{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T22:45:39Z","timestamp":1788993939948,"version":"build-2803163510"},"reference-count":78,"publisher":"National Academy of Sciences","issue":"43","license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100005663","name":"Council of State and Territorial Epidemiologists","doi-asserted-by":"publisher","award":["NU38OT000297"],"award-info":[{"award-number":["NU38OT000297"]}],"id":[{"id":"10.13039\/100005663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000030","name":"HHS | Centers for Disease Control and Prevention","doi-asserted-by":"publisher","award":["23NU38FT000008"],"award-info":[{"award-number":["23NU38FT000008"]}],"id":[{"id":"10.13039\/100000030","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000030","name":"HHS | Centers for Disease Control and Prevention","doi-asserted-by":"publisher","award":["U01IP001136"],"award-info":[{"award-number":["U01IP001136"]}],"id":[{"id":"10.13039\/100000030","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.pnas.org"],"crossmark-restriction":true},"short-container-title":["Proc. Natl. Acad. Sci. U.S.A."],"published-print":{"date-parts":[[2025,10,28]]},"abstract":"<jats:p>Accurate forecasts of disease outbreaks are critical for effective public health responses, management of healthcare surge capacity, and communication of public risk. There are a growing number of powerful forecasting methods that fall into two broad categories-empirical models that extrapolate from historical data, and mechanistic models based on fixed epidemiological assumptions. However, these methods often underperform precisely when reliable predictions are most urgently needed-during periods of rapid epidemic escalation. Here, we introduce epimodulation, a hybrid approach that integrates fundamental epidemiological principles into existing predictive models to enhance forecasting accuracy, especially around epidemic peaks. When applied to empirical and machine learning forecasting methods (Autoregressive Integrated Moving Average, Holt-Winters, gradient-boosting machines, Prophet, and spline models), epimodulation improved overall prediction accuracy by an average of 12.3% (range: 8.5 to 18.7%) for COVID-19 hospital admissions and by 32.9% (range: 24.2 to 43.7%) for influenza hospital admissions; accuracy during epidemic peaks improved even further, by an average of 27.9% and 43.8%, respectively. Epimodulation also substantially enhanced the performance of complex forecasting methods, including the COVID-19 Forecast Hub ensemble model, demonstrating its broad utility in improving forecast reliability at critical moments in disease outbreaks.<\/jats:p>","DOI":"10.1073\/pnas.2508575122","type":"journal-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:10:56Z","timestamp":1761322256000},"update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":8,"title":["Improving outbreak forecasts through model augmentation"],"prefix":"10.1073","volume":"122","author":[{"given":"Graham C.","family":"Gibson","sequence":"first","affiliation":[{"name":"Computing and Artificial Intelligence Division","place":["Los Alamos"]},{"name":"Los Alamos National Laboratory","place":["Los Alamos"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1969-3778","authenticated-orcid":false,"given":"Spencer J.","family":"Fox","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics","place":["Athens"]},{"name":"University of Georgia","place":["Athens"]},{"name":"Institute of Bioinformatics","place":["Athens"]},{"name":"University of Georgia","place":["Athens"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6008-0271","authenticated-orcid":false,"given":"Emily","family":"Javan","sequence":"additional","affiliation":[{"name":"Integrative Biology","place":["Austin"]},{"name":"University of Texas at Austin","place":["Austin"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1206-4557","authenticated-orcid":false,"given":"Susan E.","family":"Ptak","sequence":"additional","affiliation":[{"name":"Integrative Biology","place":["Austin"]},{"name":"University of Texas at Austin","place":["Austin"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2971-4301","authenticated-orcid":false,"given":"Oluwasegun M.","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"Integrative Biology","place":["Austin"]},{"name":"University of Texas at Austin","place":["Austin"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-9717","authenticated-orcid":false,"given":"Michael","family":"Lachmann","sequence":"additional","affiliation":[{"name":"Santa Fe Institute","place":["Santa Fe"]},{"name":"Beyond Center for Fundamental Concepts in Science","place":["Tempe"]},{"name":"Arizona State University","place":["Tempe"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5828-8874","authenticated-orcid":false,"given":"Lauren Ancel","family":"Meyers","sequence":"additional","affiliation":[{"name":"Integrative Biology","place":["Austin"]},{"name":"University of Texas at Austin","place":["Austin"]},{"name":"Santa Fe Institute","place":["Santa Fe"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"341","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"key":"e_1_3_4_1_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-019-7966-8"},{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2111870119"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciab673"},{"key":"e_1_3_4_4_2","volume-title":"On the Predictability of COVID-19","author":"Reich N. G.","year":"2021","unstructured":"N. G. Reich, R. J. Tibshirani, E. L. Ray, R. Rosenfeld, On the Predictability of COVID-19 (Forecasting Blog, 2021)."