期刊
出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/2783258.2783365
关键词
Medical informatics; Phenotyping; Deep learning; Multivariate time series; Healthcare; Multi-label classification
类别
资金
- Alfred E. Mann Innovation in Engineering Doctoral Fellowship
- Laura P. and Leland K. Whitter Foundation
- NSF [IIS-1254206, IIS-1134990]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1254206] Funding Source: National Science Foundation
We apply deep learning to the problem of discovery and detection of characteristic patterns of physiology in clinical time series data. We propose two novel modifications to standard neural net training that address challenges and exploit properties that are peculiar, if not exclusive, to medical data. First, we examine a general framework for using prior knowledge to regularize parameters in the topmost layers. This framework can leverage priors of any form, ranging from formal ontologies (e.g., ICD9 codes) to data-derived similarity. Second, we describe a scalable procedure for training a collection of neural networks of different sizes but with partially shared architectures. Both of these innovations are well-suited to medical applications, where available data are not yet Internet scale and have many sparse outputs (e.g., rare diagnoses) but which have exploitable structure (e.g., temporal order and relationships between labels). However, both techniques are sufficiently general to be applied to other problems and domains. We demonstrate the empirical efficacy of both techniques on two real-world hospital data sets and show that the resulting neural nets learn interpretable and clinically relevant features.
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