{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:48:46Z","timestamp":1781974126893,"version":"3.54.5"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T00:00:00Z","timestamp":1736380800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Key Programs of the National Natural Science Foundation of China","award":["12231012"],"award-info":[{"award-number":["12231012"]}]},{"name":"Joint Fund Priority Support Program of the National Natural Science Foundation of China","award":["U23A20331"],"award-info":[{"award-number":["U23A20331"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Human mobility between different regions is a major factor in large-scale outbreaks of infectious diseases. Deep learning models incorporating infectious disease transmission dynamics for predicting the spread of multi-regional outbreaks due to human mobility have become a hot research topic. In this study, we incorporate the Graph Transformer Neural Network and graph learning mechanisms into a metapopulation SIR model to build a hybrid framework, Metapopulation Graph Transformer Neural Network (M-Graphormer), for high-dimensional parameter estimation and multi-regional epidemic prediction. The framework effectively solves the problem that existing models may lose some hidden spatial dependencies in the data when dealing with the dynamic graph structure of the network due to human mobility. We performed multi-wave infectious disease prediction in multiple regions based on real epidemic data. The results show that the framework is capable of performing high-dimensional parameter estimation and accurately predicting epidemic transmission dynamics in multiple regions even with low data quality. In addition, we retrospectively extrapolate the temporal evolution patterns of contact rate under different interventions implemented in different regions, reflecting the dynamics of intervention intensity and the need for flexibility in adjusting interventions in different regions. To provide early warning of infectious disease transmission, we retrospectively predicted the arrival time of infectious diseases using data from the early stages of outbreaks.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1012738","type":"journal-article","created":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T18:24:33Z","timestamp":1736447073000},"page":"e1012738","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":15,"title":["Multi-region infectious disease prediction modeling based on spatio-temporal graph neural network and the dynamic model"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1628-5744","authenticated-orcid":true,"given":"Xiaoyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9763-707X","authenticated-orcid":true,"given":"Zhen","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,1,9]]},"reference":[{"issue":"1","key":"pcbi.1012738.ref001","article-title":"Infectious disease implications of large-scale migration of Venezuelan nationals","volume":"25","author":"AR Tuite","year":"2018","journal-title":"J Travel Med"},{"issue":"6490","key":"pcbi.1012738.ref002","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1126\/science.abb4218","article-title":"The effect of human mobility and control measures on the COVID-19 epidemic in China","volume":"368","author":"MU Kraemer","year":"2020","journal-title":"Science"},{"issue":"6","key":"pcbi.1012738.ref003","doi-asserted-by":"crossref","first-page":"cnaa041","DOI":"10.1093\/comnet\/cnaa041","article-title":"The impact of human mobility networks on the global spread of COVID-19","volume":"8","author":"MG Ha\u00cb?ncean","year":"2020","journal-title":"Journal of Complex Networks"},{"issue":"44","key":"pcbi.1012738.ref004","doi-asserted-by":"crossref","first-page":"27087","DOI":"10.1073\/pnas.2010836117","article-title":"Mobile device data reveal the dynamics in a positive relationship between human mobility and COVID-19 infections","volume":"117","author":"C Xiong","year":"2020","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"1","key":"pcbi.1012738.ref005","doi-asserted-by":"crossref","first-page":"20742","DOI":"10.1038\/s41598-020-77751-2","article-title":"Quantifying human mobility behaviour changes during the COVID-19 outbreak in the United States","volume":"10","author":"Y Pan","year":"2020","journal-title":"Sci Rep"},{"issue":"6557","key":"pcbi.1012738.ref006","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1126\/science.abj0113","article-title":"Spatiotemporal invasion dynamics of SARS-CoV-2 lineage B. 1.1. 