{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T02:39:15Z","timestamp":1790131155989,"version":"4.0.1"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T00:00:00Z","timestamp":1724284800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"French State and the German Federal Ministry for Economic Affairs and Climate Action","award":["01MJ22005A"],"award-info":[{"award-number":["01MJ22005A"]}]},{"name":"French Ministry of Economy and Finance in the context of the France 2030 initiative"},{"name":"Franco-German call on Artificial Intelligence Technologies"},{"name":"German Federal Ministry for Economic Affairs and Climate Action"},{"name":"German Federal Ministry for Economic Affairs and Climate Action"},{"name":"German Federal Ministry for Economic Affairs and Climate Action"}],"content-domain":{"domain":["www.plosglobalpublichealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Glob Public Health"],"abstract":"<jats:p>During the COVID-19 pandemic, many hospitals reached their capacity limits and could no longer guarantee treatment of all patients. At the same time, governments endeavored to take sensible measures to stop the spread of the virus while at the same time trying to keep the economy afloat. Many models extrapolating confirmed cases and hospitalization rate over short periods of time have been proposed, including several ones coming from the field of machine learning. However, the highly dynamic nature of the pandemic with rapidly introduced interventions and new circulating variants imposed non-trivial challenges for the generalizability of such models. In the context of this paper, we propose the use of ensemble models, which are allowed to change in their composition or weighting of base models over time and could thus better adapt to highly dynamic pandemic or epidemic situations. In that regard, we also explored the use of secondary metadata\u2014Google searches\u2014to inform the ensemble model. We tested our approach using surveillance data from COVID-19, Influenza, and hospital syndromic surveillance of severe acute respiratory infections (SARI). In general, we found ensembles to be more robust than the individual models. Altogether we see our work as a contribution to enhance the preparedness for future pandemic situations.<\/jats:p>","DOI":"10.1371\/journal.pgph.0003058","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T14:32:41Z","timestamp":1724337161000},"page":"e0003058","update-policy":"https:\/\/doi.org\/10.1371\/journal.pgph.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["A dynamic ensemble model for short-term forecasting in pandemic situations"],"prefix":"10.1371","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6056-3144","authenticated-orcid":true,"given":"Jonas","family":"Botz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3450-0359","authenticated-orcid":true,"given":"Diego","family":"Valderrama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4911-2751","authenticated-orcid":true,"given":"Jannis","family":"Guski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5328-1243","authenticated-orcid":true,"given":"Holger","family":"Fr\u00f6hlich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"pgph.0003058.ref001","unstructured":"Coronavirus disease (COVID-19) pandemic [Internet]. [cited 2024 Jan 5]. Available from: https:\/\/www.who.int\/europe\/emergencies\/situations\/covid-19"},{"key":"pgph.0003058.ref002","unstructured":"COVID\u2014Coronavirus Statistics\u2014Worldometer [Internet]. [cited 2024 Jan 5]. Available from: https:\/\/www.worldometers.info\/coronavirus\/"},{"key":"pgph.0003058.ref003","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/j.spc.2020.10.016","article-title":"Impact of COVID-19 on the social, economic, environmental and energy domains: Lessons learnt from a global pandemic.","volume":"26","author":"M Mofijur","year":"2021","journal-title":"Sustain Prod Consum"},{"key":"pgph.0003058.ref004","article-title":"COVID-19 outbreak: