{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T15:12:03Z","timestamp":1792422723765,"version":"4.5.0"},"update-to":[{"DOI":"10.1371\/journal.pntd.0010071","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T00:00:00Z","timestamp":1644278400000}}],"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T00:00:00Z","timestamp":1642982400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["R01GM130668"],"award-info":[{"award-number":["R01GM130668"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018077","name":"Harvard Data Science Initiative","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018077","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100018077","name":"harvard data science initiative","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018077","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100018077","name":"harvard data science initiative","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018077","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100018077","name":"harvard data science initiative","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018077","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100018077","name":"harvard data science initiative","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018077","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosntds.org"],"crossmark-restriction":false},"short-container-title":["PLoS Negl Trop Dis"],"abstract":"<jats:p>The dengue virus affects millions of people every year worldwide, causing large epidemic outbreaks that disrupt people\u2019s lives and severely strain healthcare systems. In the absence of a reliable vaccine against dengue or an effective treatment to manage the illness in humans, most efforts to combat dengue infections have focused on preventing its vectors, mainly the Aedes aegypti mosquito, from flourishing across the world. These mosquito-control strategies need reliable disease activity surveillance systems to be deployed. Despite significant efforts to estimate dengue incidence using a variety of data sources and methods, little work has been done to understand the relative contribution of the different data sources to improved prediction. Additionally, scholarship on the topic had initially focused on prediction systems at the national- and state-levels, and much remains to be done at the finer spatial resolutions at which health policy interventions often occur. We develop a methodological framework to assess and compare dengue incidence estimates at the city level, and evaluate the performance of a collection of models on 20 different cities in Brazil. The data sources we use towards this end are weekly incidence counts from prior years (seasonal autoregressive terms), weekly-aggregated weather variables, and real-time internet search data. We find that both random forest-based models and LASSO regression-based models effectively leverage these multiple data sources to produce accurate predictions, and that while the performance between them is comparable on average, the former method produces fewer extreme outliers, and can thus be considered more robust. For real-time predictions that assume long delays (6\u20138 weeks) in the availability of epidemiological data, we find that real-time internet search data are the strongest predictors of dengue incidence, whereas for predictions that assume short delays (1\u20133 weeks), in which the error rate is halved (as measured by relative RMSE), short-term and seasonal autocorrelation are the dominant predictors. Despite the difficulties inherent to city-level prediction, our framework achieves meaningful and actionable estimates across cities with different demographic, geographic and epidemic characteristics.<\/jats:p>","DOI":"10.1371\/journal.pntd.0010071","type":"journal-article","created":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T13:39:33Z","timestamp":1643031573000},"page":"e0010071","update-policy":"https:\/\/doi.org\/10.1371\/journal.pntd.corrections_policy","source":"Crossref","is-referenced-by-count":19,"title":["Predicting dengue incidence leveraging internet-based data sources. A case study in 20 cities in