{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T20:51:50Z","timestamp":1793825510607,"version":"4.6.1"},"reference-count":42,"publisher":"National Academy of Sciences","issue":"40","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000030","name":"HHS | Centers for Disease Control and Prevention","doi-asserted-by":"publisher","award":["NU38FT000002-02-00"],"award-info":[{"award-number":["NU38FT000002-02-00"]}],"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":[[2026,10,6]]},"abstract":"<jats:p>Infectious disease forecasting in novel outbreaks or low-resource settings is hampered by the need for large disease and covariate datasets, bespoke training, and expert tuning, all of which can hinder rapid generation of forecasts for new settings. To address these challenges, we developed Mantis, a foundation model trained entirely on mechanistic simulations, which enables out-of-the-box forecasting across diseases, regions, and outcomes, even in settings with limited historical data. We evaluated Mantis against 78 forecasting models across 16 diseases with diverse transmission modes, assessing both point forecast accuracy [mean absolute error (MAE)] and probabilistic performance (weighted interval score and coverage). Despite using no real-world data during training, Mantis achieved lower MAE than all models in the CDC\u2019s COVID-19 Forecast Hub when backtested on early pandemic forecasts which it had not previously seen. Across all other diseases tested, Mantis consistently ranked in the top two models across evaluation metrics. Mantis further generalized to diseases with transmission mechanisms not represented in its training data, demonstrating that it can capture fundamental contagion dynamics rather than memorizing disease-specific patterns. These capabilities illustrate that purely simulation-based foundation models such as Mantis can provide a practical foundation for disease forecasting: general-purpose, accurate, and deployable where traditional models struggle.<\/jats:p>","DOI":"10.1073\/pnas.2602542123","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:02:56Z","timestamp":1790622176000},"update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":1,"title":["Mantis: A foundation model for mechanistic disease forecasting"],"prefix":"10.1073","volume":"123","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1336-2979","authenticated-orcid":false,"given":"Carson","family":"Dudley","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00jmfr291","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Mathematics, University of Michigan","place":["Ann Arbor"]},{"id":[{"id":"https:\/\/ror.org\/00jmfr291","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Epidemiology for School of Public Health, University of Michigan","place":["Ann Arbor"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reiden","family":"Magdaleno","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00jmfr291","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Epidemiology for School of Public Health, University of Michigan","place":["Ann Arbor"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Harding","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00jmfr291","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Epidemiology for School of Public Health, University of Michigan","place":["Ann Arbor"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ananya","family":"Sharma","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00jmfr291","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Electrical Engineering and Computer Science, University of Michigan","place":["Ann Arbor"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5771-8895","authenticated-orcid":false,"given":"Emily","family":"Martin","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00jmfr291","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Epidemiology for School of Public Health, University of Michigan","place":["Ann Arbor"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marisa","family":"Eisenberg","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00jmfr291","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Mathematics, University of Michigan","place":["Ann Arbor"]},{"id":[{"id":"https:\/\/ror.org\/00jmfr291","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Epidemiology for School of Public Health, University of Michigan","place":["Ann Arbor"]},{"id":[{"id":"https:\/\/ror.org\/00jmfr291","id-type":"ROR","asserted-by":"publisher"}],"name":"Center for the Study of Complex Systems, University of Michigan","place":["Ann Arbor"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"341","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"e_1_3_4_1_2","first-page":"57","article-title":"Role of modelling in COVID-19 policy development","volume":"35","author":"McBryde E. S.","year":"2020","unstructured":"E. S. McBryde , Role of modelling in COVID-19 policy development. Paediatr. Respir. Rev. 35, 57\u201360 (2020).","journal-title":"Paediatr. Respir. Rev."},{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2113561119"},{"key":"e_1_3_4_3_2","doi-asserted-by":"crossref","unstructured":"A. Rodriguez \u201cDeepCOVID: An operational deep learning-driven framework for explainable real-time COVID-19 forecasting\u201d in Proceedings of the AAAI Conference on Artificial Intelligence (2021) vol. 35.","DOI":"10.1609\/aaai.v35i17.17808"},{"key":"e_1_3_4_4_2","unstructured":"D. Wu DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting. arXiv [Preprint] (2021). https:\/\/doi.org\/10.48550\/arXiv.2102.06684 (Accessed 8 January 2025)."},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1378\/chest.14-0734"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2021.08.072"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006785"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.2105\/AJPH.2022.306831"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.epidem.2024.100775"},{"key":"e_1_3_4_10_2","unstructured":"T. B. Brown et al. Language models are few-shot learners. arXiv [Preprint] (2020). https:\/\/doi.org\/10.48550\/arXiv.2005.14165 (Accessed 8 January 2025)."