STAN: spatio-temporal attention network for pandemic prediction using real-world evidence release_i6iaxzfl5bhhvek7zpo7ermhge

by Junyi Gao, Rakshith Sharma, Cheng Qian, Lucas M Glass, Jeffrey Spaeder, Justin Romberg, Jimeng Sun, Cao Xiao

Published in JAMIA Journal of the American Medical Informatics Association by Oxford University Press (OUP).

2021   Volume 28, Issue 4, p733-743

Abstract

<jats:title>Abstract</jats:title> <jats:sec> <jats:title>Objective</jats:title> We aim to develop a hybrid model for earlier and more accurate predictions for the number of infected cases in pandemics by (1) using patients' claims data from different counties and states that capture local disease status and medical resource utilization; (2) utilizing demographic similarity and geographical proximity between locations; and (3) integrating pandemic transmission dynamics into a deep learning model. </jats:sec> <jats:sec> <jats:title>Materials and Methods</jats:title> We proposed a spatio-temporal attention network (STAN) for pandemic prediction. It uses a graph attention network to capture spatio-temporal trends of disease dynamics and to predict the number of cases for a fixed number of days into the future. We also designed a dynamics-based loss term for enhancing long-term predictions. STAN was tested using both real-world patient claims data and COVID-19 statistics over time across US counties. </jats:sec> <jats:sec> <jats:title>Results</jats:title> STAN outperforms traditional epidemiological models such as susceptible-infectious-recovered (SIR), susceptible-exposed-infectious-recovered (SEIR), and deep learning models on both long-term and short-term predictions, achieving up to 87% reduction in mean squared error compared to the best baseline prediction model. </jats:sec> <jats:sec> <jats:title>Conclusions</jats:title> By combining information from real-world claims data and disease case counts data, STAN can better predict disease status and medical resource utilization. </jats:sec>
In application/xml+jats format

Archived Files and Locations

application/pdf  432.8 kB
file_ihkgsywljnf4fivdhx4ti76jeu
watermark.silverchair.com (publisher)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2021-01-22
Language   en ?
Journal Metadata
Not in DOAJ
In Keepers Registry
ISSN-L:  1067-5027
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: d4f90381-0174-4c99-9a0d-e795254b192e
API URL: JSON