VTechWorks staff will be away for the Independence Day holiday from July 4-7. We will respond to email inquiries on Monday, July 8. Thank you for your patience.
 

Forecasting influenza activity using machine-learned mobility map

Simple item page
dc.contributor.authorVenkatramanan, Srinivasanen
dc.contributor.authorSadilek, Adamen
dc.contributor.authorFadikar, Arindamen
dc.contributor.authorBarrett, Christopher L.en
dc.contributor.authorBiggerstaff, Matthewen
dc.contributor.authorChen, Jiangzhuoen
dc.contributor.authorDotiwalla, Xerxesen
dc.contributor.authorEastham, Paulen
dc.contributor.authorGipson, Bryanten
dc.contributor.authorHigdon, Daveen
dc.contributor.authorKucuktunc, Onuren
dc.contributor.authorLieber, Allisonen
dc.contributor.authorLewis, Bryan L.en
dc.contributor.authorReynolds, Zaneen
dc.contributor.authorVullikanti, Anil Kumar S.en
dc.contributor.authorWang, Lijingen
dc.contributor.authorMarathe, Madhav V.en
dc.contributor.departmentStatisticsen
dc.date.accessioned2021-05-20T12:08:16Zen
dc.date.available2021-05-20T12:08:16Zen
dc.date.issued2021-02-09en
dc.description.abstractHuman mobility is a primary driver of infectious disease spread. However, existing data is limited in availability, coverage, granularity, and timeliness. Data-driven forecasts of disease dynamics are crucial for decision-making by health officials and private citizens alike. In this work, we focus on a machine-learned anonymized mobility map (hereon referred to as AMM) aggregated over hundreds of millions of smartphones and evaluate its utility in forecasting epidemics. We factor AMM into a metapopulation model to retrospectively forecast influenza in the USA and Australia. We show that the AMM model performs on-par with those based on commuter surveys, which are sparsely available and expensive. We also compare it with gravity and radiation based models of mobility, and find that the radiation model's performance is quite similar to AMM and commuter flows. Additionally, we demonstrate our model's ability to predict disease spread even across state boundaries. Our work contributes towards developing timely infectious disease forecasting at a global scale using human mobility datasets expanding their applications in the area of infectious disease epidemiology. Human mobility plays a central role in the spread of infectious diseases and can help in forecasting incidence. Here the authors show a comparison of multiple mobility benchmarks in forecasting influenza, and demonstrate the value of a machine-learned mobility map with global coverage at multiple spatial scales.en
dc.description.notesWe thank Rishi Bal, Avi Bar, Curt Black, Susan Cadrecha, Stephanie Cason, Ciro Cattuto, Charina Chou, Katherine Chou, Iz Conroy, Liz Davidoff, Jeff Dean, Jutta Degener, Damien Desfontaines, Jason Freidenfelds, Vivien Hoang, Sarah Holland, Michael Howell, Pan-Pan Jiang, Ali Lange, Bhaskar Mehta, Caitlin Niedermeyer, Genevieve Park, Chase Rigby, Kathryn Rough, Flavia Sekles, Calvin Seto, Rachel Soh, Aaron Stein, Chandu Thota, Michele Tizzoni, and Ashley Zlatinov for their insights and guidance. We also thank our external collaborators and members of the Network Systems Science and Advanced Computing Division (NSSAC) for their suggestions and comments. This work has been partially supported by DTRA CNIMS Contract HDTRA1-11-D-0016-0001, NIH MIDAS Grant 5U01GM070694, NIH Grant 1R01GM109718, NSF DIBBS Grant ACI-1443054, NSF EAGER Grant CMMI-1745207, NSF BIG DATA Grant IIS-1633028. The findings and conclusions in this report are those of the authors and do not necessarily represent the official position of the funding agencies or Centers for Disease Control and Prevention.en
dc.description.sponsorshipDTRA CNIMS [HDTRA1-11-D-0016-0001]; NIH MIDAS GrantUnited States Department of Health & Human ServicesNational Institutes of Health (NIH) - USA [5U01GM070694]; NIHUnited States Department of Health & Human ServicesNational Institutes of Health (NIH) - USA [1R01GM109718]; NSF DIBBS GrantNational Science Foundation (NSF)NSF - Office of the Director (OD) [ACI-1443054]; NSF EAGER GrantNational Science Foundation (NSF) [CMMI-1745207]; NSF BIG DATA Grant [IIS-1633028]en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1038/s41467-021-21018-5en
dc.identifier.issn2041-1723en
dc.identifier.issue1en
dc.identifier.other726en
dc.identifier.pmid33563980en
dc.identifier.urihttp://hdl.handle.net/10919/103393en
dc.identifier.volume12en
dc.language.isoenen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.titleForecasting influenza activity using machine-learned mobility mapen
dc.title.serialNature Communicationsen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.dcmitypeStillImageen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
s41467-021-21018-5.pdf
Size:
2.81 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

Scholarly Works, Statistics
Destination Area: Global Systems Science (GSS)