Impact on global economy.","author":"S Naseer","year":"2023","journal-title":"Front Public Health [Internet]"},{"key":"pgph.0003058.ref005","doi-asserted-by":"crossref","first-page":"994949","DOI":"10.3389\/fpubh.2022.994949","article-title":"Modeling approaches for early warning and monitoring of pandemic situations as well as decision support.","volume":"10","author":"J Botz","year":"2022","journal-title":"Front Public Health"},{"issue":"11","key":"pgph.0003058.ref006","first-page":"e1007486","article-title":"Accuracy of real-time multi-model ensemble forecasts for seasonal influenza in the U.S. PLOS Comput Biol.","volume":"15","author":"NG Reich","year":"2019","journal-title":"Nov 22"},{"key":"pgph.0003058.ref007","doi-asserted-by":"crossref","first-page":"e15394","DOI":"10.2196\/15394","article-title":"Applying Machine Learning Models with An Ensemble Approach for Accurate Real-Time Influenza Forecasting in Taiwan: Development and Validation Study.","volume":"22","author":"HY Cheng","year":"2020","journal-title":"J Med Internet Res"},{"issue":"2","key":"pgph.0003058.ref008","doi-asserted-by":"crossref","first-page":"5723","DOI":"10.1007\/s11042-023-15848-2","article-title":"Ensemble learning-based early detection of influenza disease.","volume":"83","author":"R Kumar","year":"2024","journal-title":"Multimed Tools Appl."},{"key":"pgph.0003058.ref009","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.epidem.2017.08.002","article-title":"The RAPIDD ebola forecasting challenge: Synthesis and lessons learnt.","volume":"22","author":"C Viboud","year":"2018","journal-title":"Epidemics"},{"issue":"1","key":"pgph.0003058.ref010","doi-asserted-by":"crossref","first-page":"6750","DOI":"10.1038\/s41598-023-33795-8","article-title":"Forecasting COVID-19 spreading through an ensemble of classical and machine learning models: Spain\u2019s case study.","volume":"13","author":"I Heredia Cacha","year":"2023","journal-title":"Sci Rep."},{"issue":"18","key":"pgph.0003058.ref011","doi-asserted-by":"crossref","first-page":"e2103302119","DOI":"10.1073\/pnas.2103302119","article-title":"An ensemble model based on early predictors to forecast COVID-19 health care demand in France","volume":"119","author":"J Paireau","year":"2022","journal-title":"Proc Natl Acad Sci"},{"key":"pgph.0003058.ref012","first-page":"563","article-title":"Ensemble Methods.","author":"M Re","year":"2012","journal-title":"Adv Mach Learn Data Min Astron"},{"issue":"4","key":"pgph.0003058.ref013","doi-asserted-by":"crossref","first-page":"e311","DOI":"10.1016\/S2468-2667(23)00046-4","article-title":"Effectiveness assessment of non-pharmaceutical interventions: lessons learned from the COVID-19 pandemic","volume":"8","author":"A Lison","year":"2023","journal-title":"Lancet Public Health"},{"key":"pgph.0003058.ref014","doi-asserted-by":"crossref","first-page":"102649","DOI":"10.1016\/j.jag.2021.102649","article-title":"Impacts of worldwide individual non-pharmaceutical interventions on COVID-19 transmission across waves and space.","volume":"106","author":"Y Ge","year":"2022","journal-title":"Int J Appl Earth Obs Geoinformation."},{"key":"pgph.0003058.ref015","article-title":"Human behavior in the time of COVID-19: Learning from big data.","author":"H Lyu","year":"2023","journal-title":"Front Big Data [Internet]."},{"key":"pgph.0003058.ref016","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."},{"key":"pgph.0003058.ref017","doi-asserted-by":"crossref","first-page":"110874","DOI":"10.1016\/j.envres.2021.110874","article-title":"The role of seasonality in the spread of COVID-19 pandemic","volume":"195","author":"X Liu","year":"2021","journal-title":"Environ Res"},{"issue":"14","key":"pgph.0003058.ref018","doi-asserted-by":"crossref","first-page":"R918","DOI":"10.1016\/j.cub.2021.06.049","article-title":"The origins and potential future of SARS-CoV-2 variants of concern in the evolving COVID-19 pandemic","volume":"31","author":"SP Otto","year":"2021","journal-title":"Curr Biol"},{"issue":"3","key":"pgph.0003058.ref019","doi-asserted-by":"crossref","first-page":"e0178921","DOI":"10.1128\/spectrum.01789-21","article-title":"Effects of Spike Mutations in SARS-CoV-2 Variants of Concern on Human or Animal ACE2-Mediated Virus Entry and Neutralization.","volume":"10","author":"Y Kim","year":"2022","journal-title":"Microbiol Spectr."