{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T18:06:27Z","timestamp":1790877987952,"version":"4.1.0"},"reference-count":75,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["DSAIPA\/AI\/0087\/2018"],"award-info":[{"award-number":["DSAIPA\/AI\/0087\/2018"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["2020.10157.BD"],"award-info":[{"award-number":["2020.10157.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["2024.07331.IACDC"],"award-info":[{"award-number":["2024.07331.IACDC"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["2020.10157.BD"],"award-info":[{"award-number":["2020.10157.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Disease now-casting increasingly relies on non-traditional data, such as online activity, which offer fast, inexpensive insights but are often noisy, unstructured, and influenced by behavioral confounders. Models using search engine data have frequently suffered from overfitting and unstable performance. However, pandemics may help distinguish true disease signals from behavioral noise, as both tend to surge during outbreaks. We propose a hybrid approach to improve prediction that combines model evaluation with behavioral insight. We apply simple supervised and unsupervised methods to different flu and COVID-19 datasets, using the 2009 H1N1 and 2020 COVID-19 pandemics as training periods. In both cases, selecting a curated subset of search terms improved model performance, reduced overfitting, and increased stability, consistently outperforming models that used search terms indiscriminately. These results suggest that feature curation informed by behavioral insights can enhance now-casting beyond purely statistical approaches. Our method offers a scalable and adaptable framework for integrating digital epidemiology into public health surveillance.<\/jats:p>","DOI":"10.1371\/journal.pone.0358063","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:32:41Z","timestamp":1790875961000},"page":"e0358063","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning from pandemics: Feature selection and clustering for robust digital disease nowcasting"],"prefix":"10.1371","volume":"21","author":[{"given":"Sara","family":"Mesquita","sequence":"first","affiliation":[{"name":"LIP \u2013 Laboratory for Instrumentation and Experimental Particle Physics, Avenida Prof. Gama Pinto 2","place":["Lisboa, Portugal"]},{"name":"NOVA Medical School, Universidade NOVA de Lisboa, Campo dos M\u00e1rtires da P\u00e1tria 130","place":["Lisboa, Portugal"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jo\u00e3o","family":"Loureiro","sequence":"additional","affiliation":[{"name":"LIP \u2013 Laboratory for Instrumentation and Experimental Particle Physics, Avenida Prof. Gama Pinto 2","place":["Lisboa, Portugal"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cl\u00e1udio","family":"Haupt Vieira","sequence":"additional","affiliation":[{"name":"NOVA School of Business and Economics, Universidade NOVA de Lisboa, Rua da Holanda","place":["Carcavelos, Portugal"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4844-8763","authenticated-orcid":true,"given":"L\u00edlia","family":"Perfeito","sequence":"additional","affiliation":[{"name":"LIP \u2013 Laboratory for Instrumentation and Experimental Particle Physics, Avenida Prof. Gama Pinto 2","place":["Lisboa, Portugal"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6654-2126","authenticated-orcid":true,"given":"Joana","family":"Gon\u00e7alves-S\u00e1","sequence":"additional","affiliation":[{"name":"LIP \u2013 Laboratory for Instrumentation and Experimental Particle Physics, Avenida Prof. Gama Pinto 2","place":["Lisboa, Portugal"]},{"name":"NOVA School of Business and Economics, Universidade NOVA de Lisboa, Rua da Holanda","place":["Carcavelos, Portugal"]},{"name":"NOVA LINCS, Faculdade de Ci\u00eancias e Tecnologia, Universidade NOVA de Lisboa","place":["Caparica, Portugal"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"issue":"4","key":"pone.0358063.ref001","article-title":"Big data