{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:18:51Z","timestamp":1772173131824,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1010790","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T00:00:00Z","timestamp":1688342400000}}],"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:00:00Z","timestamp":1687305600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Kayrros, Inc.","award":["2018-0143"],"award-info":[{"award-number":["2018-0143"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    The COVID-19 pandemy has created a radically new situation where most countries provide raw measurements of their daily incidence and disclose them in real time. This enables new machine learning forecast strategies where the prediction might no longer be based just on the past values of the current incidence curve, but could take advantage of observations in many countries. We present such a simple global machine learning procedure using all past daily incidence trend curves. Each of the 27,418 COVID-19 incidence trend curves in our database contains the values of 56 consecutive days extracted from observed incidence curves across 61 world regions and countries. Given a current incidence trend curve observed over the past four weeks, its forecast in the next four weeks is computed by matching it with the first four weeks of all samples, and ranking them by their similarity to the query curve. Then the 28 days forecast is obtained by a statistical estimation combining the values of the 28 last observed days in those similar samples. Using comparison performed by the European Covid-19 Forecast Hub with the current state of the art forecast methods, we verify that the proposed global learning method,\n                    <jats:italic>EpiLearn<\/jats:italic>\n                    , compares favorably to methods forecasting from a single past curve.\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1010790","type":"journal-article","created":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T18:39:02Z","timestamp":1687372742000},"page":"e1010790","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":5,"title":["Learning from the past: A short term forecast method for the COVID-19 incidence curve"],"prefix":"10.1371","volume":"19","author":[{"given":"Jean-David","family":"Morel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6108-897X","authenticated-orcid":true,"given":"Jean-Michel","family":"Morel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Alvarez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2023,6,21]]},"reference":[{"key":"pcbi.1010790.ref001","article-title":"European COVID-19 Forecast Hub","author":"K Sherratt","year":"2022","journal-title":"Zenodo"},{"issue":"10","key":"pcbi.1010790.ref002","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1093\/aje\/kwg239","article-title":"Prediction of the spread of influenza epidemics by the method of analogues","volume":"158","author":"C Viboud","year":"2003","journal-title":"American Journal of Epidemiology"},{"issue":"30","key":"pcbi.1010790.ref003","doi-asserted-by":"crossref","first-page":"4908","DOI":"10.1002\/sim.7488","article-title":"Infectious disease prediction with kernel conditional density estimation","volume":"36","author":"EL Ray","year":"2017","journal-title":"Statistics in medicine"},{"key":"pcbi.1010790.ref004","doi-asserted-by":"crossref","unstructured":"Jin X, Wang YX, Yan X. Inter-series attention model for COVID-19 forecasting. In: Proceedings of the 2021 SIAM International Conference on Data Mining (SDM). SIAM; 2021. p. 495\u2013503.","DOI":"10.1137\/1.9781611976700.56"},{"key":"pcbi.1010790.ref005","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need (2017). arXiv preprint arXiv:170603762. 2019;."},{"issue":"4","key":"pcbi.1010790.ref006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/biology11040540","article-title":"Modeling COVID-19 incidence by the renewal equation after removal of administrative bias and noise","volume":"11","author":"L Alvarez","year":"2022","journal-title":"Biology"},{"issue":"9","key":"pcbi.1010790.ref007","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1093\/aje\/kwt133","article-title":"A new framework and software to estimate time-varying reproduction numbers during epidemics","volume":"178","author":"A Cori","year":"2013","journal-title":"American journal of epidemiology"},{"issue":"50","key":"pcbi.1010790.ref008","first-page":"1","article-title":"Computing the daily reproduction number of COVID-19 by inverting the renewal equation using a variational technique","volume":"118","author":"L Alvarez","year":"2021","journal-title":"PNAS Proceedings of the National Academy of Sciences of the United States of America"},{"key":"pcbi.1010790.ref009","unstructured":"Alvarez L, Morel JD, Morel JM. EpiInvert R package. CRAN. 2022;."},{"key":"pcbi.1010790.ref010","unstructured":"Bosse N, Abbott S, Funk S. EpiNow2 (epiforecasts). London School of Hygiene and Tropical Medicine. 2022;."