Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jun, E. | - |
dc.contributor.author | Mulyadi, A.W. | - |
dc.contributor.author | Choi, J. | - |
dc.contributor.author | Suk, H. | - |
dc.date.accessioned | 2021-12-01T16:41:58Z | - |
dc.date.available | 2021-12-01T16:41:58Z | - |
dc.date.created | 2021-08-31 | - |
dc.date.issued | 2021-09 | - |
dc.identifier.issn | 2162-237X | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/128644 | - |
dc.description.abstract | Electronic health records (EHRs) are characterized as nonstationary, heterogeneous, noisy, and sparse data; therefore, it is challenging to learn the regularities or patterns inherent within them. In particular, sparseness caused mostly by many missing values has attracted the attention of researchers who have attempted to find a better use of all available samples for determining the solution of a primary target task through defining a secondary imputation problem. Methodologically, existing methods, either deterministic or stochastic, have applied different assumptions to impute missing values. However, once the missing values are imputed, most existing methods do not consider the fidelity or confidence of the imputed values in the modeling of downstream tasks. Undoubtedly, an erroneous or improper imputation of missing variables can cause difficulties in the modeling as well as a degraded performance. In this study, we present a novel variational recurrent network that: 1) estimates the distribution of missing variables (e.g., the mean and variance) allowing to represent uncertainty in the imputed values; 2) updates hidden states by explicitly applying fidelity based on a variance of the imputed values during a recurrence (i.e., uncertainty propagation over time); and 3) predicts the possibility of in-hospital mortality. It is noteworthy that our model can conduct these procedures in a single stream and learn all network parameters jointly in an end-to-end manner. We validated the effectiveness of our method using the public data sets of MIMIC-III and PhysioNet challenge 2012 by comparing with and outperforming other state-of-the-art methods for mortality prediction considered in our experiments. In addition, we identified the behavior of the model that well represented the uncertainties for the imputed estimates, which showed a high correlation between the uncertainties and mean absolute error (MAE) scores for imputation. IEEE | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.subject | Recurrent neural networks | - |
dc.subject | Stochastic systems | - |
dc.subject | Uncertainty analysis | - |
dc.subject | Degraded performance | - |
dc.subject | Electronic health record (EHRs) | - |
dc.subject | Hospital mortality | - |
dc.subject | Mean absolute error | - |
dc.subject | Network parameters | - |
dc.subject | Recurrent networks | - |
dc.subject | State-of-the-art methods | - |
dc.subject | Uncertainty propagation | - |
dc.subject | Stochastic models | - |
dc.title | Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Suk, H. | - |
dc.identifier.doi | 10.1109/TNNLS.2020.3016670 | - |
dc.identifier.scopusid | 2-s2.0-85091316861 | - |
dc.identifier.wosid | 000692208800025 | - |
dc.identifier.bibliographicCitation | IEEE Transactions on Neural Networks and Learning Systems, v.32, no.9, pp.4052 - 4062 | - |
dc.relation.isPartOf | IEEE Transactions on Neural Networks and Learning Systems | - |
dc.citation.title | IEEE Transactions on Neural Networks and Learning Systems | - |
dc.citation.volume | 32 | - |
dc.citation.number | 9 | - |
dc.citation.startPage | 4052 | - |
dc.citation.endPage | 4062 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Hardware & Architecture | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | Recurrent neural networks | - |
dc.subject.keywordPlus | Stochastic systems | - |
dc.subject.keywordPlus | Uncertainty analysis | - |
dc.subject.keywordPlus | Degraded performance | - |
dc.subject.keywordPlus | Electronic health record (EHRs) | - |
dc.subject.keywordPlus | Hospital mortality | - |
dc.subject.keywordPlus | Mean absolute error | - |
dc.subject.keywordPlus | Network parameters | - |
dc.subject.keywordPlus | Recurrent networks | - |
dc.subject.keywordPlus | State-of-the-art methods | - |
dc.subject.keywordPlus | Uncertainty propagation | - |
dc.subject.keywordPlus | Stochastic models | - |
dc.subject.keywordAuthor | Bioinformatics | - |
dc.subject.keywordAuthor | Data models | - |
dc.subject.keywordAuthor | deep generative model | - |
dc.subject.keywordAuthor | deep learning (DL) | - |
dc.subject.keywordAuthor | electronic health records (EHRs) | - |
dc.subject.keywordAuthor | Medical services | - |
dc.subject.keywordAuthor | missing value imputation | - |
dc.subject.keywordAuthor | mortality prediction | - |
dc.subject.keywordAuthor | Predictive models | - |
dc.subject.keywordAuthor | Stochastic processes | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Time series analysis | - |
dc.subject.keywordAuthor | time series modeling | - |
dc.subject.keywordAuthor | Uncertainty | - |
dc.subject.keywordAuthor | uncertainty. | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.