{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T06:50:31Z","timestamp":1792306231462,"version":"4.4.0"},"reference-count":69,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2022,5,18]],"date-time":"2022-05-18T00:00:00Z","timestamp":1652832000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Dengue is a serious public health concern in Brazil and globally. In the absence of a universal vaccine or specific treatments, prevention relies on vector control and disease surveillance. Accurate and early forecasts can help reduce the spread of the disease. In this study, we developed a model for predicting monthly dengue cases in Brazilian cities 1 month ahead, using data from 2007\u20132019. We compared different machine learning algorithms and feature selection methods using epidemiologic and meteorological variables. We found that different models worked best in different cities, and a random forests model trained on monthly dengue cases performed best overall. It produced lower errors than a seasonal naive baseline model, gradient boosting regression, a feed-forward neural network, or support vector regression. For each city, we computed the mean absolute error between predictions and true monthly numbers of dengue cases on the test data set. The median error across all cities was 12.2 cases. This error was reduced to 11.9 when selecting the optimal combination of algorithm and input features for each city individually. Machine learning and especially decision tree ensemble models may contribute to dengue surveillance in Brazil, as they produce low out-of-sample prediction errors for a geographically diverse set of cities.<\/jats:p>","DOI":"10.1093\/aje\/kwac090","type":"journal-article","created":{"date-parts":[[2022,5,18]],"date-time":"2022-05-18T21:37:04Z","timestamp":1652909824000},"page":"1803-1812","source":"Crossref","is-referenced-by-count":56,"title":["Machine-Learning\u2013Based Forecasting of Dengue Fever in Brazilian Cities Using Epidemiologic and Meteorological Variables"],"prefix":"10.1093","volume":"191","author":[{"given":"Kirstin","family":"Roster","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Colm","family":"Connaughton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisco A","family":"Rodrigues","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,5,18]]},"reference":[{"issue":"528","key":"2022100608184552300_ref1","doi-asserted-by":"crossref","DOI":"10.1126\/scitranslmed.aax4144","article-title":"Mapping global variation in dengue transmission intensity","volume":"12","author":"Cattarino","year":"2020","journal-title":"Sci Transl Med."},{"issue":"8","key":"2022100608184552300_ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pntd.0001760","article-title":"Refining the global spatial limits of dengue virus transmission by evidence-based consensus","volume":"6","author":"Brady","year":"2012","journal-title":"PLoS Negl Trop Dis."},{"key":"2022100608184552300_ref3","author":"Pan American Health Organization"},{"issue":"1","key":"2022100608184552300_ref4","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1186\/s12889-019-6641-4","article-title":"30 years of fatal dengue cases in Brazil: a review","volume":"19","author":"Nunes","year":"2019","journal-title":"BMC Public Health."},{"key":"2022100608184552300_ref5","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.actatropica.2017.11.016","article-title":"Dengue endemic and its impact on the gross national product of BRAZILIAN\u2019S economy","volume":"178","author":"Montibeler","year":"2018","journal-title":"Acta Trop."},{"key":"2022100608184552300_ref6","author":"World Health Organization"},{"issue":"16","key":"2022100608184552300_ref7","doi-asserted-by":"crossref","first-page":"6242","DOI":"10.1073\/pnas.0508391103","article-title":"Global traffic and disease vector dispersal","volume":"103","author":"Tatem","year":"2006","journal-title":"Proc Natl Acad Sci U S A."},{"issue":"4","key":"2022100608184552300_ref8","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1007\/s10393-014-0941-z","article-title":"Anthropogenic land use change and infectious diseases: a review of the evidence","volume":"11","author":"Gottdenker","year":"2014","journal-title":"Ecohealth."},{"issue":"4","key":"2022100608184552300_ref9","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0005471","article-title":"Socioeconomic and environmental determinants of dengue transmission in an urban setting: an ecological study in Noum\u00e9a","volume":"11","author":"Zellweger","year":"2017","journal-title":"PLoS Negl Trop Dis."},{"key":"2022100608184552300_ref10","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.envint.2014.06.018","article-title":"Impact of meteorological factors on the spatiotemporal patterns of dengue fever incidence","volume":"73C","author":"Chien","year":"2014","journal-title":"Environ Int."},{"issue":"2","key":"2022100608184552300_ref11","doi-asserted-by":"crossref","first-page":"771","DOI":"10.4081\/gh.2019.771","article-title":"Spatiotemporal dengue fever hotspots associated with climatic factors in Taiwan including outbreak predictions based on machine-learning","volume":"14","author":"Anno","year":"2019","journal-title":"Geospat Health."