opportunities for global infectious disease surveillance","volume":"10","author":"SI Hay","year":"2013","journal-title":"PLoS Med"},{"issue":"6491","key":"pone.0358063.ref002","doi-asserted-by":"crossref","DOI":"10.1126\/science.abb6936","article-title":"Quantifying SARS-CoV-2 transmission suggests epidemic control with digital contact tracing","volume":"368","author":"L Ferretti","year":"2020","journal-title":"Science"},{"issue":"7","key":"pone.0358063.ref003","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1002616","article-title":"Digital epidemiology","volume":"8","author":"M Salath\u00e9","year":"2012","journal-title":"PLoS Comput Biol"},{"issue":"6","key":"pone.0358063.ref004","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1038\/s43588-025-00798-6","article-title":"Advancing real-time infectious disease forecasting using large language models","volume":"5","author":"H Du","year":"2025","journal-title":"Nat Comput Sci"},{"key":"pone.0358063.ref005","unstructured":"Fox S. Online health search 2006. Pew Internet & American Life Project; 2006."},{"issue":"2","key":"pone.0358063.ref006","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0002713","article-title":"Evaluation of Internet-based dengue query data: Google Dengue Trends","volume":"8","author":"RT Gluskin","year":"2014","journal-title":"PLoS Negl Trop Dis"},{"issue":"5","key":"pone.0358063.ref007","article-title":"Using web search query data to monitor dengue epidemics: a new model for neglected tropical disease surveillance","volume":"5","author":"EH Chan","year":"2011","journal-title":"PLoS Negl Trop Dis"},{"issue":"8","key":"pone.0358063.ref008","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0001258","article-title":"Prediction of dengue incidence using search query surveillance","volume":"5","author":"BM Althouse","year":"2011","journal-title":"PLoS Negl Trop Dis"},{"issue":"1","key":"pone.0358063.ref009","doi-asserted-by":"crossref","first-page":"1552652","DOI":"10.1080\/16549716.2018.1552652","article-title":"Correlation between Google Trends on dengue fever and national surveillance report in Indonesia","volume":"12","author":"A Husnayain","year":"2019","journal-title":"Glob Health Action"},{"issue":"1","key":"pone.0358063.ref010","doi-asserted-by":"crossref","first-page":"10434","DOI":"10.1038\/s41598-019-46898-y","article-title":"Avian Influenza A (H7N9) and related Internet search query data in China","volume":"9","author":"Y Chen","year":"2019","journal-title":"Scientific reports"},{"issue":"1","key":"pone.0358063.ref011","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0165085","article-title":"Dynamic Forecasting of Zika Epidemics Using Google Trends","volume":"12","author":"Y Teng","year":"2017","journal-title":"PLoS One"},{"key":"pone.0358063.ref012","unstructured":"Google Flu Trends. Google Flu Trends [Internet]. Google.org; 2013 [cited 2020 Dec 22]. Available from: https:\/\/web.archive.org\/web\/20121022154915\/http:\/\/www.google.org\/flutrends\/about\/how.html"},{"issue":"7232","key":"pone.0358063.ref013","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1038\/nature07634","article-title":"Detecting influenza epidemics using search engine query data","volume":"457","author":"J Ginsberg","year":"2009","journal-title":"Nature"},{"issue":"2","key":"pone.0358063.ref014","article-title":"Early and Real-Time Detection of Seasonal Influenza Onset","volume":"13","author":"M Won","year":"2017","journal-title":"PLoS Comput Biol"},{"issue":"8","key":"pone.0358063.ref015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0256858","article-title":"A general method for estimating the prevalence of influenza-like-symptoms with Wikipedia data","volume":"16","author":"G De Toni","year":"2021","journal-title":"PLoS One"},{"issue":"6","key":"pone.0358063.ref016","doi-asserted-by":"crossref","first-page":"3681","DOI":"10.3390\/ijerph19063681","article-title":"Real-Time Detection of Flu Season Onset: A Novel Approach to Flu Surveillance","volume":"19","author":"J Liu","year":"2022","journal-title":"Int