7 emergence","volume":"373","author":"MU Kraemer","year":"2021","journal-title":"Science"},{"issue":"3","key":"pcbi.1012738.ref007","doi-asserted-by":"crossref","DOI":"10.3390\/math7030304","article-title":"Role of Media and Effects of Infodemics and Escapes in the Spatial Spread of Epidemics: A Stochastic Multi-Region Model with Optimal Control Approach","volume":"7","author":"F El Kihal","year":"2019","journal-title":"Mathematics"},{"issue":"23","key":"pcbi.1012738.ref008","article-title":"The Effect of Local and Global Interventions on Epidemic Spreading","volume":"18","author":"J Fan","year":"2021","journal-title":"Int J Environ Res Public Health"},{"key":"pcbi.1012738.ref009","doi-asserted-by":"crossref","first-page":"103010","DOI":"10.1016\/j.cities.2020.103010","article-title":"Spread of COVID-19 in China: analysis from a city-based epidemic and mobility model","volume":"110","author":"Y Wei","year":"2021","journal-title":"Cities"},{"issue":"7","key":"pcbi.1012738.ref010","doi-asserted-by":"crossref","first-page":"e0254403","DOI":"10.1371\/journal.pone.0254403","article-title":"The effect of human mobility restrictions on the COVID-19 transmission network in China","volume":"16","author":"T Oka","year":"2021","journal-title":"PLoS One"},{"issue":"1","key":"pcbi.1012738.ref011","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1186\/s13662-018-1801-x","article-title":"Moment closure of infectious diseases model on heterogeneous metapopulation network","volume":"2018","author":"S Feng","year":"2018","journal-title":"Adv Differ Equ"},{"issue":"18","key":"pcbi.1012738.ref012","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2007488118","article-title":"Comparing metapopulation dynamics of infectious diseases under different models of human movement","volume":"118","author":"DT Citron","year":"2021","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"1","key":"pcbi.1012738.ref013","doi-asserted-by":"crossref","first-page":"10546","DOI":"10.1038\/s41598-023-37192-z","article-title":"Role of immigration and emigration on the spread of COVID-19 in a multipatch environment: a case study of India","volume":"13","author":"T Das","year":"2023","journal-title":"Sci Rep"},{"key":"pcbi.1012738.ref014","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1038\/srep00062","article-title":"Modeling human mobility responses to the large-scale spreading of infectious diseases","volume":"1","author":"S Meloni","year":"2011","journal-title":"Sci Rep"},{"key":"pcbi.1012738.ref015","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.amc.2019.05.005","article-title":"Infectious diseases spreading on a metapopulation network coupled with its second-neighbor network","volume":"361","author":"S Feng","year":"2019","journal-title":"Appl Math Comput"},{"issue":"1829","key":"pcbi.1012738.ref016","doi-asserted-by":"crossref","first-page":"20200272","DOI":"10.1098\/rstb.2020.0272","article-title":"A spatial model of COVID-19 transmission in England and Wales: early spread, peak timing and the impact of seasonality","volume":"376","author":"L Danon","year":"2021","journal-title":"Philos Trans R Soc Lond B Biol Sci"},{"issue":"5","key":"pcbi.1012738.ref017","doi-asserted-by":"crossref","first-page":"e1011123","DOI":"10.1371\/journal.pcbi.1011123","article-title":"Understanding the impact of mobility on COVID-19 spread: A hybrid gravity-metapopulation model of COVID-19","volume":"19","author":"SA Iyaniwura","year":"2023","journal-title":"PLoS Comput Biol"},{"issue":"3","key":"pcbi.1012738.ref018","article-title":"LSTM-RNN Based Approach for Prediction of Dengue Cases in India","volume":"25","author":"AR Doni","year":"2020","journal-title":"Ing\u00e9nierie des Syst\u00e9mes d\u2019Information"},{"issue":"1","key":"pcbi.1012738.ref019","doi-asserted-by":"crossref","first-page":"e0262708","DOI":"10.1371\/journal.pone.0262708","article-title":"Deep learning via LSTM models for COVID-19 infection forecasting in India","volume":"17","author":"R Chandra","year":"2022","journal-title":"PLoS One"},{"issue":"9","key":"pcbi.1012738.ref020","doi-asserted-by":"crossref","first-page":"e0237750","DOI":"10.1371\/journal.pone.0237750","article-title":"Prediction