ABSTRACT
With the increasing prevalence of infectious diseases like COVID-19, there is a growing interest in modeling and predicting their transmission. Leveraging the wealth of mobile trajectory data collected through advanced localization and mobile communication techniques, numerous approaches have been proposed to predict the spatial spread of infectious diseases based on human mobility dynamics characterized by microscopic user contact graphs or macroscopic population flow graphs. However, existing pure macroscopic and microscopic models have limitations in terms of modeling capabilities or in protecting user privacy. Thus, in this study, we present a Multi-scale Spatial Disease prediction Network (MSDNet) for predicting the spatial spread of infectious diseases. The model predicts the spread of infectious diseases using a macromicro collaborative approach by combining the temporal and spatial characteristics of the macroscopic information in the population flow graph and the microscopic information in the user contact graph. To understand the coupling between human mobility and infectious disease transmission, we propose a loss term that combines infectious disease spread dynamics and modeling of infectious disease parameters that can achieve stable adaptation to key characteristics of infectious diseases even when human mobility is affected by policy measures such as travel restrictions. Extensive experimental results show the MSDNet model's superiority for epidemic prediction on graph networks using macro-micro collaboration, achieving a 15%-20% improvement in terms of RMSE and a 15%-30% improvement in terms of SMAPE compared to existing baseline models. In addition, we predict infectious disease parameters under changes in human mobility, and the results show that MSDNet could effectively distinguish between human mobility and infectious disease characteristics, achieving a relative improvement of 76% in terms of RMSE and 80% in terms of SMAPE in predicting infectious disease parameters under changes in human mobility.
- Parul Arora, Himanshu Kumar, and Bijaya Ketan Panigrahi. 2020. Prediction and analysis of COVID-19 positive cases using deep learning models: A descriptive case study of India. Chaos, Solitons & Fractals 139 (2020), 110017.Google ScholarCross Ref
- Norman TJ Bailey. 1986. Macro-modelling and prediction of epidemic spread at community level. Mathematical Modelling 7, 5--8 (1986), 689--717.Google ScholarCross Ref
- Andrew W Bartlow, Carrie Manore, Chonggang Xu, Kimberly A Kaufeld, Sara Del Valle, Amanda Ziemann, Geoffrey Fairchild, and Jeanne M Fair. 2019. Forecasting zoonotic infectious disease response to climate change: mosquito vectors and a changing environment. Veterinary sciences 6, 2 (2019), 40.Google Scholar
- Cristiane M Batistela, Diego PF Correa, Átila M Bueno, and José Roberto C Piqueira. 2021. SIRSi compartmental model for COVID-19 pandemic with immunity loss. Chaos, Solitons & Fractals 142 (2021), 110388.Google ScholarCross Ref
- Davide Chicco, Matthijs J Warrens, and Giuseppe Jurman. 2021. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science 7 (2021), e623.Google ScholarCross Ref
- Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014).Google ScholarDigital Library
- Songgaojun Deng, Shusen Wang, Huzefa Rangwala, Lijing Wang, and Yue Ning. 2020. Cola-GNN: Cross-location attention based graph neural networks for long-term ILI prediction. In Proceedings of the 29th ACM international conference on information & knowledge management. 245--254.Google ScholarDigital Library
- Angel N Desai, Moritz UG Kraemer, Sangeeta Bhatia, Anne Cori, Pierre Nouvellet, Mark Herringer, Emily L Cohn, Malwina Carrion, John S Brownstein, Lawrence C Madoff, et al. 2019. Real-time epidemic forecasting: challenges and opportunities. Health security 17, 4 (2019), 268--275.Google Scholar
- Martin Eichenbaum, Sergio T Rebelo, and Mathias Trabandt. 2020. Epidemics in the neoclassical and new-Keynesian models. (2020).Google Scholar