J Environ Res Public Health"},{"issue":"8","key":"pone.0358063.ref017","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1011392","article-title":"Neural network models for influenza forecasting with associated uncertainty using Web search activity trends","volume":"19","author":"M Morris","year":"2023","journal-title":"PLoS Comput Biol"},{"issue":"8","key":"pone.0358063.ref018","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0305579","article-title":"Incorporating connectivity among Internet search data for enhanced influenza-like illness tracking","volume":"19","author":"S Ning","year":"2024","journal-title":"PLoS One"},{"key":"pone.0358063.ref019","doi-asserted-by":"crossref","unstructured":"A JB, Beryl Princess PJ. LLM-Assisted Keyword Curation for Early Disease Outbreak Detection Using Search Trends. In: 2025 4th International Conference on Applied Artificial Intelligence and Computing (ICAAIC), 2025. 478\u201383. https:\/\/doi.org\/10.1109\/icaaic64647.2025.11330303","DOI":"10.1109\/ICAAIC64647.2025.11330303"},{"issue":"6176","key":"pone.0358063.ref020","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1126\/science.1248506","article-title":"Big data. The parable of Google Flu: traps in big data analysis","volume":"343","author":"D Lazer","year":"2014","journal-title":"Science"},{"issue":"6","key":"pone.0358063.ref021","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0129179","article-title":"Mass Media and the Contagion of Fear: The Case of Ebola in America","volume":"10","author":"S Towers","year":"2015","journal-title":"PLoS One"},{"issue":"10","key":"pone.0358063.ref022","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1003256","article-title":"Reassessing Google Flu Trends data for detection of seasonal and pandemic influenza: a comparative epidemiological study at three geographic scales","volume":"9","author":"DR Olson","year":"2013","journal-title":"PLoS Comput Biol"},{"issue":"3","key":"pone.0358063.ref023","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1007633","article-title":"The impact of news exposure on collective attention in the United States during the 2016 Zika epidemic","volume":"16","author":"M Tizzoni","year":"2020","journal-title":"PLoS Comput Biol"},{"issue":"47","key":"pone.0358063.ref024","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":"Proc Natl Acad Sci U S A"},{"key":"pone.0358063.ref025","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.16777","article-title":"Origins of the 2009 H1N1 influenza pandemic in swine in Mexico","volume":"5","author":"I Mena","year":"2016","journal-title":"Elife"},{"key":"pone.0358063.ref026","article-title":"Surveillance for influenza during the 2009 influenza A (H1N1) pandemic\u2013United States, April 2009\u2013March 2010","author":"L Brammer","year":"2011","journal-title":"Clinic Infect Dis"},{"issue":"49","key":"pone.0358063.ref027","doi-asserted-by":"crossref","first-page":"19740","DOI":"10.2807\/ese.15.49.19740-en","article-title":"Initial surveillance of 2009 influenza A(H1N1) pandemic in the European Union and European Economic Area, April-September 2009","volume":"15","author":"I Devaux","year":"2010","journal-title":"Euro Surveill"},{"issue":"10","key":"pone.0358063.ref028","article-title":"Seasonality in risk of pandemic influenza emergence","volume":"13","author":"SJ Fox","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"pone.0358063.ref029","volume-title":"Pandemic (H1N1) 2009 \u2013 update 112","author":"World Health Organization","year":"2010"},{"issue":"9","key":"pone.0358063.ref030","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1016\/S1473-3099(12)70121-4","article-title":"Estimated global mortality associated with the first 12 months of 2009 pandemic influenza A H1N1 virus circulation: a modelling study","volume":"12","author":"FS Dawood","year":"2012","journal-title":"Lancet Infect Dis"},{"key":"pone.0358063.ref031","volume-title":"WHO COVID-19 Dashboard: Deaths [Internet","author":"World Health Organization","year":"2025"},{"issue":"36","key":"pone.0358063.ref032","doi-asserted-by":"crossref","first-page":"19329","DOI":"10.2807\/ese.14.36.19329-en","article-title":"Detection of influenza A (H1N1) v virus by real-time RT-PCR","volume":"14","author":"M Panning","year":"2009","journal-title":"Eurosurveillance"},{"key":"pone.0358063.ref033","doi-asserted-by":"crossref","unstructured":"Teymouri M, Mollazadeh S, Mortazavi H, Ghale-Noie ZN, Keyvani V, Aghababaei F, et al. Recent advances and challenges of RT-PCR tests for the diagnosis of COVID-19. Pathology-Research and Practice. 