},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_4_12_2","unstructured":"A. Radford Learning transferable visual models from natural language supervision. arXiv [Preprint] (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.00020 (Accessed 8 January 2025)."},{"key":"e_1_3_4_13_2","doi-asserted-by":"crossref","unstructured":"C. Dudley R. Magdaleno C. Harding M. Eisenberg Training neural networks on mechanistic simulations improves scientific inference. Sci. Rep. (2026). https:\/\/doi.org\/10.1038\/s41598-026-64106-6","DOI":"10.1038\/s41598-026-64106-6"},{"key":"e_1_3_4_14_2","unstructured":"University of Michigan Michigan Department of Health and Human Services and Michigan Department of Labor and Economic Opportunity MI Safe Start Map: Active Metrics. https:\/\/www.mistartmap.info\/active-metrics.html. Accessed 15 August 2025."},{"key":"e_1_3_4_15_2","unstructured":"D. C. Farrow L. C. Brooks R. J. Tibshirani R. Rosenfeld Delphi epidata API (Carnegie Mellon University Delphi Research Group 2015). https:\/\/github.com\/cmu-delphi\/delphi-epidata. Accessed 8 January 2025."},{"key":"e_1_3_4_16_2","unstructured":"CDC COVID-19 Response Weekly United States COVID-19 cases and deaths by state\u2014Archived (2025). https:\/\/data.cdc.gov\/Case-Surveillance\/Weekly-United-States-COVID-19-Cases-and-Deaths-by-\/pwn4-m3yp. Accessed 5 January 2025."},{"key":"e_1_3_4_17_2","unstructured":"W. Van Panhuis A. Cross D. Burke Counts of dengue without warning signs reported in Brazil: 1980\u20132005 (2.0) [Dataset]. Project Tycho. https:\/\/www.tycho.pitt.edu\/dataset\/BR.38362002\/. Accessed 8 January 2025."},{"key":"e_1_3_4_18_2","unstructured":"W. Van Panhuis A. Cross D. Burke Counts of viral hepatitis type B reported in United States of America: 1951\u20132007 (2.0) [Dataset]. Project Tycho. https:\/\/www.tycho.pitt.edu\/dataset\/US.66071002\/. Accessed 8 January 2025."},{"key":"e_1_3_4_19_2","unstructured":"W. Van Panhuis A. Cross D. Burke Counts of smallpox reported in United States of America: 1888\u20131952 (2.0) [Dataset]. Project Tycho. https:\/\/www.tycho.pitt.edu\/dataset\/US.67924001\/. Accessed 8 January 2025."},{"key":"e_1_3_4_20_2","unstructured":"W. Van Panhuis A. Cross D. Burke Counts of scarlet fever reported in United States of America: 1888\u20131969 (2.0) [Dataset]. Project Tycho. https:\/\/www.tycho.pitt.edu\/dataset\/US.30242009\/. Accessed 8 January 2025."},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008618"},{"key":"e_1_3_4_22_2","unstructured":"A. F. Ansari Chronos: Learning the language of time series. Trans. Mach. Learn. Res. (2024)."},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sste.2020.100372"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph20054130"},{"key":"e_1_3_4_25_2","first-page":"338","article-title":"Dengue forecasting and outbreak detection in Brazil using LSTM: Integrating human mobility and climate factors","volume":"11","author":"Chen X.","year":"2025","unstructured":"X. Chen, P. Moraga, Dengue forecasting and outbreak detection in Brazil using LSTM: Integrating human mobility and climate factors. Infect. Dis. Model. 11, 338\u2013354 (2025).","journal-title":"Infect. Dis. Model."},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.epidem.2026.100916"},{"key":"e_1_3_4_27_2","doi-asserted-by":"crossref","unstructured":"E. O. Taga M. E. Ildiz S. Oymak \u201cTimePFN: Effective multivariate time series forecasting with synthetic data\u201d in NeurIPS Workshop on Time Series in the Age of Large Models (2024).","DOI":"10.1609\/aaai.v39i19.34288"},{"key":"e_1_3_4_28_2","doi-asserted-by":"crossref","unstructured":"L. Wang J. Chen M. Marathe \u201cDEFSI: Deep learning based epidemic forecasting with synthetic information\u201d in Proceedings of the AAAI Conference on Artificial Intelligence (2019) vol. 33.","DOI":"10.1609\/aaai.v33i01.33019607"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwag058"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abb5659"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1515\/9781400841035"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002993"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2105482118"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-98302-3"},{"key":"e_1_3_4_35_2","doi-asserted-by":"crossref","first-page":"20200689","DOI":"10.1098\/rspa.2020.0689","article-title":"A scaling investigation of pattern in the spread of COVID-19: Universality in real data and a predictive analytical description","volume":"477","author":"Das S. K.","year":"2021","unstructured":"S. K. Das, A scaling investigation of pattern in the spread of COVID-19: Universality in real data and a predictive analytical description. Proc. R. Soc. A: Math. Phys. Eng. Sci. 477, 20200689 (2021).","journal-title":"Proc. R. Soc. A: Math. Phys. Eng. Sci."},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1134695"},{"key":"e_1_3_4_37_2","first-page":"153","article-title":"The geographic spread of infectious diseases: Models and applications","volume":"10","author":"Sattenspiel L.","year":"2009","unstructured":"L. Sattenspiel, The geographic spread of infectious diseases: Models and applications. Lancet Infect. Dis. 10, 153\u2013154 (2009).","journal-title":"Lancet Infect. Dis."},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-018-1184-6"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2009.0204"},{"key":"e_1_3_4_40_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2004978117"},{"key":"e_1_3_4_41_2","unstructured":"I. Loshchilov F. Hutter Decoupled weight decay regularization. Int. Conf. Learn. Represent. (2019)."},{"key":"e_1_3_4_42_2","unstructured":"C. Dudley R. Magdaleno Mantis. Github Repository. https:\/\/github.com\/carsondudley1\/Mantis. Deposited 8 May 2025."}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.2602542123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:03:51Z","timestamp":1790622231000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/10.1073\/pnas.2602542123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":42,"journal-issue":{"issue":"40","published-print":{"date-parts":[[2026,10,6]]}},"alternative-id":["10.1073\/pnas.2602542123"],"URL":"https:\/\/doi.org\/10.1073\/pnas.2602542123","relation":{},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"assertion":[{"value":"2026-01-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2602542123"}}