Brazil"],"prefix":"10.1371","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4906-0779","authenticated-orcid":true,"given":"Gal","family":"Koplewitz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1026-5734","authenticated-orcid":true,"given":"Fred","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8939-8841","authenticated-orcid":true,"given":"Leonardo","family":"Clemente","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caroline","family":"Buckee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mauricio","family":"Santillana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,1,24]]},"reference":[{"key":"pntd.0010071.ref001","unstructured":"World Health Organization. Dengue and severe dengue; 2021. https:\/\/www.who.int\/en\/news-room\/fact-sheets\/detail\/dengue-and-severe-dengue"},{"issue":"9","key":"pntd.0010071.ref002","doi-asserted-by":"crossref","first-page":"1508","DOI":"10.1038\/s41564-019-0476-8","article-title":"The current and future global distribution and population at risk of dengue","volume":"4","author":"JP Messina","year":"2019","journal-title":"Nature microbiology"},{"key":"pntd.0010071.ref003","unstructured":"World Health Organization, Special Programme for Research, Training in Tropical Diseases, World Health Organization. Department of Control of Neglected Tropical Diseases, World Health Organization. Epidemic, Pandemic Alert. Dengue: guidelines for diagnosis, treatment, prevention and control. World Health Organization; 2009."},{"issue":"11","key":"pntd.0010071.ref004","doi-asserted-by":"crossref","first-page":"e0006070","DOI":"10.1371\/journal.pntd.0006070","article-title":"The introduction of dengue follows transportation infrastructure changes in the state of Acre, Brazil: A network-based analysis","volume":"11","author":"RM Lana","year":"2017","journal-title":"PLoS neglected tropical diseases"},{"issue":"1","key":"pntd.0010071.ref005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12889-019-6641-4","article-title":"30 years of fatal dengue cases in Brazil: a review","volume":"19","author":"PC Nunes","year":"2019","journal-title":"BMC public health"},{"issue":"8","key":"pntd.0010071.ref006","doi-asserted-by":"crossref","first-page":"1022","DOI":"10.1111\/j.1365-3156.2008.02112.x","article-title":"What does dengue disease surveillance contribute to predicting and detecting outbreaks and describing trends?","volume":"13","author":"S Runge-Ranzinger","year":"2008","journal-title":"Tropical Medicine & International Health"},{"issue":"5","key":"pntd.0010071.ref007","doi-asserted-by":"crossref","first-page":"e1215","DOI":"10.1371\/journal.pntd.0001215","article-title":"A new approach to monitoring dengue activity","volume":"5","author":"LC Madoff","year":"2011","journal-title":"PLoS neglected tropical diseases"},{"issue":"11","key":"pntd.0010071.ref008","doi-asserted-by":"crossref","first-page":"e50972","DOI":"10.1371\/journal.pone.0050972","article-title":"The incubation periods of dengue viruses","volume":"7","author":"M Chan","year":"2012","journal-title":"PloS one"},{"key":"pntd.0010071.ref009","unstructured":"Centers for Disease Control and Prevention. Dengue; 2016. http:\/\/www.cdc.gov\/dengue\/."},{"issue":"11","key":"pntd.0010071.ref010","doi-asserted-by":"crossref","first-page":"e78263","DOI":"10.1371\/journal.pone.0078263","article-title":"Dengue vector dynamics (Aedes aegypti) influenced by climate and social factors in Ecuador: implications for targeted control","volume":"8","author":"AM Stewart Ibarra","year":"2013","journal-title":"PloS one"},{"issue":"11","key":"pntd.0010071.ref011","doi-asserted-by":"crossref","first-page":"e1908","DOI":"10.1371\/journal.pntd.0001908","article-title":"Forecast of dengue incidence using temperature and rainfall","volume":"6","author":"YL Hii","year":"2012","journal-title":"PLoS neglected tropical diseases"},{"issue":"3","key":"pntd.0010071.ref012","first-page":"347","article-title":"Distribution, seasonal variation & dengue transmission prediction in Sisaket, Thailand","volume":"138","author":"S Wongkoon","year":"2013","journal-title":"The Indian journal of medical research"},{"issue":"8","key":"pntd.0010071.ref013","doi-asserted-by":"crossref","first-page":"944","DOI":"10.1258\/ebm.2011.010402","article-title":"The role of climate variability and change in the transmission dynamics and geographic distribution of dengue","volume":"236","author":"KT Thai","year":"2011","journal-title":"Experimental biology and medicine"},{"issue":"8","key":"pntd.0010071.ref014","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1017\/S0950268809002040","article-title":"Assessing the effects of temperature on the population of Aedes aegypti, the vector of dengue","volume":"137","author":"HM Yang","year":"2009","journal-title":"Epidemiology & Infection"},{"issue":"8","key":"pntd.0010071.ref015","doi-asserted-by":"crossref","first-page":"e1799","DOI":"10.1371\/journal.pntd.0001799","article-title":"The interactive roles of Aedes aegypti super-production and human density in dengue transmission","volume":"6","author":"H Padmanabha","year":"2012","journal-title":"PLoS neglected tropical disease"},{"issue":"1","key":"pntd.0010071.ref016","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1017\/S0950268807008126","article-title":"Environmental factors and incidence of dengue fever and dengue haemorrhagic fever in an urban area, Southern Thailand","volume":"136","author":"S Thammapalo","year":"2008","journal-title":"Epidemiology & Infection"},{"issue":"1","key":"pntd.0010071.ref017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/srep33707","article-title":"Evaluating the performance of infectious disease forecasts: A comparison of climate-driven and seasonal dengue forecasts for Mexico","volume":"6","author":"MA Johansson","year":"2016","journal-title":"Scientific reports"},{"key":"pntd.0010071.ref018","first-page":"99","article-title":"Forecasting dengue haemorrhagic fever cases in Southern Thailand using ARIMA Models","volume":"30","author":"S Promprou","year":"2006","journal-title":"Dengue Bulletin"},{"key":"pntd.0010071.ref019","first-page":"29","article-title":"Forecasting dengue incidence in Dhaka, Bangladesh: A time series analysis","volume":"32","author":"ZM Choudhury","year":"2008","journal-title":"Dengue Bulletin, WHO Regional Office for South-East Asia"},{"issue":"3","key":"pntd.0010071.ref020","doi-asserted-by":"crossref","first-page":"598","DOI":"10.4269\/ajtmh.13-0303","article-title":"Intra-and interseasonal autoregressive prediction of dengue outbreaks using local weather and regional climate for a tropical environment in Colombia","volume":"91","author":"MD Eastin","year":"2014","journal-title":"The American journal of tropical medicine and hygiene"},{"issue":"9","key":"pntd.0010071.ref021","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1289\/ehp.1509981","article-title":"Three-month real-time dengue forecast models: an early warning system for outbreak alerts and policy decision support in Singapore","volume":"124","author":"Y Shi","year":"2016","journal-title":"Environmental health perspectives"},{"issue":"7","key":"pntd.0010071.ref022","doi-asserted-by":"crossref","first-page":"e1005607","DOI":"10.1371\/journal.pcbi.1005607","article-title":"Advances in using Internet searches to track dengue","volume":"13","author":"S Yang","year":"2017","journal-title":"PLoS computational biology"},{"key":"pntd.0010071.ref023","unstructured":"For work done at the state level, see for example Kempfert, Katherine, Kaitlyn Martinez, Amir Siraj, Jessica Conrad, Geoffrey Fairchild, Amanda Ziemann, et al. \u201cTime Series Methods and Ensemble Models to Nowcast Dengue at the State Level in Brazil.\u201d arXiv preprint arXiv:2006.02483 (2020)."},{"issue":"7","key":"pntd.0010071.ref024","doi-asserted-by":"crossref","first-page":"e0005729","DOI":"10.1371\/journal.pntd.0005729","article-title":"Dengue prediction by the web: Tweets are a useful tool for estimating and forecasting Dengue at country and city level","volume":"11","author":"CD Marques-Toledo","year":"2017","journal-title":"PLoS neglected tropical diseases"},{"key":"pntd.0010071.ref025","doi-asserted-by":"crossref","first-page":"S386","DOI":"10.1016\/j.respe.2018.05.408","article-title":"Infodengue: A nowcasting system for the surveillance of arboviruses in Brazil","volume":"66","author":"C Codeco","year":"2018","journal-title":"Revue d\u2019\u00c9pid\u00e9miologie et de Sant\u00e9 Publique"},{"issue":"22","key":"pntd.0010071.ref026","doi-asserted-by":"crossref","first-page":"4363","DOI":"10.1002\/sim.8303","article-title":"A modelling approach for correcting reporting delays in disease surveillance data","volume":"38","author":"LS Bastos","year":"2019","journal-title":"Statistics in medicine"},{"issue":"6","key":"pntd.0010071.ref027","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1002\/bimj.201400159","article-title":"Bayesian outbreak detection in the presence of reporting delays","volume":"57","author":"M Salmon","year":"2015","journal-title":"Biometrical Journal"},{"issue":"5","key":"pntd.0010071.ref028","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1097\/EDE.0000000000001050","article-title":"Nowcasting the number of new symptomatic cases during infectious disease outbreaks using constrained p-spline smoothing","volume":"30","author":"J van de Kassteele","year":"2019","journal-title":"Epidemiology (Cambridge, Mass.)"