Stochastic Imputation and Uncertainty-Aware Attention to EHR for Mortality Prediction

Eunji Jun; Ahmad Wisnu Mulyadi; Heung Il Suk

doi:10.1109/IJCNN.2019.8852132

Stochastic Imputation and Uncertainty-Aware Attention to EHR for Mortality Prediction

Eunji Jun, Ahmad Wisnu Mulyadi, Heung Il Suk

Department of Artificial Intelligence

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

15 Citations (Scopus)

Abstract

Electronic health records (EHR) have become an important source of a patient data but characterized by a variety of missing values. Using the variational inference of Bayesian framework, variational autoencoder (VAE), a deep generative model, has been shown to be efficient and accurate to capture the latent structure of complex high-dimensional data. Recently, it has been used for missing data imputation. In this paper, we propose a general framework that incorporates effective missing data imputation using VAE and multivariate time series prediction. We utilize the uncertainty obtained from the generative network of the VAE and employ uncertainty-aware attention in imputing the missing values. We evaluated the performance of our architecture on real-world clinical dataset (MIMIC-III) for in-hospital mortality prediction task. Our results showed higher performance than other competing methods in mortality prediction task.

Original language	English
Title of host publication	2019 International Joint Conference on Neural Networks, IJCNN 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728119854
DOIs	https://doi.org/10.1109/IJCNN.2019.8852132
Publication status	Published - 2019 Jul
Event	2019 International Joint Conference on Neural Networks, IJCNN 2019 - Budapest, Hungary Duration: 2019 Jul 14 → 2019 Jul 19

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2019-July

Conference

Conference	2019 International Joint Conference on Neural Networks, IJCNN 2019
Country/Territory	Hungary
City	Budapest
Period	19/7/14 → 19/7/19

Bibliographical note

Funding Information:
This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No.2017-0-00053, A Technology Development of Artificial Intelligence Doctors for Cardiovascular Disease).

Publisher Copyright:
© 2019 IEEE.

Keywords

Bayesian framework
Deep learning
Electronic health records
Missing data imputation

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2019.8852132

Cite this

Jun, E., Mulyadi, A. W., & Suk, H. I. (2019). Stochastic Imputation and Uncertainty-Aware Attention to EHR for Mortality Prediction. In 2019 International Joint Conference on Neural Networks, IJCNN 2019 Article 8852132 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2019-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2019.8852132

Stochastic Imputation and Uncertainty-Aware Attention to EHR for Mortality Prediction. / Jun, Eunji; Mulyadi, Ahmad Wisnu; Suk, Heung Il.
2019 International Joint Conference on Neural Networks, IJCNN 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8852132 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2019-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Jun, E, Mulyadi, AW & Suk, HI 2019, Stochastic Imputation and Uncertainty-Aware Attention to EHR for Mortality Prediction. in 2019 International Joint Conference on Neural Networks, IJCNN 2019., 8852132, Proceedings of the International Joint Conference on Neural Networks, vol. 2019-July, Institute of Electrical and Electronics Engineers Inc., 2019 International Joint Conference on Neural Networks, IJCNN 2019, Budapest, Hungary, 19/7/14. https://doi.org/10.1109/IJCNN.2019.8852132

@inproceedings{61a87db8a32d40e4ac4c5d6b92b35c74,

title = "Stochastic Imputation and Uncertainty-Aware Attention to EHR for Mortality Prediction",

abstract = "Electronic health records (EHR) have become an important source of a patient data but characterized by a variety of missing values. Using the variational inference of Bayesian framework, variational autoencoder (VAE), a deep generative model, has been shown to be efficient and accurate to capture the latent structure of complex high-dimensional data. Recently, it has been used for missing data imputation. In this paper, we propose a general framework that incorporates effective missing data imputation using VAE and multivariate time series prediction. We utilize the uncertainty obtained from the generative network of the VAE and employ uncertainty-aware attention in imputing the missing values. We evaluated the performance of our architecture on real-world clinical dataset (MIMIC-III) for in-hospital mortality prediction task. Our results showed higher performance than other competing methods in mortality prediction task.",

keywords = "Bayesian framework, Deep learning, Electronic health records, Missing data imputation",

author = "Eunji Jun and Mulyadi, {Ahmad Wisnu} and Suk, {Heung Il}",

note = "Funding Information: This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No.2017-0-00053, A Technology Development of Artificial Intelligence Doctors for Cardiovascular Disease). Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 International Joint Conference on Neural Networks, IJCNN 2019 ; Conference date: 14-07-2019 Through 19-07-2019",

year = "2019",

month = jul,

doi = "10.1109/IJCNN.2019.8852132",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 International Joint Conference on Neural Networks, IJCNN 2019",

}

TY - GEN

T1 - Stochastic Imputation and Uncertainty-Aware Attention to EHR for Mortality Prediction

AU - Jun, Eunji

AU - Mulyadi, Ahmad Wisnu

AU - Suk, Heung Il

N1 - Funding Information: This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No.2017-0-00053, A Technology Development of Artificial Intelligence Doctors for Cardiovascular Disease). Publisher Copyright: © 2019 IEEE.

PY - 2019/7

Y1 - 2019/7

N2 - Electronic health records (EHR) have become an important source of a patient data but characterized by a variety of missing values. Using the variational inference of Bayesian framework, variational autoencoder (VAE), a deep generative model, has been shown to be efficient and accurate to capture the latent structure of complex high-dimensional data. Recently, it has been used for missing data imputation. In this paper, we propose a general framework that incorporates effective missing data imputation using VAE and multivariate time series prediction. We utilize the uncertainty obtained from the generative network of the VAE and employ uncertainty-aware attention in imputing the missing values. We evaluated the performance of our architecture on real-world clinical dataset (MIMIC-III) for in-hospital mortality prediction task. Our results showed higher performance than other competing methods in mortality prediction task.

AB - Electronic health records (EHR) have become an important source of a patient data but characterized by a variety of missing values. Using the variational inference of Bayesian framework, variational autoencoder (VAE), a deep generative model, has been shown to be efficient and accurate to capture the latent structure of complex high-dimensional data. Recently, it has been used for missing data imputation. In this paper, we propose a general framework that incorporates effective missing data imputation using VAE and multivariate time series prediction. We utilize the uncertainty obtained from the generative network of the VAE and employ uncertainty-aware attention in imputing the missing values. We evaluated the performance of our architecture on real-world clinical dataset (MIMIC-III) for in-hospital mortality prediction task. Our results showed higher performance than other competing methods in mortality prediction task.

KW - Bayesian framework

KW - Deep learning

KW - Electronic health records

KW - Missing data imputation

UR - http://www.scopus.com/inward/record.url?scp=85073253420&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2019.8852132

DO - 10.1109/IJCNN.2019.8852132

M3 - Conference contribution

AN - SCOPUS:85073253420

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2019 International Joint Conference on Neural Networks, IJCNN 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Joint Conference on Neural Networks, IJCNN 2019

Y2 - 14 July 2019 through 19 July 2019

ER -

Stochastic Imputation and Uncertainty-Aware Attention to EHR for Mortality Prediction

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this