},{"issue":"3","key":"2022100608184552300_ref12","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1093\/ilar\/ilx034","article-title":"The impact of global environmental changes on infectious disease emergence with a focus on risks for Brazil","volume":"58","author":"Nava","year":"2017","journal-title":"ILAR J."},{"key":"2022100608184552300_ref13","first-page":"103","volume-title":"Climate Change and Human Health: Risks and Responses","author":"Patz","year":"2003"},{"issue":"2","key":"2022100608184552300_ref14","first-page":"280","article-title":"The effect of temperature and humidity on dengue virus propagation in Aedes aegypti mosquitos","volume":"29","author":"Thu","year":"1998","journal-title":"Southeast Asian J Trop Med Public Health."},{"issue":"3","key":"2022100608184552300_ref15","first-page":"1","article-title":"Identifying the high-risk areas and associated meteorological factors of dengue transmission in Guangdong Province, China from 2005 to 2011","volume":"142","author":"Fan","year":"2013","journal-title":"Epidemiol Infect."},{"issue":"4","key":"2022100608184552300_ref16","doi-asserted-by":"crossref","first-page":"328","DOI":"10.3390\/rs9040328","article-title":"Niche modeling of dengue fever using remotely sensed environmental factors and boosted regression trees","volume":"9","author":"Ashby","year":"2017","journal-title":"Remote Sens (Basel)."},{"issue":"1","key":"2022100608184552300_ref17","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/s13662-019-1981-z","article-title":"Analysis of the fractional order dengue transmission model: a case study in Malaysia","volume":"2019","author":"Hamdan","year":"2019","journal-title":"Adv Differ Equ."},{"issue":"1","key":"2022100608184552300_ref18","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/1475-925X-2-4","article-title":"A model of dengue fever","volume":"2","author":"Derouich","year":"2003","journal-title":"Biomed Eng Online."},{"key":"2022100608184552300_ref19","first-page":"53","article-title":"Agent-based model of Aedes aegypti population","volume":"5816","author":"Isidoro","year":"2009","journal-title":"Dynamics."},{"key":"2022100608184552300_ref20","article-title":"Evaluation of Zika vector control strategies using agent-based modeling","author":"Gunaratne","year":"2016","journal-title":"arXiv."},{"key":"2022100608184552300_ref21","doi-asserted-by":"crossref","first-page":"33707","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":"Johansson","year":"2016","journal-title":"Sci Rep."},{"key":"2022100608184552300_ref22","article-title":"SARIMA forecasts of dengue incidence in Brazil, Mexico, Singapore, Sri Lanka, and Thailand: model performance and the significance of reporting delays","author":"Riley","year":"2020","journal-title":"medRxiv."},{"issue":"6","key":"2022100608184552300_ref23","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2012-001992","article-title":"A scoping review of malaria forecasting: past work and future directions","volume":"2","author":"Zinszer","year":"2012","journal-title":"BMJ Open."},{"issue":"1","key":"2022100608184552300_ref24","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/s12976-017-0074-5","article-title":"A review of influenza detection and prediction through social networking sites","volume":"15","author":"Alessa","year":"2017","journal-title":"Theor Biol Med Model."},{"key":"2022100608184552300_ref25","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1613\/jair.1.12162","article-title":"Mapping the landscape of artificial intelligence applications against COVID-19","volume":"69","author":"Bullock","year":"2020","journal-title":"J Artif Intell Res."},{"issue":"4","key":"2022100608184552300_ref26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0195065","article-title":"Dengue forecasting in S\u00e3o Paulo City with generalized additive models, artificial neural networks and seasonal autoregressive integrated moving average models","volume":"13","author":"Baquero","year":"2018","journal-title":"PLOS One."},{"key":"2022100608184552300_ref27","first-page":"1","volume-title":"2019 International Joint Conference on Neural Networks (IJCNN)","author":"Andersson","year":"2019"},{"issue":"10","key":"2022100608184552300_ref28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pntd.0005973","article-title":"Developing a dengue forecast model using machine learning: a case study in China","volume":"11","author":"Guo","year":"2017","journal-title":"PLoS Negl Trop Dis."},{"issue":"5","key":"2022100608184552300_ref29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0125049","article-title":"Morbidity rate prediction of dengue hemorrhagic fever (DHF) using the support vector machine and the Aedes aegypti infection rate in similar climates and geographical areas","volume":"10","author":"Kesorn","year":"2015","journal-title":"PLoS One."},{"issue":"2","key":"2022100608184552300_ref30","doi-asserted-by":"crossref","first-page":"453","DOI":"10.3390\/ijerph17020453","article-title":"Forecast of dengue cases in 20 Chinese cities based on the deep learning method","volume":"17","author":"Xu","year":"2020","journal-title":"Int J Environ Res Public Health."