},{"key":"pcbi.1010790.ref011","unstructured":"Mathieu E, Ritchie H, Rod\u00e9s-Guirao L, Appel C, Giattino C, Hasell J, et al. Coronavirus Pandemic (COVID-19). Our World in Data. 2020;."},{"key":"pcbi.1010790.ref012","article-title":"Epidemiological parameters of coronavirus disease 2019: a pooled analysis of publicly reported individual data of 1155 cases from seven countries","author":"S Ma","year":"2020","journal-title":"Medrxiv"},{"issue":"1","key":"pcbi.1010790.ref013","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/1742-4682-4-20","article-title":"Time variations in the transmissibility of pandemic influenza in Prussia, Germany, from 1918\u201319","volume":"4","author":"H Nishiura","year":"2007","journal-title":"Theoretical Biology and Medical Modelling"},{"key":"pcbi.1010790.ref014","first-page":"103","volume-title":"The Effective Reproduction Number as a Prelude to Statistical Estimation of Time-Dependent Epidemic Trends","author":"H Nishiura","year":"2009"},{"issue":"4","key":"pcbi.1010790.ref015","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1080\/00224065.1986.11979014","article-title":"The exponentially weighted moving average","volume":"18","author":"JS Hunter","year":"1986","journal-title":"Journal of quality technology"},{"key":"pcbi.1010790.ref016","doi-asserted-by":"crossref","unstructured":"Srivastava A. The Variations of SIkJalpha Model for COVID-19 Forecasting and Scenario Projections. arXiv preprint arXiv:220702919. 2022;.","DOI":"10.1016\/j.epidem.2023.100729"},{"key":"pcbi.1010790.ref017","unstructured":"European Covid-19 Forecast Hub;. https:\/\/covid19forecasthub.eu\/."},{"key":"pcbi.1010790.ref018","unstructured":"The COVID-19 Forecast Hub;. https:\/\/covid19forecasthub.org."},{"key":"pcbi.1010790.ref019","unstructured":"Bosse NI, Gruson H, Cori A, van Leeuwen E, Funk S, Abbott S. Evaluating Forecasts with scoringutils in R. arXiv preprint arXiv:220507090. 2022;."},{"key":"pcbi.1010790.ref020","article-title":"Predictive performance of multi-model ensemble forecasts of COVID-19 across European nations","author":"K Sherratt","year":"2022","journal-title":"medRxiv"},{"key":"pcbi.1010790.ref021","unstructured":"Baseline model automatically generated using past truth data;. https:\/\/github.com\/reichlab\/covidModels\/blob\/master\/R-package\/R\/quantile_baseline.R."},{"key":"pcbi.1010790.ref022","article-title":"Forecasting functions for time series and linear models","volume":"6","author":"R Hyndman","year":"2015","journal-title":"R package version"},{"key":"pcbi.1010790.ref023","unstructured":"epiforecasts-weeklygrowth;. https:\/\/github.com\/seabbs\/ecdc-weekly-growth-forecasts."},{"key":"pcbi.1010790.ref024","unstructured":"MUNI-ARIMA;. https:\/\/krausstat.shinyapps.io\/covid19global\/."},{"issue":"7","key":"pcbi.1010790.ref025","doi-asserted-by":"crossref","first-page":"2929","DOI":"10.1007\/s00521-020-05434-0","article-title":"ARIMA models for predicting the end of COVID-19 pandemic and the risk of second rebound","volume":"33","author":"Z Malki","year":"2021","journal-title":"Neural Computing and Applications"},{"key":"pcbi.1010790.ref026","article-title":"Forecasting: principles and practice","author":"RJ Hyndman","year":"2018","journal-title":"OTexts"},{"key":"pcbi.1010790.ref027","article-title":"Application of ARIMA and Holt-Winters forecasting model to predict the spreading of COVID-19 for India and its states","author":"M Panda","year":"2020","journal-title":"medRxiv"},{"issue":"6500","key":"pcbi.1010790.ref028","doi-asserted-by":"crossref","first-page":"eabb9789","DOI":"10.1126\/science.abb9789","article-title":"Inferring change points in the spread of COVID-19 reveals the effectiveness of interventions","volume":"369","author":"J Dehning","year":"2020","journal-title":"Science"},{"issue":"6500","key":"pcbi.1010790.ref029","doi-asserted-by":"crossref","first-page":"eabb9789","DOI":"10.1126\/science.abb9789","article-title":"Inferring change points in the spread of COVID-19 reveals the effectiveness of interventions","volume":"369","author":"J Dehning","year":"2020","journal-title":"Science"},{"key":"pcbi.1010790.ref030","article-title":"SEIR filter: A stochastic model of epidemics","author":"M \u0160m\u00edd","year":"2021","journal-title":"medRxiv"},{"key":"pcbi.1010790.ref031","unstructured":"Rodiah I, et al. age-structured and extended SEIR model. Helmholtz Zentrum fuer Infektionsforschung, Leibniz Universitaet Hannover, Technische Universitaet Kaiserslautern. 2022;."},{"key":"pcbi.1010790.ref032","unstructured":"Srivastava A, Xu T, Prasanna VK. Fast and Accurate Forecasting of COVID-19 Deaths Using the SIkJ \u2216\u03b1 Model. arXiv preprint arXiv:200705180. 2020;."