- Jeffrey L Elman. 1990. Finding structure in time. Cognitive science 14, 2 (1990), 179--211.Google Scholar
- Enrique Frias-Martinez, Graham Williamson, and Vanessa Frias-Martinez. 2011. An agent-based model of epidemic spread using human mobility and social network information. In IEEE international conference on privacy, security, risk and trust and IEEE international conference on social computing. IEEE, 57--64.Google ScholarCross Ref
- Junyi Gao, Rakshith Sharma, Cheng Qian, Lucas M Glass, Jeffrey Spaeder, Justin Romberg, Jimeng Sun, and Cao Xiao. 2021. STAN: spatio-temporal attention network for pandemic prediction using real-world evidence. Journal of the American Medical Informatics Association 28, 4 (2021), 733--743.Google ScholarCross Ref
- Nicholas C Grassly and Christophe Fraser. 2008. Mathematical models of infectious disease transmission. Nature Reviews Microbiology 6, 6 (2008), 477--487.Google ScholarCross Ref
- Shaobo He, Yuexi Peng, and Kehui Sun. 2020. SEIR modeling of the COVID-19 and its dynamics. Nonlinear dynamics 101 (2020), 1667--1680.Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780.Google ScholarDigital Library
- Ruvim Izikson, Daniel Brune, Jean-Sébastien Bolduc, Pierre Bourron, Marion Fournier, Tamala Mallett Moore, Aseem Pandey, Lucia Perez, Nessryne Sater, Anju Shrestha, et al. 2022. Safety and immunogenicity of a high-dose quadrivalent influenza vaccine administered concomitantly with a third dose of the mRNA-1273 SARS-CoV-2 vaccine in adults aged 65 years: a phase 2, randomised, open-label study. The Lancet Respiratory Medicine 10, 4 (2022), 392--402.Google ScholarCross Ref
- Shan Jiang, Yingxiang Yang, Siddharth Gupta, Daniele Veneziano, Shounak Athavale, and Marta C González. 2016. The TimeGeo modeling framework for urban mobility without travel surveys. Proceedings of the National Academy of Sciences 113, 37 (2016), E5370--E5378.Google ScholarCross Ref
- Amol Kapoor, Xue Ben, Luyang Liu, Bryan Perozzi, Matt Barnes, Martin Blais, and Shawn O'Banion. 2020. Examining covid-19 forecasting using spatio-temporal graph neural networks. arXiv preprint arXiv:2007.03113 (2020).Google Scholar
- Nikos Kargas, Cheng Qian, Nicholas D Sidiropoulos, Cao Xiao, Lucas M Glass, and Jimeng Sun. 2021. Stelar: Spatio-temporal tensor factorization with latent epidemiological regularization. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 4830--4837.Google ScholarCross Ref
- Cliff C Kerr, Robyn M Stuart, Dina Mistry, Romesh G Abeysuriya, Katherine Rosenfeld, Gregory R Hart, Rafael C Núñez, Jamie A Cohen, Prashanth Selvaraj, Brittany Hagedorn, et al. 2021. Covasim: an agent-based model of COVID-19 dynamics and interventions. PLOS Computational Biology 17, 7 (2021), e1009149.Google ScholarCross Ref
- Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- Moritz UG Kraemer, Nick Golding, Dionisio Bisanzio, Samir Bhatt, David M Pigott, SE Ray, OJ Brady, JS Brownstein, NR Faria, DAT Cummings, et al. 2019. Utilizing general human movement models to predict the spread of emerging infectious diseases in resource poor settings. Scientific reports 9, 1 (2019), 5151.Google Scholar
- Shannon L LaDeau, Gregory E Glass, N Thompson Hobbs, Andrew Latimer, and Richard S Ostfeld. 2011. Data-model fusion to better understand emerging pathogens and improve infectious disease forecasting. Ecological Applications 21, 5 (2011), 1443--1460.Google ScholarCross Ref
- Ying Liu and Joacim Rocklöv. 2022. The effective reproductive number of the Omicron variant of SARS-CoV-2 is several times relative to Delta. Journal of Travel Medicine 29, 3 (2022), taac037.Google ScholarCross Ref
- Dang Lien Minh, Abolghasem Sadeghi-Niaraki, Huynh Duc Huy, Kyungbok Min, and Hyeonjoon Moon. 2018. Deep learning approach for short-term stock trends prediction based on two-stream gated recurrent unit network. Ieee Access 6 (2018), 55392--55404.Google ScholarCross Ref