},{"key":"pgph.0003058.ref020","unstructured":"Introduction to ARIMA models [Internet]. [cited 2024 Feb 6]. Available from: https:\/\/people.duke.edu\/~rnau\/411arim.htm#arima010"},{"key":"pgph.0003058.ref021","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining [Internet]. New York, NY, USA: Association for Computing Machinery; 2016 [cited 2024 Feb 6]. p. 785\u201394. (KDD \u201816). Available from: https:\/\/dl.acm.org\/doi\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"issue":"2","key":"pgph.0003058.ref022","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s11749-016-0481-7","article-title":"A random forest guided tour.","volume":"25","author":"G Biau","year":"2016","journal-title":"TEST"},{"issue":"8","key":"pgph.0003058.ref023","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."},{"issue":"1","key":"pgph.0003058.ref024","doi-asserted-by":"crossref","first-page":"20780","DOI":"10.1038\/s41598-023-48096-3","article-title":"Development of an early alert model for pandemic situations in Germany","volume":"13","author":"D Wang","year":"2023","journal-title":"Sci Rep"},{"issue":"5","key":"pgph.0003058.ref025","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1007\/s42979-020-00298-6","article-title":"COVID-19 Pandemic: ARIMA and Regression Model-Based Worldwide Death Cases Predictions.","volume":"1","author":"V Chaurasia","year":"2020","journal-title":"SN Comput Sci."},{"issue":"1","key":"pgph.0003058.ref026","first-page":"1","article-title":"ARIMA MODEL IN PREDICTING OF COVID-19 EPIDEMIC FOR THE SOUTHERN AFRICA REGION","volume":"17","author":"S Claris","year":"2022","journal-title":"Afr J Infect Dis"},{"key":"pgph.0003058.ref027","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/j.procs.2021.01.036","article-title":"Time series analysis and forecasting of coronavirus disease in Indonesia using ARIMA model and PROPHET.","volume":"179","author":"C Satrio","year":"2021","journal-title":"Procedia Comput Sci."},{"issue":"1","key":"pgph.0003058.ref028","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1186\/s12874-022-01755-x","article-title":"Forecasting COVID-19 cases using time series modeling and association rule mining.","volume":"22","author":"R Somyanonthanakul","year":"2022","journal-title":"BMC Med Res Methodol.1"},{"key":"pgph.0003058.ref029","unstructured":"Time Series Differencing: A Complete Guide | InfluxData [Internet]. [cited 2024 Feb 27]. Available from: https:\/\/www.influxdata.com\/blog\/time-series-differencing-complete-guide-influxdb\/"},{"key":"pgph.0003058.ref030","unstructured":"pmdarima: ARIMA estimators for Python\u2014pmdarima 2.0.4 documentation [Internet]. [cited 2024 Feb 6]. Available from: http:\/\/alkaline-ml.com\/pmdarima\/"},{"issue":"1","key":"pgph.0003058.ref031","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1111\/joes.12429","article-title":"Machine learning advances for time series forecasting.","volume":"37","author":"RP Masini","year":"2023","journal-title":"J Econ Surv"},{"issue":"1","key":"pgph.0003058.ref032","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1186\/s12879-021-06503-y","article-title":"Time series analysis of hemorrhagic fever with renal syndrome in mainland China by using an XGBoost forecasting model.","volume":"21","author":"CX Lv","year":"2021","journal-title":"BMC Infect Dis."},{"key":"pgph.0003058.ref033","doi-asserted-by":"crossref","first-page":"104462","DOI":"10.1016\/j.rinp.2021.104462","article-title":"Time series prediction of COVID-19 transmission in America using LSTM and XGBoost algorithms.","volume":"27","author":"J Luo","year":"2021","journal-title":"Results Phys."