The search space of different lab tests is large and the optimal reduction is hard to determine without modeling the time trajectory of decisions, which is a nontrivial optimization problem. In this paper, we propose a novel deep-learning method with a very concise architecture to jointly predict future lab test events to be omitted and the values of the omitted events based on observed testing values. Using our method, we were able to omit 15% of lab tests with <5% prediction accuracy loss. Although the application is specific to repeated lab tests, our proposed framework is highly generalizable and can be used to tackle a family of similar business decision making problems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据