of hepatitis E using machine learning models","volume":"15","author":"Y Guo","year":"2020","journal-title":"PLoS One"},{"key":"pcbi.1012738.ref021","doi-asserted-by":"crossref","first-page":"109864","DOI":"10.1016\/j.chaos.2020.109864","article-title":"Time series forecasting of COVID-19 transmission in Canada using LSTM networks","volume":"135","author":"VKR Chimmula","year":"2020","journal-title":"Chaos Solitons Fractals"},{"key":"pcbi.1012738.ref022","doi-asserted-by":"crossref","first-page":"110017","DOI":"10.1016\/j.chaos.2020.110017","article-title":"Prediction and analysis of COVID-19 positive cases using deep learning models: A descriptive case study of India","volume":"139","author":"P Arora","year":"2020","journal-title":"Chaos Solitons Fractals"},{"issue":"1","key":"pcbi.1012738.ref023","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/TBDATA.2020.3032755","article-title":"An Epidemiological Neural Network Exploiting Dynamic Graph Structured Data Applied to the COVID-19 Outbreak","volume":"7","author":"V La Gatta","year":"2021","journal-title":"IEEE Trans Big Data"},{"key":"pcbi.1012738.ref024","unstructured":"Kapoor A, Ben X, Liu L, Perozzi B, Barnes M, Blais M, et al. Examining covid-19 forecasting using spatio-temporal graph neural networks. arXiv preprint arXiv:200703113. 2020."},{"issue":"11","key":"pcbi.1012738.ref025","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1038\/s43588-021-00158-0","article-title":"Identifiability and predictability of integer- and fractional-order epidemiological models using physics-informed neural networks","volume":"1","author":"E Kharazmi","year":"2021","journal-title":"Nat Comput Sci"},{"issue":"10","key":"pcbi.1012738.ref026","doi-asserted-by":"crossref","first-page":"e1011535","DOI":"10.1371\/journal.pcbi.1011535","article-title":"Combining the dynamic model and deep neural networks to identify the intensity of interventions during COVID-19 pandemic","volume":"19","author":"M He","year":"2023","journal-title":"PLoS Comput Biol"},{"issue":"4","key":"pcbi.1012738.ref027","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1093\/jamia\/ocaa322","article-title":"STAN: spatio-temporal attention network for pandemic prediction using real-world evidence","volume":"28","author":"J Gao","year":"2021","journal-title":"J Am Med Inform Assoc"},{"issue":"11","key":"pcbi.1012738.ref028","doi-asserted-by":"crossref","first-page":"12191","DOI":"10.1609\/aaai.v36i11.21479","article-title":"CausalGNN: Causal-Based Graph Neural Networks for Spatio-Temporal Epidemic Forecasting","volume":"36","author":"L Wang","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"pcbi.1012738.ref029","doi-asserted-by":"crossref","unstructured":"Cao Q, Jiang R, Yang C, Fan Z, Song X, Shibasaki R, editors. MepoGNN: Metapopulation Epidemic Forecasting with\u00c2 Graph Neural Networks. Machine Learning and Knowledge Discovery in Databases; 2023 2023\/\/; Cham: Springer Nature Switzerland.","DOI":"10.1007\/978-3-031-26422-1_28"},{"issue":"4","key":"pcbi.1012738.ref030","article-title":"MPSTAN: Metapopulation-Based Spatio-Temporal Attention Network for Epidemic Forecasting","volume":"26","author":"J Mao","year":"2024","journal-title":"Entropy (Basel)"},{"issue":"2","key":"pcbi.1012738.ref031","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1111\/insr.12402","article-title":"A Review of Multi-Compartment Infectious Disease Models","volume":"88","author":"L Tang","year":"2020","journal-title":"Int Stat Rev"},{"key":"pcbi.1012738.ref032","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"C Ying","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"pcbi.1012738.ref033","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"issue":"6164","key":"pcbi.1012738.ref034","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1126\/science.1245200","article-title":"The hidden geometry of complex, network-driven contagion phenomena","volume":"342","author":"D Brockmann","year":"2013","journal-title":"science"},{"key":"pcbi.1012738.ref035","unstructured":"Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:151107122. 2015."},{"key":"pcbi.1012738.ref036","unstructured":"Dauphin YN, Fan A, Auli M, Grangier D. Language Modeling with Gated Convolutional Networks. In: Doina P, Yee Whye T, editors. Proceedings of the 34th International Conference on Machine Learning; Proceedings of Machine Learning Research: PMLR; 2017. p. 933\u201341."