},{"key":"2022100608184552300_ref31","author":"Sistema de Informa\u00e7\u00e3o de Agravos de Notifica\u00e7\u00e3o (SINAN), Governo do Brasil"},{"key":"2022100608184552300_ref32","author":"Instituto Nacional de Meteorologia, Governo do Brasil"},{"issue":"5","key":"2022100608184552300_ref33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3409382","article-title":"Causality-based feature selection","volume":"53","author":"Yu","year":"2020","journal-title":"ACM Comput Surv."},{"issue":"9","key":"2022100608184552300_ref34","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.1093\/aje\/kwab087","article-title":"Data-driven model building for life-course epidemiology","volume":"190","author":"Petersen","year":"2021","journal-title":"Am J Epidemiol."},{"key":"2022100608184552300_ref35","first-page":"107","article-title":"Causal and non-causal feature selection for ridge regression","volume":"3","author":"Cawley","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2022100608184552300_ref36","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1201\/9781584888796.ch4","volume-title":"Computational Methods of Feature Selection","author":"Guyon","year":"2007","edition":"1st"},{"issue":"11","key":"2022100608184552300_ref37","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.aau4996","article-title":"Detecting and quantifying causal associations in large nonlinear time series datasets","volume":"5","author":"Runge","year":"2019","journal-title":"Sci Adv."},{"issue":"1","key":"2022100608184552300_ref38","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1177\/089443939100900106","article-title":"An algorithm for fast recovery of sparse causal graphs","volume":"9","author":"Spirtes","year":"1991","journal-title":"Soc Sci Comput Rev."},{"key":"2022100608184552300_ref39","doi-asserted-by":"crossref","first-page":"524","DOI":"10.3389\/fgene.2019.00524","article-title":"Review of causal discovery methods based on graphical models","volume":"10","author":"Glymour","year":"2019","journal-title":"Front Genet."},{"key":"2022100608184552300_ref40","volume-title":"Forecasting: Principles and Practice","author":"Hyndman","year":"2018","edition":"2nd"},{"issue":"1","key":"2022100608184552300_ref41","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn."},{"issue":"(5","key":"2022100608184552300_ref42","first-page":"1189","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2000","journal-title":"Ann Stat."},{"key":"2022100608184552300_ref43","first-page":"281","volume-title":"Advances in Neural Information Processing Systems 9","author":"Vapnik","year":"1997"},{"issue":"3","key":"2022100608184552300_ref44","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn."},{"issue":"3","key":"2022100608184552300_ref45","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1023\/B:STCO.0000035301.49549.88","article-title":"A tutorial on support vector regression","volume":"14","author":"Smola","year":"2004","journal-title":"Stat Comput."},{"key":"2022100608184552300_ref46","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511801389","volume-title":"An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods","author":"Cristianini","year":"2000"},{"key":"2022100608184552300_ref47","volume-title":"Neural Networks: A Comprehensive Foundation","author":"Haykin","year":"1999"},{"issue":"4","key":"2022100608184552300_ref48","doi-asserted-by":"crossref","first-page":"542","DOI":"10.3201\/eid1904.120117","article-title":"Cost-effectiveness of novel system of mosquito surveillance and control, Brazil","volume":"19","author":"Pepin","year":"2013","journal-title":"Emerg Infect Dis."},{"issue":"3","key":"2022100608184552300_ref49","first-page":"267","article-title":"Aedes aegypti e sociedade: o impacto econ\u00f4mico das arboviroses no Brasil","volume":"9","author":"Teich","year":"2017","journal-title":"J Bras Econ Sa\u00fade."},{"issue":"1","key":"2022100608184552300_ref50","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1186\/s13071-015-0659-y","article-title":"Utility of mosquito surveillance data for spatial prioritization of vector control against dengue viruses in three Brazilian cities","volume":"8","author":"Pepin","year":"2015","journal-title":"Parasit Vectors."},{"issue":"1","key":"2022100608184552300_ref51","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1093\/ije\/dyx003","article-title":"Epidemiology in the age of sustainable development","volume":"46","author":"Sachs","year":"2017","journal-title":"Int J Epidemiol."},{"issue":"1","key":"2022100608184552300_ref52","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1186\/s40249-018-0473-9","article-title":"Effective surveillance systems for vector-borne diseases in urban settings and translation of the data into action: a scoping review","volume":"7","author":"Fournet","year":"2018","journal-title":"Infect Dis Poverty."},{"issue":"22","key":"2022100608184552300_ref53","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":"Bastos","year":"2019","journal-title":"Stat Med."