{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T18:07:53Z","timestamp":1780078073284,"version":"3.54.0"},"reference-count":27,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Afya"},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Timely forecasting of dengue hospitalizations is essential for public health preparedness but is frequently limited by delays in official reporting systems. While climatic variables are known to influence dengue transmission and can be obtained in near-real time, hospitalization data often become available only weeks after patient admission, reducing their value for early response. Digital information generated during clinical practice, such as physicians\u2019 search patterns, may provide a complementary and more timely signal of emerging disease activity. This study evaluates whether integrating climate data with real-time records of physicians\u2019 searches for dengue-related information improves short-term forecasts of dengue hospitalizations in Brazil under both ideal and realistic reporting conditions. Three complementary data sources were combined to generate forecasts across multiple geographic regions: weekly hospitalization counts, climatic indicators, and anonymized physician search records from a widely used clinical decision-support platform. Model performance was compared under two scenarios: one assuming immediate availability of hospitalization data and another incorporating typical reporting delays. When hospitalization data were timely, simpler model configurations \u2014 particularly those relying on hospitalization history alone or combined with climate \u2014 achieved the highest predictive accuracy, indicating that the temporal structure of the outcome itself carried substantial forecasting value. Under realistic reporting delays, however, models incorporating physicians\u2019 search behavior consistently outperformed all other approaches across most regions. In several regions, increases in physician search activity preceded or coincided with rises in hospital admissions, indicating early clinical engagement with dengue cases. These findings indicate that physician search behavior constitutes a valuable real-time indicator of dengue activity. Integrating digital clinical behavior with climate data enhances forecasting performance under real-world reporting constraints and may strengthen early-warning systems and public health decision-making for dengue and other climate-sensitive diseases.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001206","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T17:38:16Z","timestamp":1780076296000},"page":"e0001206","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dengue hospitalizations in Brazil: Forecasting with climatic and physicians\u2019 digital search data under real-world reporting delays"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4063-6658","authenticated-orcid":true,"given":"Dayanna Quintanilha","family":"Palmer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcela","family":"Motta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eduardo","family":"Moura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danielly","family":"Xavier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4493-7287","authenticated-orcid":true,"given":"Guilherme","family":"Schittine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ang\u00e9lica","family":"Caseri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0884-4190","authenticated-orcid":true,"given":"Ronaldo","family":"Gismondi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"issue":"10","key":"pdig.0001206.ref001","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1016\/j.jiph.2023.08.001","article-title":"Dengue overview: an updated systemic review","volume":"16","author":"MB Khan","year":"2023","journal-title":"J Infect Public Health"},{"issue":"3","key":"pdig.0001206.ref002","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.tim.2013.12.011","article-title":"Global spread of dengue virus types: mapping the 70 year history","volume":"22","author":"JP Messina","year":"2014","journal-title":"Trends Microbiol"},{"key":"pdig.0001206.ref003","unstructured":"Minist\u00e9rio da Sa\u00fade B. TABNET\/SINAN \u2013 Notifica\u00e7\u00f5es de Dengue no Brasil (2001\u20132025) [Internet]. 2025 [cited 2025 Oct 19]. Available from: http:\/\/tabnet.datasus.gov.br\/cgi\/tabcgi.exe?sinannet\/cnv\/denguebbr.def"},{"issue":"7","key":"pdig.0001206.ref004","article-title":"Projecting the risk of mosquito-borne diseases in a warmer and more populated world: a multi-model, multi-scenario intercomparison modelling study","volume":"5","author":"FJ Col\u00f3n-Gonz\u00e1lez","year":"2021","journal-title":"Lancet Planet Health"},{"key":"pdig.0001206.ref005","doi-asserted-by":"crossref","first-page":"104582","DOI":"10.1016\/j.ebiom.2023.104582","article-title":"Effects of high temperatures and heatwaves on dengue fever: a systematic review and meta-analysis","volume":"91","author":"YT Damtew","year":"2023","journal-title":"EBioMedicine"},{"issue":"9","key":"pdig.0001206.ref006","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":"Nat Microbiol"},{"issue":"12","key":"pdig.0001206.ref007","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0004211","article-title":"Socio-economic and climate factors associated with dengue fever spatial