},{"issue":"1","key":"pcbi.1010790.ref033","doi-asserted-by":"crossref","first-page":"14","DOI":"10.3934\/bdia.2020002","article-title":"A data driven analysis and forecast of an SEIARD epidemic model for COVID-19 in Mexico","volume":"5","author":"UAP de Le\u00f3n","year":"2020","journal-title":"Big Data and Information Analytics"},{"issue":"2253","key":"pcbi.1010790.ref034","doi-asserted-by":"crossref","first-page":"20210027","DOI":"10.1098\/rspa.2021.0027","article-title":"SUIHTER: A new mathematical model for COVID-19. Application to the analysis of the second epidemic outbreak in Italy","volume":"477","author":"N Parolini","year":"2021","journal-title":"Proceedings of the Royal Society A"},{"key":"pcbi.1010790.ref035","unstructured":"Ardenghi G, et al. epiMOX-SUIHTER. MOX, Dipartimento di Matematica, Politecnico di Milano. 2022;."},{"issue":"2","key":"pcbi.1010790.ref036","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1093\/jxb\/10.2.290","article-title":"A flexible growth function for empirical use","volume":"10","author":"F Richards","year":"1959","journal-title":"Journal of experimental Botany"},{"issue":"16","key":"pcbi.1010790.ref037","doi-asserted-by":"crossref","first-page":"3843","DOI":"10.1002\/sim.9004","article-title":"Nowcasting COVID-19 incidence indicators during the Italian first outbreak","volume":"40","author":"P Alaimo Di Loro","year":"2021","journal-title":"Statistics in Medicine"},{"key":"pcbi.1010790.ref038","doi-asserted-by":"crossref","first-page":"100544","DOI":"10.1016\/j.spasta.2021.100544","article-title":"Spatio-temporal modelling of COVID-19 incident cases using Richards\u2019 curve: An application to the Italian regions","volume":"49","author":"M Mingione","year":"2022","journal-title":"Spatial Statistics"},{"key":"pcbi.1010790.ref039","unstructured":"Mingione M, AND PADL. Statgroup19-richards. University of Rome \u201cLa Sapienza\u201d. 2022;."},{"key":"pcbi.1010790.ref040","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pcbi.1008431","article-title":"Empirical model for short-time prediction of COVID-19 spreading","volume":"16","author":"M Catal\u00e0","year":"2020","journal-title":"PLOS Computational Biology"},{"key":"pcbi.1010790.ref041","unstructured":"Beckmann D. DirkBeckmann-Gompertz. 2022;."},{"key":"pcbi.1010790.ref042","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.idm.2020.02.002","article-title":"Real-time forecasts of the COVID-19 epidemic in China from February 5th to February 24th, 2020","volume":"5","author":"K Roosa","year":"2020","journal-title":"Infectious Disease Modelling"},{"key":"pcbi.1010790.ref043","unstructured":"RobertWalraven-ESG;. https:\/\/github.com\/seabbs\/ecdc-weekly-growth-forecasts."},{"issue":"4","key":"pcbi.1010790.ref044","doi-asserted-by":"crossref","first-page":"e0250110","DOI":"10.1371\/journal.pone.0250110","article-title":"COVID-19: Short term prediction model using daily incidence data","volume":"16","author":"H Zhao","year":"2021","journal-title":"PloS one"},{"key":"pcbi.1010790.ref045","article-title":"Comparing human and model-based forecasts of COVID-19 in Germany and Poland","author":"NI Bosse","year":"2021","journal-title":"medRxiv"},{"key":"pcbi.1010790.ref046","unstructured":"ILM-EKF;. https:\/\/github.com\/Stochastik-TU-Ilmenau."},{"issue":"32","key":"pcbi.1010790.ref047","doi-asserted-by":"crossref","first-page":"e2112656119","DOI":"10.1073\/pnas.2112656119","article-title":"Trend estimation and short-term forecasting of COVID-19 cases and deaths worldwide","volume":"119","author":"E Krymova","year":"2022","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"pcbi.1010790.ref048","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12889-021-11058-3","article-title":"Predicting the incidence of COVID-19 using data mining","volume":"21","author":"F Ahouz","year":"2021","journal-title":"BMC public health"},{"issue":"2","key":"pcbi.1010790.ref049","doi-asserted-by":"crossref","first-page":"e1005910","DOI":"10.1371\/journal.pcbi.1005910","article-title":"Prediction of infectious disease epidemics via weighted density ensembles","volume":"14","author":"EL Ray","year":"2018","journal-title":"PLoS computational biology"},{"issue":"4","key":"pcbi.1010790.ref050","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1016\/j.ijforecast.2021.03.004","article-title":"Principles and algorithms for forecasting groups of time series: Locality and globality","volume":"37","author":"P Montero-Manso","year":"2021","journal-title":"International Journal of Forecasting"},{"key":"pcbi.1010790.ref051","first-page":"99","volume-title":"Healthcare","author":"J St\u00fcbinger","year":"2020"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1010790","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T00:00:00Z","timestamp":1688342400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1010790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T08:27:58Z","timestamp":1702628878000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1010790"}},"subtitle":[],"editor":[{"given":"Virginia E.","family":"Pitzer","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,6,21]]},"references-count":51,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,6,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1010790","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.11.05.22281904","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,21]]}}}