},{"issue":"5","key":"2022100608184552300_ref54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pntd.0009392","article-title":"Using heterogeneous data to identify signatures of dengue outbreaks at fine spatio-temporal scales across Brazil","volume":"15","author":"Castro","year":"2021","journal-title":"PLoS Negl Trop Dis."},{"key":"2022100608184552300_ref55","article-title":"Epidemia de dengue no pa\u00eds est\u00e1 concentrada em nove estados, diz Chioro","author":"Maciel"},{"issue":"4","key":"2022100608184552300_ref56","doi-asserted-by":"crossref","first-page":"e209","DOI":"10.1016\/S2542-5196(20)30292-8","article-title":"Combined effects of hydrometeorological hazards and urbanisation on dengue risk in Brazil: a spatiotemporal modelling study","volume":"5","author":"Lowe","year":"2021","journal-title":"Lancet Planet Health."},{"issue":"suppl","key":"2022100608184552300_ref57","first-page":"236","article-title":"Dengue: abastecimento de \u00e1gua no Estado de S\u00e3o Paulo","volume":"19","author":"Ribeiro","year":"2018","journal-title":"Rev Faculd Ci\u00eancias M\u00e9d Sorocaba."},{"key":"2022100608184552300_ref58","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.jcv.2016.05.012","article-title":"Clinical and laboratory profile of Zika virus infection in dengue suspected patients: a case series","volume":"81","author":"Fernanda Estofolete","year":"2016","journal-title":"J Clin Virol."},{"issue":"3","key":"2022100608184552300_ref59","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pntd.0009208","article-title":"Co-circulation and misdiagnosis led to underestimation of the 2015\u20132017 Zika epidemic in the Americas","volume":"15","author":"Oidtman","year":"2021","journal-title":"PLoS Negl Trop Dis."},{"issue":"12","key":"2022100608184552300_ref60","doi-asserted-by":"crossref","first-page":"e3201","DOI":"10.1097\/MD.0000000000003201","article-title":"Investigation into an outbreak of dengue-like illness in Pernambuco, Brazil, revealed a cocirculation of Zika, chikungunya, and dengue virus type 1","volume":"95","author":"Pess\u00f4a","year":"2016","journal-title":"Medicine."},{"issue":"3","key":"2022100608184552300_ref61","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/S1473-3099(19)30547-X","article-title":"Age-dependent manifestations and case definitions of paediatric Zika: a prospective cohort study","volume":"20","author":"Burger-Calderon","year":"2019","journal-title":"Lancet Infect Dis."},{"key":"2022100608184552300_ref62","author":"World Health Organization","year":"2016"},{"issue":"12","key":"2022100608184552300_ref63","first-page":"2222","article-title":"What is machine learning? A primer for the epidemiologist","volume":"188","author":"Bi","year":"2019","journal-title":"Am J Epidemiol."},{"key":"2022100608184552300_ref64","article-title":"Causality for machine learning","author":"Sch\u00f6lkopf","year":"2019"},{"issue":"11","key":"2022100608184552300_ref65","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pntd.0001908","article-title":"Forecast of dengue incidence using temperature and rainfall","volume":"6","author":"Hii","year":"2012","journal-title":"PLoS Negl Trop Dis."},{"issue":"0","key":"2022100608184552300_ref66","article-title":"Empirical model for estimating dengue incidence using temperature, rainfall, and relative humidity: a 19-year retrospective analysis in East Delhi","volume":"38","author":"Ramachandran","year":"2016","journal-title":"Epidemiol Health."},{"issue":"8","key":"2022100608184552300_ref67","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0220106","article-title":"Forecasting dengue fever in Brazil: an assessment of climate conditions","volume":"14","author":"Stolerman","year":"2019","journal-title":"PLoS One."},{"issue":"1","key":"2022100608184552300_ref68","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1038\/s41598-020-79438-0","article-title":"Incorporating human mobility data improves forecasts of dengue fever in Thailand","volume":"11","author":"Kiang","year":"2021","journal-title":"Sci Rep."},{"key":"2022100608184552300_ref69","author":"Roster"}],"container-title":["American Journal of Epidemiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/aje\/advance-article-pdf\/doi\/10.1093\/aje\/kwac090\/44650650\/kwac090.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/aje\/article-pdf\/191\/10\/1803\/46129839\/kwac090.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/aje\/article-pdf\/191\/10\/1803\/46129839\/kwac090.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T08:22:52Z","timestamp":1665044572000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/aje\/article\/191\/10\/1803\/6588223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,18]]},"references-count":69,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,5,18]]},"published-print":{"date-parts":[[2022,9,28]]}},"URL":"https:\/\/doi.org\/10.1093\/aje\/kwac090","relation":{},"ISSN":["0002-9262","1476-6256"],"issn-type":[{"value":"0002-9262","type":"print"},{"value":"1476-6256","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,10]]},"published":{"date-parts":[[2022,5,18]]}}}