},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2113561119"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2007868117"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.230634"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.2.2850.250"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1198\/016214506000001437"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008618"},{"key":"e_1_3_4_11_2","unstructured":"ReichLab COVID-HUB. https:\/\/doi.org\/10.5281\/zenodo.3963372 (Accessed July 27 2020)."},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-016-1669-x"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-36361-9"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1812594116"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-020-05743-y"},{"key":"e_1_3_4_16_2","doi-asserted-by":"crossref","unstructured":"G. Pandey P. Chaudhary R. Gupta S. Pal SEIR and regression model based COVID-19 outbreak predictions in India. arXiv [Preprint] (2020). http:\/\/arxiv.org\/abs\/2004.00958 (Accessed 3 February 2025).","DOI":"10.2196\/preprints.19406"},{"key":"e_1_3_4_17_2","doi-asserted-by":"crossref","unstructured":"G. C. Gibson N. G. Reich D. Sheldon Real-time mechanistic Bayesian forecasts of COVID-19 mortality. medRxiv [Preprint] (2020). https:\/\/doi.org\/10.1101\/2020.12.22.20248736 (Accessed 3 February 2025).","DOI":"10.1101\/2020.12.22.20248736"},{"key":"e_1_3_4_18_2","doi-asserted-by":"crossref","unstructured":"E. L. Piccolomini F. Zama Preliminary analysis of COVID-19 spread in Italy with an adaptive SEIRD model. arXiv [Preprint] (2020). http:\/\/arxiv.org\/abs\/2003.09909 (Accessed 3 February 2025).","DOI":"10.1101\/2020.04.03.20049734"},{"key":"e_1_3_4_19_2","doi-asserted-by":"crossref","unstructured":"S. Pei S. Kandula J. Shaman Differential effects of intervention timing on COVID-19 spread in the United States. medRxiv [Preprint] (2020). https:\/\/doi.org\/10.1101\/2020.05.15.20103655 (Accessed 3 February 2025).","DOI":"10.1101\/2020.05.15.20103655"},{"key":"e_1_3_4_20_2","doi-asserted-by":"crossref","unstructured":"S. Venkatramanan et al. Using data-driven agent-based models for forecasting emerging infectious diseases. Epidemics 22 43\u201349 (2018).","DOI":"10.1016\/j.epidem.2017.02.010"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0245414"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.7488"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.109864"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11538-022-01112-5"},{"key":"e_1_3_4_25_2","doi-asserted-by":"crossref","unstructured":"N. Kumar S. Susan \u201cCOVID-19 pandemic prediction using time series forecasting models\u201d in 2020 11th International Conference on Computing Communication and Networking Technologies (ICCCNT) (IEEE Kharagpur India 2020) pp. 1\u20137.","DOI":"10.1109\/ICCCNT49239.2020.9225319"},{"key":"e_1_3_4_26_2","unstructured":"N. Sesti J. J. Garau-Luis E. Crawley B. Cameron Integrating LSTMs and GNNs for COVID-19 forecasting. arXiv [Preprint] (2021). http:\/\/arxiv.org\/abs\/2108.10052 (Accessed 3 February 2025)."},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-21018-5"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2018.0174"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-36361-9"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsbl.2017.0660"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1004382"},{"key":"e_1_3_4_32_2","doi-asserted-by":"crossref","unstructured":"B. Gompertz On the nature of the function expressive of the law of human mortality and on a new mode of determining the value of life contingencies. In a letter to Francis Baily Esq. F. R. S. &c. Philos. Trans. R. Soc. Lond. 115 513\u2013583 (1825).","DOI":"10.1098\/rstl.1825.0026"},{"key":"e_1_3_4_33_2","doi-asserted-by":"crossref","unstructured":"S. Woody et al. Projections for first-wave COVID-19 deaths across the US using social-distancing measures derived from mobile phones. medRxiv [Preprint] (2020). https:\/\/doi.org\/10.1101\/2020.04.16.20068163. (Accessed 3 February 2025).","DOI":"10.1101\/2020.04.16.20068163"},{"key":"e_1_3_4_34_2","unstructured":"ReichLab Covidhubutils (2023). https:\/\/github.com\/reichlab\/covidHubUtils."},{"key":"e_1_3_4_35_2","unstructured":"Reichlab\/covid19-forecast-hub (2024). https:\/\/github.com\/reichlab\/covid19-forecast-hub."},{"key":"e_1_3_4_36_2","unstructured":"Cdcepi\/FluSight-forecast-hub (2024). https:\/\/github.com\/cdcepi\/FluSight-forecast-hub."