- Xiaolan Mo, Xiujuan Chen, Chifong Ieong, Xia Gao, Yingjie Li, Xin Liao, Huabin Yang, Huiyi Li, Fan He, Yanling He, et al. 2021. Early prediction of tacrolimus-induced tubular toxicity in pediatric refractory nephrotic syndrome using machine learning. Frontiers in Pharmacology 12 (2021), 638724.Google ScholarCross Ref
- Charles Murphy, Edward Laurence, and Antoine Allard. 2021. Deep learning of contagion dynamics on complex networks. Nature Communications 12, 1 (2021), 4720.Google ScholarCross Ref
- Petrônio CL Silva, Paulo VC Batista, Hélder S Lima, Marcos A Alves, Frederico G Guimarães, and Rodrigo CP Silva. 2020. COVID-ABS: An agent-based model of COVID-19 epidemic to simulate health and economic effects of social distancing interventions. Chaos, Solitons & Fractals 139 (2020), 110088.Google ScholarCross Ref
- Alexis Akira Toda. 2020. Susceptible-infected-recovered (sir) dynamics of covid-19 and economic impact. arXiv preprint arXiv:2003.11221 (2020).Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).Google Scholar
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- Lijing Wang, Jiangzhuo Chen, and Madhav Marathe. 2019. DEFSI: Deep learning based epidemic forecasting with synthetic information. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 9607--9612.Google ScholarDigital Library
- Shuai Xia, Qiaoshuai Lan, Yun Zhu, Chao Wang, Wei Xu, Yutang Li, Lijue Wang, Fanke Jiao, Jie Zhou, Chen Hua, et al. 2021. Structural and functional basis for pan-CoV fusion inhibitors against SARS-CoV-2 and its variants with preclinical evaluation. Signal Transduction and Targeted Therapy 6, 1 (2021), 288.Google ScholarCross Ref
- Zifeng Yang, Zhiqi Zeng, Ke Wang, Sook-San Wong, Wenhua Liang, Mark Zanin, Peng Liu, Xudong Cao, Zhongqiang Gao, Zhitong Mai, et al. 2020. Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions. Journal of thoracic disease 12, 3 (2020), 165.Google ScholarCross Ref
- Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, Will Hamilton, and Jure Leskovec. 2018. Hierarchical graph representation learning with differentiable pooling. Advances in neural information processing systems 31 (2018).Google Scholar
- Linyun Yu, Peng Cui, Fei Wang, Chaoming Song, and Shiqiang Yang. 2015. From micro to macro: Uncovering and predicting information cascading process with behavioral dynamics. In IEEE international conference on data mining. IEEE, 559--568.Google ScholarDigital Library
- Juanjuan Zhang, Maria Litvinova, Yuxia Liang, Yan Wang, Wei Wang, Shanlu Zhao, Qianhui Wu, Stefano Merler, Cécile Viboud, Alessandro Vespignani, et al. 2020. Changes in contact patterns shape the dynamics of the COVID-19 outbreak in China. Science 368, 6498 (2020), 1481--1486.Google Scholar
Index Terms
- Enhancing Spatial Spread Prediction of Infectious Diseases through Integrating Multi-scale Human Mobility Dynamics
Recommendations
Temporal analysis of infectious diseases: influenza
SAC '05: Proceedings of the 2005 ACM symposium on Applied computingA Bayesian network is developed to embed the probabilistic reasoning dependencies of the demographics on the incidence of infectious diseases. Influenza epidemics occur every year in both hemispheres during the winter. The Bayesian learning paradigm is ...
Enhancing Traceability of Infectious Diseases: A Blockchain-Based Approach
Highlights- Develop a Blockchain-based method for disease information tracing with key components including infectious disease information collection, information chain-...
AbstractThe global pandemic of COVID-19 has brought significant attentions to three important features of disease direct reporting systems: traceability, reliability, and effectiveness. A traditional disease direct reporting system has a ...
Analysis of the Vaccine Effect on Infectious Diseases by System Dynamics Model
BIBE2021: The Fifth International Conference on Biological Information and Biomedical EngineeringWhat is the impact of vaccine research and development on the prevention and control of infectious diseases, and what is the path of the impact? In this paper, the vaccination rate and effective rate were introduced into the system dynamics model of ...
Comments