{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T00:18:57Z","timestamp":1794269937023,"version":"4.9.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:00:00Z","timestamp":1765497600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":38,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Infect Dis"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate prediction of trends in infectious diseases is crucial for early public health actions, which are difficult to achieve in low-resource countries such as Bangladesh, where the healthcare system is significantly challenged. Although many researchers worldwide have utilized machine learning (ML) and deep learning (DL) models for making COVID-19 predictions, limited research has focused on context-specific ensemble forecasting approaches for Bangladesh, creating a gap in local epidemic modeling. This study aims to design a Weighted Ensemble forecasting model that combines the best time series models (SARIMA, ETS), ML (XGBoost), and DL (LSTM, RNN, GRU) models to improve the accuracy of daily new COVID-19 cases in Bangladesh.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a context-specific Weighted Ensemble model integrating Seasonal Autoregressive Integrated Moving Average, XGBoost, and Recurrent Neural Network, with weights (0.1531, 0.4319, 0.4150). Log transformation handled zeros, with scaling for neural networks. Forecasts extended to May 2027.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>Out-of-sample results (SARIMA: RMSE\u2009=\u200914.56, MAE\u2009=\u20099.02, MAPE\u2009=\u2009216.87%; XGBoost: RMSE\u2009=\u20095.16, MAE\u2009=\u20093.45, MAPE\u2009=\u2009134.52%; Recurrent Neural Network: RMSE\u2009=\u20095.37, MAE\u2009=\u20092.71, MAPE\u2009=\u200941.11%; Weighted Ensemble: RMSE\u2009=\u20095.87, MAE\u2009=\u20093.49, MAPE\u2009=\u2009111.02%) show the Weighted Ensemble outperforms individual models, including the best time series, machine learning, and deep learning models, despite misspecification in traditional models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The Combination model based on Seasonal Autoregressive Integrated Moving Average, XGBoost, and Recurrent Neural Network can improve prediction performance for Bangladesh\u2019s complex COVID-19 data better than the XGBoost model does. The power of ensemble modeling in capturing linear seasonality and the nonlinear dynamics it is evident from these results. This novel integration can inform public health policy, allowing health authorities to fine-tune interventions and make more efficient use of resources while avoiding unnecessary lockdowns as COVID-19 becomes an endemic disease.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12879-025-12305-3","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T18:53:44Z","timestamp":1765565624000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Combination forecasting of COVID-19 in Bangladesh: guiding public health policy through integrated time series, ML, and DL models"],"prefix":"10.1186","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6664-5932","authenticated-orcid":false,"given":"Sharmin","family":"Akther","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5980-7149","authenticated-orcid":false,"given":"Amartay Kumar","family":"Dhar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9346-8303","authenticated-orcid":false,"given":"Jakia Sultana","family":"Pingky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,12]]},"reference":[{"key":"12305_CR1","unstructured":"Pollard CA, Morran MP, Nestor-Kalinoski AL. Downloaded from journals.Physiology.org\/journal\/physiolgenomics. 2020"},{"key":"12305_CR2","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12081295","author":"R Filip","year":"2022","unstructured":"Filip R, Puscaselu RG, Anchidin-Norocel L, Dimian M, Savage WK. Global challenges to Public health Care Systems during the COVID-19 Pandemic: a review of Pandemic measures and problems. MDPI. 2022, Aug, 01. https:\/\/doi.org\/10.3390\/jpm12081295","journal-title":"MDPI"},{"key":"12305_CR3","unstructured":"World Health Organization. WHO COVID-19 dashboard. 