TY - GEN
T1 - PopNet
T2 - 31st ACM World Wide Web Conference, WWW 2022
AU - Gao, Junyi
AU - Xiao, Cao
AU - Glass, Lucas M.
AU - Sun, Jimeng
N1 - This work was supported in part by the Center for Information Technology Policy at Princeton University. The authors also thank the Knight Foundation for research support. They thank Ben Kaiser and Eli Lucherini for feedback on the manuscript, Sanne Kruikemeier and Tom Dopper for fruitful discussions on the research process, Ashley Gorham for the support in the initial steps of the study, and Minos Papakyriakopoulos and Lev Cohen for their contributions in tweets’ labeling. They also thank the anonymous reviewers for their constructive comments.
PY - 2022/4/25
Y1 - 2022/4/25
N2 - Population-level disease prediction estimates the number of potential patients of particular diseases in some location at a future time based on (frequently updated) historical disease statistics. Existing approaches often assume the existing disease statistics are reliable and will not change. However, in practice, data collection is often time-consuming and has time delays, with both historical and current disease statistics being updated continuously. In this work, we propose a real-time population-level disease prediction model which captures data latency (PopNet) and incorporates the updated data for improved predictions. To achieve this goal, PopNet models real-time data and updated data using two separate systems, each capturing spatial and temporal effects using hybrid graph attention networks and recurrent neural networks. PopNet then fuses the two systems using both spatial and temporal latency-aware attentions in an end-to-end manner. We evaluate PopNet on real-world disease datasets and show that PopNet consistently outperforms all baseline disease prediction and general spatial-temporal prediction models, achieving up to 47% lower root mean squared error and 24% lower mean absolute error compared with the best baselines.
AB - Population-level disease prediction estimates the number of potential patients of particular diseases in some location at a future time based on (frequently updated) historical disease statistics. Existing approaches often assume the existing disease statistics are reliable and will not change. However, in practice, data collection is often time-consuming and has time delays, with both historical and current disease statistics being updated continuously. In this work, we propose a real-time population-level disease prediction model which captures data latency (PopNet) and incorporates the updated data for improved predictions. To achieve this goal, PopNet models real-time data and updated data using two separate systems, each capturing spatial and temporal effects using hybrid graph attention networks and recurrent neural networks. PopNet then fuses the two systems using both spatial and temporal latency-aware attentions in an end-to-end manner. We evaluate PopNet on real-world disease datasets and show that PopNet consistently outperforms all baseline disease prediction and general spatial-temporal prediction models, achieving up to 47% lower root mean squared error and 24% lower mean absolute error compared with the best baselines.
KW - Graph attention network
KW - Population health prediction
KW - Spatio-temporal prediction
UR - http://www.scopus.com/inward/record.url?scp=85129832584&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129832584&partnerID=8YFLogxK
U2 - 10.1145/3485447.3512127
DO - 10.1145/3485447.3512127
M3 - Conference contribution
AN - SCOPUS:85129832584
T3 - WWW 2022 - Proceedings of the ACM Web Conference 2022
SP - 2552
EP - 2562
BT - WWW 2022 - Proceedings of the ACM Web Conference 2022
PB - Association for Computing Machinery
Y2 - 25 April 2022 through 29 April 2022
ER -