Compound Density Networks for Risk Prediction using Electronic Health Records

Yuxi Liu, Shaowen Qin, Zhenhao Zhang, Wei Shao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Electronic Health Records (EHRs) exhibit a high amount of missing data due to variations of patient conditions and treatment needs. Imputation of missing values has been considered an effective approach to deal with this challenge. Existing work separates imputation method and prediction model as two independent parts of an EHR-based machine learning system. We propose an integrated end-to-end approach by utilizing a Compound Density Network (CDNet) that allows the imputation method and prediction model to be tuned together within a single framework. CDNet consists of a Gated recurrent unit (GRU), a Mixture Density Network (MDN), and a Regularized Attention Network (RAN). The GRU is used as a latent variable model to model EHR data. The MDN is designed to sample latent variables generated by GRU. The RAN serves as a regularizer for less reliable imputed values. The architecture of CDNet enables GRU and MDN to iteratively leverage the output of each other to impute missing values, leading to a more accurate and robust prediction. We validate CDNet on the mortality prediction task on the MIMIC-III dataset. Our model outperforms state-of-the-art models by significant margins. We also empirically show that regularizing imputed values is a key factor for superior prediction performance. Analysis of prediction uncertainty shows that our model can capture both aleatoric and epistemic uncertainties, which offers model users a better understanding of the model results.

Original languageEnglish
Title of host publicationProceedings
Subtitle of host publication2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
EditorsDonald Adjeroh, Qi Long, Xinghua (Mindy) Shi, Fei Guo, Xiaohua Hu, Srinivas Aluru, Giri Narasimhan, Jianxin Wang, Mingon Kang, Ananda M. Mondal, Jin Liu
Place of PublicationUnited States
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1078-1085
Number of pages8
ISBN (Print)978166546819022
DOIs
Publication statusPublished - 2022
Event2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022 - Las Vegas, United States
Duration: 6 Dec 20228 Dec 2022

Publication series

NameProceedings - 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

Conference

Conference2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022
Country/TerritoryUnited States
CityLas Vegas
Period6/12/228/12/22

Bibliographical note

This conference was held in two locations - Las Vegas, USA & Changsha, China

Keywords

  • data mining
  • Electronic Health Records
  • machine learning
  • missing data imputation
  • model uncertainty

Fingerprint

Dive into the research topics of 'Compound Density Networks for Risk Prediction using Electronic Health Records'. Together they form a unique fingerprint.

Cite this