heterogeneity: a worked example in New Caledonia","volume":"9","author":"M Teurlai","year":"2015","journal-title":"PLoS Negl Trop Dis"},{"issue":"2","key":"pdig.0001206.ref008","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0010631","article-title":"A systematic review of dengue outbreak prediction models: Current scenario and future directions","volume":"17","author":"XY Leung","year":"2023","journal-title":"PLoS Negl Trop Dis"},{"issue":"7446","key":"pdig.0001206.ref009","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1038\/nature12060","article-title":"The global distribution and burden of dengue","volume":"496","author":"S Bhatt","year":"2013","journal-title":"Nature"},{"key":"pdig.0001206.ref010","unstructured":"Minist\u00e9rio da Sa\u00fade. Portaria SAES no 1.110, de 18 de novembro de 2021. 2021."},{"issue":"1","key":"pdig.0001206.ref011","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1186\/s12889-025-22106-7","article-title":"Forecasting dengue across Brazil with LSTM neural networks and SHAP-driven lagged climate and spatial effects","volume":"25","author":"X Chen","year":"2025","journal-title":"BMC Public Health"},{"issue":"10","key":"pdig.0001206.ref012","doi-asserted-by":"crossref","first-page":"1803","DOI":"10.1093\/aje\/kwac090","article-title":"Machine-learning\u2013based forecasting of dengue fever in Brazilian cities using epidemiologic and meteorological variables","volume":"191","author":"K Roster","year":"2022","journal-title":"Am J Epidemiol"},{"issue":"21","key":"pdig.0001206.ref013","doi-asserted-by":"crossref","first-page":"2153","DOI":"10.1056\/NEJMp0900702","article-title":"Digital disease detection--harnessing the Web for public health surveillance","volume":"360","author":"JS Brownstein","year":"2009","journal-title":"N Engl J Med"},{"issue":"1","key":"pdig.0001206.ref014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40504-017-0065-7","article-title":"Digital epidemiology: what is it, and where is it going?","volume":"14","author":"M Salath\u00e9","year":"2018","journal-title":"Life Sci Soc Policy"},{"issue":"1","key":"pdig.0001206.ref015","doi-asserted-by":"crossref","first-page":"2827","DOI":"10.1186\/s12889-025-24188-9","article-title":"Hospitalisations in Brazil: an ecological time series analysis of the impact of medical decision support data as an exogenous variable","volume":"25","author":"D Quintanilha","year":"2025","journal-title":"BMC Public Health"},{"issue":"8","key":"pdig.0001206.ref016","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"pdig.0001206.ref017","unstructured":"Instituto Brasileiro de Geografia e Estat\u00edstica. Divis\u00e3o Regional do Brasil em Regi\u00f5es Geogr\u00e1ficas Imediatas e [Internet]. [cited 2025 Oct 16]. Available from: https:\/\/www.ibge.gov.br\/apps\/regioes_geograficas\/pdfs-extra\/O%20recorte%20das%20Regi%C3%B5es%20Geogr%C3%A1ficas%20Imediatas%20e%20Intermedi%C3%A1rias%20de%202017.pdf"},{"key":"pdig.0001206.ref018","unstructured":"Minist\u00e9rio da Sa\u00fade. DATASUS \u2013 Departamento de Inform\u00e1tica do Sistema \u00danico de Sa\u00fade [Internet]. 2025 [cited 2025 Oct 19]. Available from: https:\/\/datasus.saude.gov.br\/"},{"key":"pdig.0001206.ref019","unstructured":"Conselho Federal de Medicina. Observat\u00f3rio Demografia M\u00e9dica \u2013 Painel de Demografia M\u00e9dica [Internet]. 2024 [cited 2025 Dec 2]. Available from: https:\/\/observatorio.cfm.org.br\/demografia\/dashboard\/"},{"key":"pdig.0001206.ref020","volume-title":"Dados de Acesso e Engajamento Afya Whitebook","author":"AFYA","year":"2025"},{"key":"pdig.0001206.ref021","unstructured":"Instituto Nacional de Meteorologia (INMET). BDMEP \u2014 Banco de Dados Meteorol\u00f3gicos para Ensino e Pesquisa [Internet]. 2025 [cited 2025 Mar 3]. Available from: https:\/\/bdmep.inmet.gov.br\/"},{"key":"pdig.0001206.ref022","unstructured":"Python Software Foundation. Python: A Programming Language [Internet]. 2021 [cited 2025 Jul 18]."},{"key":"pdig.0001206.ref023","unstructured":"Statsmodels Developers. statsmodels.tsa.statespace.sarimax.SARIMAX [Internet]. 2025 [cited 2025 Dec 2]. Available from: https:\/\/www.statsmodels.org\/"},{"issue":"10","key":"pdig.0001206.ref024","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.1162\/089976600300015015","article-title":"Learning to forget: continual prediction with LSTM","volume":"12","author":"FA Gers","year":"2000","journal-title":"Neural Comput"},{"issue":"7","key":"pdig.0001206.ref025","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":"CDA Marques-Toledo","year":"2017","journal-title":"PLoS Negl Trop Dis"},{"issue":"1","key":"pdig.0001206.ref026","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1038\/s41467-022-28231-w","article-title":"Fine-scale heterogeneity in population density predicts wave dynamics in dengue epidemics","volume":"13","author":"V Romeo-Aznar","year":"2022","journal-title":"Nat Commun"},{"key":"pdig.0001206.ref027","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"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T17:38:25Z","timestamp":1780076305000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001206"}},"subtitle":[],"editor":[{"given":"Charles B.","family":"Delahunt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":27,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001206","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]}}}