{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T08:08:18Z","timestamp":1791274098192,"version":"4.1.0"},"reference-count":16,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Public-health forecasting is central to epidemic intelligence and operational decision support. In practice, surveillance data are affected by reporting delays, revisions, and backfill, as well as abrupt regime shifts, which often reduce model reliability across regions and systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed EpiMap-LLM, a protocol-aware forecasting approach that links epidemic dynamics with surveillance context using a frozen language-model backbone and lightweight trainable components.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Across daily and weekly surveillance settings (JHU CSSE COVID-19 and CDC influenza hospitalization surveillance), EpiMap-LLM consistently improves MAE and RMSE over strong forecasting baselines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Protocol-aware forecasting improves robustness and practical usefulness for surveillance dashboards, early warning, and public-health decision support in heterogeneous reporting systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1829302","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T06:09:54Z","timestamp":1780034994000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Protocol-aware epidemic forecasting across heterogeneous public health surveillance systems"],"prefix":"10.3389","volume":"14","author":[{"given":"Yihan","family":"Hu","sequence":"first","affiliation":[{"name":"Medical Research Council (MRC) Epidemiology Unit, School of Clinical Medicine, Institute of Metabolic Science, University of Cambridge","place":["Cambridge, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyuan","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Cancer Prevention and Control, National Cancer Center, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Health Communication, Graduate School of Medicine, The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e370","DOI":"10.1016\/S1473-3099(22)00434-0","article-title":"The Johns Hopkins University Center for Systems Science and Engineering COVID-19 Dashboard: data collection process, challenges faced, and lessons learned","volume":"22","author":"Dong","year":"2022","journal-title":"Lancet Infect Dis"},{"key":"B2","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1101\/2021.11.04.21265886","article-title":"The United States COVID-19 Forecast Hub dataset","volume":"9","author":"Cramer","year":"2022","journal-title":"Scientific Data"},{"key":"B3","doi-asserted-by":"publisher","first-page":"3146","DOI":"10.1073\/pnas.1812594116","article-title":"A collaborative multiyear, multimodel assessment of seasonal influenza forecasting in the United States","volume":"116","author":"Reich","year":"2019","journal-title":"Proc Nat Acad Sci USA"},{"key":"B4","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1038\/s41598-018-36361-9","article-title":"Collaborative efforts to forecast seasonal influenza in the United States, 2015-2016","volume":"9","author":"McGowan","year":"2019","journal-title":"Sci Rep"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1016\/j.ijforecast.2022.06.005","article-title":"Comparing trained and untrained probabilistic ensemble forecasts of COVID-19 cases and deaths in the United States","volume":"39","author":"Ray","year":"2023","journal-title":"Int J Forecast"},{"key":"B6","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1111\/biom.12194","article-title":"Bayesian nowcasting during the STEC O104:H4 outbreak in Germany, 2011","volume":"70","author":"H\u00f6hle","year":"2014","journal-title":"Biometrics"},{"key":"B7","doi-asserted-by":"publisher","first-page":"11106","DOI":"10.1609\/aaai.v35i12.17325","article-title":"Informer: beyond efficient transformer for long sequence time-series forecasting","author":"Zhou","year":"2021","journal-title":"Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021)"},{"key":"B8","unstructured":"A time series is worth 64 words: long-term forecasting with transformers\n          \n          \n            \n              Nie\n              Y\n            \n            \n              Nguyen\n              NH\n            \n            \n              Sinthong\n              P\n            \n            \n              Kalagnanam\n              J\n            \n          \n          The Eleventh International Conference on Learning Representations (ICLR 2023)\n          \n          2023"},{"key":"B9","unstructured":"Latent ordinary differential equations for irregularly-sampled time series\n          \n          5321\n          31\n          \n            \n              Rubanova\n              Y\n            \n            \n              Chen\n              TQ\n            \n            \n              Duvenaud\n              D\n            \n          \n          Advances in Neural Information Processing Systems 32 (NeurIPS 2019)\n          \n          2019"},{"key":"B10","unstructured":"Neural Controlled Differential Equations for Irregular Time Series\n          \n          \n            \n              Kidger\n              P\n            \n            \n              Morrill\n              J\n            \n            \n              Foster\n              J\n            \n            \n              Lyons\n              TJ\n            \n          \n          Advances in Neural Information Processing Systems 33 (NeurIPS 2020)\n          \n          2020"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.52202\/075280-2042","article-title":"ContiFormer: continuous-time transformer for irregular time series modeling","volume-title":"Advances in Neural Information Processing Systems 36 (NeurIPS)","author":"Chen","year":"2023"},{"key":"B12","unstructured":"A decoder-only foundation model for time-series forecasting\n          \n          10148\n          67\n          \n            \n              Das\n              A\n            \n            \n              Kong\n              W\n            \n            \n              Sen\n              R\n            \n            \n              Zhou\n              Y\n            \n          \n          \n            \n              Salakhutdinov\n              R\n            \n            \n              Kolter\n              Z\n            \n            \n              Heller\n              K\n            \n            \n              Weller\n              A\n            \n            \n              Oliver\n              N\n            \n            \n              Scarlett\n              J\n            \n            \n              et\n              al.\n            \n          \n          PMLR\n          Proceedings of the 41st International Conference on Machine Learning. vol. 235 of Proceedings of Machine Learning Research\n          \n          2024"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.07815","article-title":"Chronos: learning the language of time series","author":"Ansari","year":"","journal-title":"CoRR. (2024). arXiv"},{"key":"B14","first-page":"22419","article-title":"Autoformer: decomposition transformers with auto-correlation for long-term series forecasting","volume-title":"Advances in Neural Information Processing Systems","author":"Wu","year":"2021"},{"key":"B15","first-page":"63574","article-title":"Irregular multivariate time series forecasting: a transformable patching graph neural networks approach","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Zhang","year":"2024"},{"key":"B16","volume-title":"Time Series Analysis: Forecasting and Control","author":"Box","year":"1970"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1829302\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T06:09:57Z","timestamp":1780034997000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1829302\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":16,"alternative-id":["10.3389\/fpubh.2026.1829302"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1829302","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]},"article-number":"1829302"}}