Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/136896
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Dynamic illness severity prediction via multi-task RNNs for Intensive Care Unit |
Author: | Chen, W. Wang, S. Long, G. Yao, L. Sheng, Q.Z. Li, X. |
Citation: | Proceedings / IEEE International Conference on Data Mining. IEEE International Conference on Data Mining, 2018, pp.917-922 |
Publisher: | IEEE |
Publisher Place: | Piscataway, NJ, USA |
Issue Date: | 2018 |
Series/Report no.: | IEEE International Conference on Data Mining |
ISBN: | 1538691590 9781538691601 |
ISSN: | 1550-4786 2374-8486 |
Conference Name: | IEEE International Conference on Data Mining (ICDM) (17 Nov 2018 - 20 Nov 2018 : Singapore) |
Statement of Responsibility: | Weitong Chen, Sen Wang, Guodong Long, Lina Yao, Quan Z. Sheng, Xue Li |
Abstract: | Most of the existing analytics on ICU data mainly focus on mortality risk prediction and phenotyping analysis. However, they have limitations in providing sufficient evidence for decision making in a dynamically changing clinical environment. In this paper, we propose a novel approach that simultaneously analyses different organ systems to predict the illness severity of patients in an ICU, which can intuitively reflect the condition of the patients in a timely fashion. Specifically, we develop a novel deep learning model, namely MTRNN-ATT, which is based on multi-task recurrent neural networks. The physiological features of each organ system in time-series representations are learned by a single long short-term memory unit as a specific task. To utilize the relationships between organ systems, we use a shared LSTM unit to exploit the correlations between different tasks for further performance improvement. Also, we apply an attention mechanism in our deep model to learn the selective features at each stage to achieve better prediction results. We conduct extensive experiments on a real-world clinical dataset (MIMIC-III) to compare our method with many state-ofthe- art methods. The experiment results demonstrate that the proposed approach performs better on the prediction tasks of illness severity scores. |
Keywords: | deep learning; multi-task learning; clinical informatics; illness severity prediction |
Rights: | ©2018 IEEE |
DOI: | 10.1109/ICDM.2018.00111 |
Grant ID: | http://purl.org/au-research/grants/arc/DP160104075 http://purl.org/au-research/grants/arc/LP150100671 http://purl.org/au-research/grants/arc/LP160100630 |
Published version: | https://ieeexplore.ieee.org/xpl/conhome/8591042/proceeding |
Appears in Collections: | Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.