},{"issue":"123","key":"pntd.0010071.ref029","doi-asserted-by":"crossref","first-page":"20160410","DOI":"10.1098\/rsif.2016.0410","article-title":"Superensemble forecasts of dengue outbreaks","volume":"13","author":"TK Yamana","year":"2016","journal-title":"Journal of The Royal Society Interface"},{"issue":"48","key":"pntd.0010071.ref030","doi-asserted-by":"crossref","first-page":"24268","DOI":"10.1073\/pnas.1909865116","article-title":"An open challenge to advance probabilistic forecasting for dengue epidemics","volume":"116","author":"MA Johansson","year":"2019","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"3","key":"pntd.0010071.ref031","doi-asserted-by":"crossref","first-page":"e1003542","DOI":"10.1371\/journal.pmed.1003542","article-title":"Probabilistic seasonal dengue forecasting in Vietnam: A modelling study using superensembles","volume":"18","author":"FJ Col\u00f3n-Gonz\u00e1lez","year":"2021","journal-title":"PLoS medicine"},{"issue":"171","key":"pntd.0010071.ref032","doi-asserted-by":"crossref","first-page":"20200691","DOI":"10.1098\/rsif.2020.0691","article-title":"Predicting dengue outbreaks at neighbourhood level using human mobility in urban areas","volume":"17","author":"R Bomfim","year":"2020","journal-title":"Journal of the Royal Society Interface"},{"issue":"14","key":"pntd.0010071.ref033","doi-asserted-by":"crossref","first-page":"5419","DOI":"10.1175\/JCLI-D-16-0758.1","article-title":"The modern-era retrospective analysis for research and applications, version 2 (MERRA-2)","volume":"30","author":"R Gelaro","year":"2017","journal-title":"Journal of climate"},{"key":"pntd.0010071.ref034","unstructured":"Brazillian Ministry of Health. Epidemiological Report on Dengue Fever: January to June 2008. http:\/\/bvsms.saude.gov.br\/bvs\/publicacoes\/informe_epidemiologico_dengue_janeiro_junho_2008.pdf (website in Portuguese)."},{"issue":"47","key":"pntd.0010071.ref035","doi-asserted-by":"crossref","first-page":"14473","DOI":"10.1073\/pnas.1515373112","article-title":"Accurate estimation of influenza epidemics using Google search data via ARGO","volume":"112","author":"S Yang","year":"2015","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"2","key":"pntd.0010071.ref036","doi-asserted-by":"crossref","first-page":"e12214","DOI":"10.2196\/12214","article-title":"Improved real-time influenza surveillance: using internet search data in eight Latin American countries","volume":"5","author":"L Clemente","year":"2019","journal-title":"JMIR public health and surveillance"},{"key":"pntd.0010071.ref037","doi-asserted-by":"crossref","unstructured":"Ho TK. Random decision forests. In Proceedings of 3rd international conference on document analysis and recognition 1995 Aug 14 (Vol. 1, pp. 278\u2013282). IEEE.","DOI":"10.1109\/ICDAR.1995.598994"},{"issue":"1","key":"pntd.0010071.ref038","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"L. Breiman","year":"2001","journal-title":"Machine learning"},{"key":"pntd.0010071.ref039","unstructured":"Lundberg SM, Lee SI. A unified approach to interpreting model predictions. In Proceedings of the 31st international conference on neural information processing systems 2017 Dec 4 (pp. 4768\u20134777)."},{"key":"pntd.0010071.ref040","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.actatropica.2018.03.006","article-title":"Time series analysis of dengue surveillance data in two Brazilian cities","volume":"182","author":"F Cortes","year":"2018","journal-title":"Acta tropica"}],"updated-by":[{"DOI":"10.1371\/journal.pntd.0010071","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T00:00:00Z","timestamp":1644278400000}}],"container-title":["PLOS Neglected Tropical Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0010071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T16:23:09Z","timestamp":1726503789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0010071"}},"subtitle":[],"editor":[{"given":"Marc","family":"Choisy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,1,24]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,1,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pntd.0010071","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.10.21.20210948","asserted-by":"object"}]},"ISSN":["1935-2735"],"issn-type":[{"value":"1935-2735","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,24]]}}}