TY - JOUR
T1 - Forecasting influenza activity using machine-learned mobility map
AU - Venkatramanan, Srinivasan
AU - Sadilek, Adam
AU - Fadikar, Arindam
AU - Barrett, Christopher L.
AU - Biggerstaff, Matthew
AU - Chen, Jiangzhuo
AU - Dotiwalla, Xerxes
AU - Eastham, Paul
AU - Gipson, Bryant
AU - Higdon, Dave
AU - Kucuktunc, Onur
AU - Lieber, Allison
AU - Lewis, Bryan L.
AU - Reynolds, Zane
AU - Vullikanti, Anil K.
AU - Wang, Lijing
AU - Marathe, Madhav
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12/1
Y1 - 2021/12/1
N2 - Human 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.
AB - Human 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.
UR - http://www.scopus.com/inward/record.url?scp=85100760141&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100760141&partnerID=8YFLogxK
U2 - 10.1038/s41467-021-21018-5
DO - 10.1038/s41467-021-21018-5
M3 - Article
C2 - 33563980
AN - SCOPUS:85100760141
SN - 2041-1723
VL - 12
JO - Nature communications
JF - Nature communications
IS - 1
M1 - 726
ER -