},{"issue":"6498","key":"pcbi.1012738.ref037","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1126\/science.abb8001","article-title":"Changes in contact patterns shape the dynamics of the COVID-19 outbreak in China","volume":"368","author":"J Zhang","year":"2020","journal-title":"Science"},{"issue":"5","key":"pcbi.1012738.ref038","doi-asserted-by":"crossref","first-page":"e261","DOI":"10.1016\/S2468-2667(20)30073-6","article-title":"The effect of control strategies to reduce social mixing on outcomes of the COVID-19 epidemic in Wuhan, China: a modelling study","volume":"5","author":"K Prem","year":"2020","journal-title":"Lancet Public Health"},{"issue":"6","key":"pcbi.1012738.ref039","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1038\/s41562-021-01063-2","article-title":"Integrated vaccination and physical distancing interventions to prevent future COVID-19 waves in Chinese cities","volume":"5","author":"B Huang","year":"2021","journal-title":"Nat Hum Behav"},{"key":"pcbi.1012738.ref040","unstructured":"Health Commission of the People\u2019s Republic of China. [cited 30 Dec 2022]. Available from: http:\/\/www.nhc.gov.cn\/."},{"key":"pcbi.1012738.ref041","unstructured":"Beijing Health Commission.[cited 30 Dec 2022]. Available from: http:\/\/wjw.beijing.gov.cn\/"},{"key":"pcbi.1012738.ref042","unstructured":"National Bureau of Statistics of China. [cited 22 Oct 2023]. Available from: https:\/\/www.stats.gov.cn\/"},{"key":"pcbi.1012738.ref043","unstructured":"Baidu migration. [cited 22 Oct 2023]. Available from: https:\/\/qianxi.baidu.com\/"},{"key":"pcbi.1012738.ref044","first-page":"616","article-title":"An inversion of the constitution of the Baidu migration scale index","author":"C Wang","year":"2021","journal-title":"Dianzi Keji Daxue Xuebao\/Journal of the University of Electronic Science and Technology of China"},{"issue":"6","key":"pcbi.1012738.ref045","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1038\/s41591-022-01828-w","article-title":"A joint international collaboration to address the inevitable mental health crisis in Ukraine","volume":"28","author":"W Bai","year":"2022","journal-title":"Nat Med"},{"issue":"1","key":"pcbi.1012738.ref046","doi-asserted-by":"crossref","first-page":"013105","DOI":"10.1063\/1.5002009","article-title":"Estimating epidemic arrival times using linear spreading theory","volume":"28","author":"LM Chen","year":"2018","journal-title":"Chaos"},{"issue":"1","key":"pcbi.1012738.ref047","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s11538-022-01110-7","article-title":"Epidemic Spreading on Complex Networks as Front Propagation into an Unstable State","volume":"85","author":"A Armbruster","year":"2022","journal-title":"Bull Math Biol"},{"key":"pcbi.1012738.ref048","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.tranpol.2020.05.012","article-title":"Exploring the roles of high-speed train, air and coach services in the spread of COVID-19 in China","volume":"94","author":"Y Zhang","year":"2020","journal-title":"Transp Policy (Oxf)"},{"key":"pcbi.1012738.ref049","doi-asserted-by":"crossref","first-page":"100397","DOI":"10.1016\/j.epidem.2020.100397","article-title":"The effects of border control and quarantine measures on the spread of COVID-19","volume":"32","author":"MP Hossain","year":"2020","journal-title":"Epidemics"},{"issue":"7820","key":"pcbi.1012738.ref050","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1038\/s41586-020-2405-7","article-title":"Estimating the effects of non-pharmaceutical interventions on COVID-19 in Europe","volume":"584","author":"S Flaxman","year":"2020","journal-title":"Nature"},{"issue":"7825","key":"pcbi.1012738.ref051","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1038\/s41586-020-2293-x","article-title":"Effect of non-pharmaceutical interventions to contain COVID-19 in China","volume":"585","author":"S Lai","year":"2020","journal-title":"Nature"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T18:24:54Z","timestamp":1736447094000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012738"}},"subtitle":[],"editor":[{"given":"Jessica M.","family":"Conway","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1,9]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012738","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,9]]}}}