Mortality Prediction with Bidirectional Coupled and Gumbel Subset Network on Irregularly Multivariate Time Series

Qinfen Wang, Siyuan Ren, Yong Xia

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

Mortality prediction is a crucial challenge because of multivariate time series (MTS) complexity, which are sparse, irregularly, asynchronous and hold missing values for various reasons in a single acquisition. Various methods are proposed to deal with missing values for the final mortality prediction. However, existing models only capture the temporal dependencies within a time series and are inefficient to capture the dependencies between time series to rebuild missing values for mortality prediction. To address these challenges, in this paper, we present an end-to-end imputation and mortality prediction model, named bidirectional coupled and Gumbel subset network (BiCGSN), for mortality prediction with such irregularly multivariate time series. Our proposed model (BiCGSN) uses a recurrent network to learn the temporal dependencies (intra-time series couplings) and uses a Gumbel selector on multi-head attention to obtain the relationship between the variables (inter-time series couplings) in the forward and backward directions. Then the learned bidirectional inter-and intra-time series couplings are fused to impute missing values for further mortality prediction. We evaluate our model on PhysioNet2012 and COVID-19 datasets to imputation and predict mortality. Experiments show that BiCGSN obtains the AUC 0.869 and 0.911 on two real-world datasets respectively and outperforms all the baselines.

源语言英语
主期刊名ICSP 2022 - 2022 16th IEEE International Conference on Signal Processing, Proceedings
编辑Baozong Yuan, Qiuqi Ruan, Shikui Wei, Gaoyun An
出版商Institute of Electrical and Electronics Engineers Inc.
468-473
页数6
ISBN(电子版)9781665460569
DOI
出版状态已出版 - 2022
活动16th IEEE International Conference on Signal Processing, ICSP 2022 - Beijing, 中国
期限: 21 10月 202224 10月 2022

出版系列

姓名International Conference on Signal Processing Proceedings, ICSP
2022-October

会议

会议16th IEEE International Conference on Signal Processing, ICSP 2022
国家/地区中国
Beijing
时期21/10/2224/10/22

指纹

探究 'Mortality Prediction with Bidirectional Coupled and Gumbel Subset Network on Irregularly Multivariate Time Series' 的科研主题。它们共同构成独一无二的指纹。

引用此