},{"key":"pgph.0003058.ref034","article-title":"Original research: Application of a data-driven XGBoost model for the prediction of COVID-19 in the USA: a time-series study.","author":"Fang Z gang","year":"2022","journal-title":"BMJ Open"},{"key":"pgph.0003058.ref035","doi-asserted-by":"crossref","first-page":"111779","DOI":"10.1016\/j.chaos.2021.111779","article-title":"A random forest model for forecasting regional COVID-19 cases utilizing reproduction number estimates and demographic data","volume":"156","author":"J Galasso","year":"2022","journal-title":"Chaos Solitons Fractals"},{"issue":"4","key":"pgph.0003058.ref036","doi-asserted-by":"crossref","first-page":"e25746","DOI":"10.1016\/j.heliyon.2024.e25746","article-title":"Random forest regression for prediction of Covid-19 daily cases and deaths in Turkey.","volume":"10","author":"F. \u00d6zen","year":"2024","journal-title":"Heliyon"},{"issue":"1","key":"pgph.0003058.ref037","doi-asserted-by":"crossref","first-page":"17953","DOI":"10.1038\/s41598-023-44924-8","article-title":"A novel bidirectional LSTM deep learning approach for COVID-19 forecasting.","volume":"13","author":"NN Aung","year":"2023","journal-title":"Sci Rep"},{"issue":"1","key":"pgph.0003058.ref038","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."},{"key":"pgph.0003058.ref039","unstructured":"Mean Absolute Percentage Error (MAPE): What You Need To Know [Internet]. Arize AI. [cited 2024 Feb 15]. Available from: https:\/\/arize.com\/blog-course\/mean-absolute-percentage-error-mape-what-you-need-to-know\/"},{"issue":"2","key":"pgph.0003058.ref040","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization.","volume":"5","author":"DH Wolpert","year":"1992","journal-title":"Neural Netw."},{"key":"pgph.0003058.ref041","unstructured":"A new rank correlation coefficient with application to the consensus ranking problem\u2014Emond\u20142002\u2014Journal of Multi-Criteria Decision Analysis\u2014Wiley Online Library [Internet]. [cited 2024 Feb 29]. Available from: https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1002\/mcda.313"},{"key":"pgph.0003058.ref042","volume-title":"Mathematical Models in the Social Sciences [Internet].","author":"JG Kemeny"},{"issue":"260","key":"pgph.0003058.ref043","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1080\/01621459.1952.10483441","article-title":"Use of Ranks in One-Criterion Variance Analysis","volume":"47","author":"WH Kruskal","year":"1952","journal-title":"J Am Stat Assoc"},{"issue":"6","key":"pgph.0003058.ref044","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual Comparisons by Ranking Methods.","volume":"1","author":"F. Wilcoxon","year":"1945","journal-title":"Biom Bull."},{"issue":"2","key":"pgph.0003058.ref045","first-page":"65","article-title":"A Simple Sequentially Rejective Multiple Test Procedure.","volume":"6","author":"S. Holm","year":"1979","journal-title":"Scand J Stat."},{"issue":"1","key":"pgph.0003058.ref046","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1186\/s12913-023-09206-z","article-title":"Health system characteristics and COVID-19 performance in high-income countries.","volume":"23","author":"I Moolla","year":"2023","journal-title":"BMC Health Serv Res."}],"container-title":["PLOS Global Public Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgph.0003058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T14:33:27Z","timestamp":1724337207000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgph.0003058"}},"subtitle":[],"editor":[{"given":"Francesco","family":"Branda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,8,22]]},"references-count":46,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,8,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pgph.0003058","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.03.08.24303963","asserted-by":"object"}]},"ISSN":["2767-3375"],"issn-type":[{"value":"2767-3375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,22]]}}}