},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.2105\/AJPH.2022.306831"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.epidem.2018.02.003"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abc2535"},{"key":"e_1_3_4_40_2","doi-asserted-by":"crossref","unstructured":"K. Nixon et al. Real-time COVID-19 forecasting: Challenges and opportunities of model performance and translation. Lancet Digit. Health 4 e699\u2013e701 (2022).","DOI":"10.1016\/S2589-7500(22)00167-4"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1011200"},{"key":"e_1_3_4_42_2","unstructured":"A. L. Bertozzi E. Franco G. Mohler M. B. Short D. Sledge The challenges of modeling and forecasting the spread of COVID-19. arXiv [Preprint] (2020). http:\/\/arxiv.org\/abs\/2004.04741 (Accessed 3 February 2025)."},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00294"},{"key":"e_1_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1175\/MWR2906.1"},{"key":"e_1_3_4_45_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-38874-y"},{"key":"e_1_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1710231115"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015874028196"},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-5347(00)01874-7"},{"key":"e_1_3_4_49_2","volume-title":"Ecological Forecasting","author":"Dietze M.","year":"2017","unstructured":"M. Dietze, Ecological Forecasting (Princeton University Press, Princeton, 2017)."},{"key":"e_1_3_4_50_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0806852106"},{"key":"e_1_3_4_51_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abc2535"},{"key":"e_1_3_4_52_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-21358-2"},{"key":"e_1_3_4_53_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.ppat.1004591"},{"key":"e_1_3_4_54_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2014564118"},{"key":"e_1_3_4_55_2","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.58989"},{"key":"e_1_3_4_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)30164-7"},{"key":"e_1_3_4_57_2","first-page":"606","article-title":"Seroprevalence of infection-induced SARS-CoV-2 antibodies - United States, September 2021\u2013February 2022","volume":"71","author":"Clarke K. E.","year":"2022","unstructured":"K. E. Clarke , Seroprevalence of infection-induced SARS-CoV-2 antibodies - United States, September 2021\u2013February 2022. MMWR 71, 606\u2013608 (2022).","journal-title":"MMWR"},{"key":"e_1_3_4_58_2","doi-asserted-by":"publisher","DOI":"10.3201\/eid3103.240594"},{"key":"e_1_3_4_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.epidem.2024.100746"},{"key":"e_1_3_4_60_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(23)00198-5"},{"key":"e_1_3_4_61_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14956"},{"key":"e_1_3_4_62_2","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1927.0118"},{"key":"e_1_3_4_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.idm.2016.12.003"},{"key":"e_1_3_4_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2020.07.002"},{"key":"e_1_3_4_65_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2021.111699"},{"key":"e_1_3_4_66_2","volume-title":"R: A Language and Environment for Statistical Computing","year":"2021","unstructured":"R Core Team, R: A Language and Environment for Statistical Computing (R Foundation for Statistical Computing, Vienna, Austria, 2021)."},{"key":"e_1_3_4_67_2","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v027.i03"},{"key":"e_1_3_4_68_2","unstructured":"S. Taylor B. Letham Prophet: Automatic Forecasting Procedure (R package version 1.0 2021)."},{"key":"e_1_3_4_69_2","unstructured":"G. Ke et al. \u201cA highly efficient gradient boosting decision tree\u201d in Advances in Neural Information Processing Systems 30 I. Guyon et al. Eds. (Curran Associates Inc. 2017) pp. 3146\u20133154."},{"key":"e_1_3_4_70_2","doi-asserted-by":"crossref","unstructured":"S. Wood Generalized Additive Models: An Introduction with R (Chapman and Hall\/CRC ed. 2 2017).","DOI":"10.1201\/9781315370279"},{"key":"e_1_3_4_71_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2112656119"},{"key":"e_1_3_4_72_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2111453118"},{"key":"e_1_3_4_73_2","unstructured":"COVID-19 Community Mobility Report (2024). https:\/\/www.google.com\/covid19\/mobility\/."},{"key":"e_1_3_4_74_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2111454118"},{"key":"e_1_3_4_75_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008618"},{"key":"e_1_3_4_76_2","unstructured":"G. C. Gibson epimodulation. Github. https:\/\/github.com\/gcgibson1989\/epimodulation. Deposited 9 September 2025."},{"key":"e_1_3_4_77_2","unstructured":"CDC Epi Flusight-forecast-data. Github. https:\/\/github.com\/cdcepi\/Flusight-forecast-data. Accessed 9 September 2025."},{"key":"e_1_3_4_78_2","unstructured":"Reich Lab covid19-forecast-hub. Github. https:\/\/github.com\/reichlab\/covid19-forecast-hub\/. Accessed 9 September 2025."}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.2508575122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:11:18Z","timestamp":1761322278000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/10.1073\/pnas.2508575122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"references-count":78,"journal-issue":{"issue":"43","published-print":{"date-parts":[[2025,10,28]]}},"alternative-id":["10.1073\/pnas.2508575122"],"URL":"https:\/\/doi.org\/10.1073\/pnas.2508575122","relation":{},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,24]]},"assertion":[{"value":"2025-04-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2508575122"}}