2021.","DOI":"10.1016\/j.prp.2021.153443"},{"key":"pone.0358063.ref034","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/978-3-031-62772-9_9","article-title":"Coronavirus Variant Emergence and Epidemiology","volume-title":"The COVID-19 Pandemic","author":"JM Rosen","year":"2024"},{"issue":"9","key":"pone.0358063.ref035","doi-asserted-by":"crossref","first-page":"2841","DOI":"10.1007\/s00216-021-03806-6","article-title":"Antigenic characterization of influenza and SARS-CoV-2 viruses","volume":"414","author":"Y Wang","year":"2022","journal-title":"Anal Bioanal Chem"},{"key":"pone.0358063.ref036","volume-title":"Pandemic influenza vaccine manufacturing process and timeline [Internet","author":"World Health Organization","year":"2009"},{"issue":"5","key":"pone.0358063.ref037","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1016\/j.vaccine.2023.12.031","article-title":"How manufacturing won or lost the COVID-19 vaccine race","volume":"42","author":"ML King","year":"2024","journal-title":"Vaccine"},{"issue":"12","key":"pone.0358063.ref038","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1016\/j.jiph.2020.09.023","article-title":"Comparative epidemiology between the 2009 H1N1 influenza and COVID-19 pandemics","volume":"13","author":"VG da Costa","year":"2020","journal-title":"J Infect Public Health"},{"issue":"5","key":"pone.0358063.ref039","doi-asserted-by":"crossref","first-page":"920","DOI":"10.1080\/09638237.2022.2091754","article-title":"A systematic review of fear, stigma, and mental health outcomes of pandemics","volume":"32","author":"A Wasim","year":"2023","journal-title":"J Ment Health"},{"issue":"5","key":"pone.0358063.ref040","doi-asserted-by":"crossref","first-page":"619","DOI":"10.21149\/12367","article-title":"Comparison between Covid-19 and influenza A(H1N1) pandemic experiences and risk perception in Mexican university","volume":"63","author":"I Pel\u00e1ez-Ballestas","year":"2021","journal-title":"Salud Publica Mex"},{"issue":"10","key":"pone.0358063.ref041","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.abd6989","article-title":"An early warning approach to monitor COVID-19 activity with multiple digital traces in near real time","volume":"7","author":"NE Kogan","year":"2021","journal-title":"Sci Adv"},{"key":"pone.0358063.ref042","unstructured":"Dewhurst DR, Alshaabi T, Arnold MV, Minot JR, Danforth CM, Dodds PS. Divergent modes of online collective attention to the COVID-19 pandemic are associated with future caseload variance. arXiv preprint arXiv:200403516. 2020."},{"key":"pone.0358063.ref043","unstructured":"Liu D, Clemente L, Poirier C, Ding X, Chinazzi M, Davis JT, et al. A machine learning methodology for real-time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches, news alerts, and estimates from mechanistic models. arXiv preprint arXiv:200404019. 2020."},{"issue":"2","key":"pone.0358063.ref044","doi-asserted-by":"crossref","DOI":"10.2196\/18828","article-title":"Predicting COVID-19 Incidence Through Analysis of Google Trends Data in Iran: Data Mining and Deep Learning Pilot Study","volume":"6","author":"SM Ayyoubzadeh","year":"2020","journal-title":"JMIR Public Health Surveill"},{"issue":"1","key":"pone.0358063.ref045","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1038\/s41746-021-00396-6","article-title":"Internet search patterns reveal clinical course of COVID-19 disease progression and pandemic spread across 32 countries","volume":"4","author":"T Lu","year":"2021","journal-title":"NPJ Digit Med"},{"key":"pone.0358063.ref046","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.ijid.2020.04.033","article-title":"Association of the COVID-19 pandemic with Internet Search Volumes: A Google TrendsTM Analysis","volume":"95","author":"M Effenberger","year":"2020","journal-title":"Int J Infect Dis"},{"issue":"12","key":"pone.0358063.ref047","doi-asserted-by":"crossref","first-page":"1406","DOI":"10.1080\/10810730.2015.1018634","article-title":"Understanding Health Information Seeking: A Test of the Risk Perception Attitude Framework","volume":"20","author":"KL Grasso","year":"2015","journal-title":"J Health Commun"},{"issue":"7","key":"pone.0358063.ref048","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1038\/s44360-026-00117-x","article-title":"Public use of a generalist LLM chatbot for health queries","volume":"1","author":"B Costa-Gomes","year":"2026","journal-title":"Nat Health"},{"issue":"8","key":"pone.0358063.ref049","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.2105\/AJPH.2009.180521","article-title":"Health information-seeking behaviors, health indicators, and health risks","volume":"100","author":"3rd Weaver JB","year":"2010","journal-title":"Am J Public Health"},{"issue":"5","key":"pone.0358063.ref050","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1093\/eurpub\/ckw022","article-title":"Association of searching for health-related information online with self-rated health in the European Union","volume":"26","author":"T Hone","year":"2016","journal-title":"Eur J Public Health"},{"issue":"12","key":"pone.0358063.ref051","doi-asserted-by":"crossref","DOI":"10.2196\/25963","article-title":"Explaining Online Information Seeking Behaviors in People With Different Health Statuses: German Representative Cross-sectional Survey","volume":"23","author":"E Link","year":"2021","journal-title":"J Med Internet Res"},{"issue":"1","key":"pone.0358063.ref052","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1177\/1077699020961518","article-title":"Online Information Seeking and Disease Prevention Intent During COVID-19 Outbreak","volume":"99","author":"J Li","year":"2020","journal-title":"Journalism & Mass Communication Quarterly"},{"issue":"6","key":"pone.0358063.ref053","doi-asserted-by":"crossref","first-page":"996","DOI":"10.3390\/math13060996","article-title":"Mathematical Methods in Feature Selection: A Review","volume":"13","author":"F Kamalov","year":"2025","journal-title":"Mathematics"},{"issue":"3","key":"pone.0358063.ref054","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1007\/s10115-017-1059-8","article-title":"Recent advances in feature selection and its applications","volume":"53","author":"Y Li","year":"2017","journal-title":"Knowl Inf Syst"},{"key":"pone.0358063.ref055","unstructured":"FluNet. Accessed: 2026-08-18. https:\/\/www.who.int\/tools\/flunet"},{"key":"pone.0358063.ref056","unstructured":"Our World in data;. Accessed: 2020-08-20. https:\/\/github.com\/owid\/covid-19-data\/tree\/master\/public\/data"},{"key":"pone.0358063.ref057","unstructured":"Google Trends. Google Trends; 2025. Accessed: 2025-02-10. Available from: https:\/\/trends.google.com\/trends\/"},{"key":"pone.0358063.ref058","article-title":"Vanderbilt TV News Abstracts. Harvard Dataverse;","author":"G Sood","year":"2020","journal-title":"Available from"},{"key":"pone.0358063.ref059","unstructured":"Cloud M. Media Cloud: Global News Database; 2023. Accessed: 2023-05-15. https:\/\/search.mediacloud.org\/search"},{"key":"pone.0358063.ref060","unstructured":"SciPy Community. SciPy: Scientific Computing Tools for Python; 2023. Accessed: 2025-02-09. Available from: https:\/\/scipy.org"},{"key":"pone.0358063.ref061","unstructured":"LinearRegression. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.linear_model.LinearRegression.html"},{"key":"pone.0358063.ref062","unstructured":"RandomForestRegressor. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.ensemble.RandomForestRegressor.html"},{"key":"pone.0358063.ref063","unstructured":"Raschka S. Mlxtend: A library of Python tools and extensions for data science; 2023. Version retrieved: 2023-05-15. Available from: https:\/\/pypi.org\/project\/mlxtend\/"},{"key":"pone.0358063.ref064","doi-asserted-by":"crossref","unstructured":"Ma KC. Genomic surveillance for SARS-CoV-2 variants: circulation of omicron lineages\u2014United States, January 2022\u2013May 2023. MMWR Morbidity and mortality weekly report. 2023;72.","DOI":"10.15585\/mmwr.mm7224a2"},{"issue":"1","key":"pone.0358063.ref065","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing","volume":"57","author":"Y Benjamini","year":"1995","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"key":"pone.0358063.ref066","doi-asserted-by":"crossref","unstructured":"Breiman L, Friedman J, Olshen RA, Stone CJ. Classification and regression trees. Chapman and Hall\/CRC; 2017.","DOI":"10.1201\/9781315139470"},{"issue":"9","key":"pone.0358063.ref067","doi-asserted-by":"crossref","first-page":"1620","DOI":"10.1111\/2041-210X.13650","article-title":"Predicting into unknown space? Estimating the area of applicability of spatial prediction models","volume":"12","author":"H Meyer","year":"2021","journal-title":"Methods Ecol Evol"},{"key":"pone.0358063.ref068","doi-asserted-by":"crossref","DOI":"10.7717\/peerj.5518","article-title":"Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables","volume":"6","author":"T Hengl","year":"2018","journal-title":"PeerJ"},{"issue":"1","key":"pone.0358063.ref069","doi-asserted-by":"crossref","first-page":"3886","DOI":"10.1038\/s41598-023-31057-1","article-title":"Seasonal trends in COVID-19 cases, hospitalizations, and mortality in the United States and Europe","volume":"13","author":"TL Wiemken","year":"2023","journal-title":"Sci Rep"},{"issue":"2","key":"pone.0358063.ref070","doi-asserted-by":"crossref","first-page":"334","DOI":"10.3390\/jcm13020334","article-title":"Influence of Seasonality and Public-Health Interventions on the COVID-19 Pandemic in Northern Europe","volume":"13","author":"GA Quinn","year":"2024","journal-title":"J Clin Med"},{"issue":"7","key":"pone.0358063.ref071","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1016\/j.jval.2019.02.012","article-title":"Machine Learning for Health Services Researchers","volume":"22","author":"P Doupe","year":"2019","journal-title":"Value Health"},{"issue":"9","key":"pone.0358063.ref072","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1038\/nmeth.3968","article-title":"Points of significance: model selection and overfitting","volume":"13","author":"J Lever","year":"2016","journal-title":"Nature methods"},{"key":"pone.0358063.ref073","doi-asserted-by":"crossref","first-page":"117290","DOI":"10.1016\/j.chaos.2025.117290","article-title":"Forecasting dengue cases through time-series modeling with Google Trends and deep neural networks","volume":"201","author":"KH Cheong","year":"2025","journal-title":"Chaos, Solitons & Fractals"},{"issue":"1","key":"pone.0358063.ref074","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000670","article-title":"Epidemiological methods in transition: Minimizing biases in classical and digital approaches","volume":"4","author":"S Mesquita","year":"2025","journal-title":"PLOS Digit Health"},{"key":"pone.0358063.ref075","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.annepidem.2025.07.024","article-title":"Machine learning in epidemiology: An introduction, comparison with traditional methods, and a case study of predicting extreme longevity","volume":"110","author":"D Atias","year":"2025","journal-title":"Ann Epidemiol"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:32:56Z","timestamp":1790875976000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358063"}},"subtitle":[],"editor":[{"given":"Kyungwon","family":"Kim","sequence":"first","affiliation":[{"name":"Incheon National University","place":["KOREA, REPUBLIC OF"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":75,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0358063","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]}}}