2025, Accessed: Jul. 15, 2025. [Online]. Available: https:\/\/data.who.int\/dashboards\/covid19\/cases?n=c"},{"key":"12305_CR4","doi-asserted-by":"publisher","unstructured":"Egeren DV, et al. Vaccines alone Cannot slow the evolution of SARS-CoV-2. Vaccines (Basel). 2023, Apr;11(4). https:\/\/doi.org\/10.3390\/vaccines11040853","DOI":"10.3390\/vaccines11040853"},{"key":"12305_CR5","doi-asserted-by":"publisher","unstructured":"Song TH, Clemente L, Pan X, Jang J, Santillana M, Lee K. Fine-grained forecasting of COVID-19 trends at the county level in the United States. NPJ Digit Med. 2025, Dec;8(1). https:\/\/doi.org\/10.1038\/s41746-025-01606-1","DOI":"10.1038\/s41746-025-01606-1"},{"key":"12305_CR6","unstructured":"WHO. WHO COVID-19 dashboard. Accessed: Jul. 2025. [Online]. Available: 15. https:\/\/data.who.int\/dashboards\/covid19\/summary"},{"key":"12305_CR7","doi-asserted-by":"publisher","unstructured":"Akter M. \u201cImpact of covid-19 on the overall sector of Bangladesh economy: an overview,\u201d Aug. 04, 2021, Cent For Res On Islamic Banking And Finance And Bus. https:\/\/doi.org\/10.46281\/bjmsr.v4i1.1421","DOI":"10.46281\/bjmsr.v4i1.1421"},{"issue":"1","key":"12305_CR8","doi-asserted-by":"publisher","first-page":"66","DOI":"10.4269\/AJTMH.20-0757","volume":"104","author":"IM Khan","year":"2021","unstructured":"Khan IM, Haque U, Kaisar S, Rahman MS. A computational modeling study of covid-19 in Bangladesh. Am J Trop Med And Hyg. 2021, Jan;104(1):66\u201374. https:\/\/doi.org\/10.4269\/AJTMH.20-0757","journal-title":"Am J Trop Med And Hyg"},{"key":"12305_CR9","unstructured":"Ministry of Health & Family Welfare of Bangladesh, \u201cCOVID Dashboard\u201d, Accessed: Jul. 15, 2025. https:\/\/dashboard.dghs.gov.bd\/pages\/covid19.php. [Online]. Available"},{"key":"12305_CR10","doi-asserted-by":"publisher","unstructured":"Tabassum T, et al. \u201cCOVID-19 in Bangladesh: wave-centric assessments and mitigation measures for future pandemics,\u201d . Elsevier Ltd. https:\/\/doi.org\/10.1016\/j.heliyon.2023.e20113. Oct. 1, 2023","DOI":"10.1016\/j.heliyon.2023.e20113"},{"key":"12305_CR11","unstructured":"Rabbi D. Bhattacharya Towfiqul Islam Khan Md Mursalin Hossain. \u201cBangladesh Macroeconomic Impact and Policy Choices\u201d"},{"key":"12305_CR12","doi-asserted-by":"publisher","unstructured":"Alkhalefah H, Preethi D, Khare N, Abidi MH, Umer U. Deep learning infused SIRVD model for COVID-19 prediction: XGBoost-SIRVD-LSTM approach. Front Med (Lausanne). 2024;11. https:\/\/doi.org\/10.3389\/fmed.2024.1427239","DOI":"10.3389\/fmed.2024.1427239"},{"issue":"1","key":"12305_CR13","doi-asserted-by":"publisher","first-page":"717","DOI":"10.54254\/2755-2721\/4\/2023404","volume":"4","author":"S Su","year":"2023","unstructured":"Su S. Machine learning for covid-19: a review on forecasting models. Appl And Comput Eng. 2023, May;4(1):717\u201323. https:\/\/doi.org\/10.54254\/2755-2721\/4\/2023404","journal-title":"Appl And Comput Eng"},{"key":"12305_CR14","doi-asserted-by":"publisher","unstructured":"Rahman MS, Chowdhury AH, Amrin M. Accuracy comparison of ARIMA and XGBoost forecasting models in predicting the incidence of COVID-19 in Bangladesh. PLoS Global Public Health. 2022, May;2(5). https:\/\/doi.org\/10.1371\/journal.pgph.0000495","DOI":"10.1371\/journal.pgph.0000495"},{"key":"12305_CR15","doi-asserted-by":"publisher","unstructured":"Kumar S, Sharma R, Tsunoda T, Kumarevel T, Sharma A. Forecasting the spread of COVID-19 using LSTM network. BMC Bioinf. 2021, Jun;22. https:\/\/doi.org\/10.1186\/s12859-021-04224-2","DOI":"10.1186\/s12859-021-04224-2"},{"key":"12305_CR16","doi-asserted-by":"publisher","unstructured":"Qaid TS, Mazaar H, Al-Shamri MYH, Alqahtani MS, Raweh AA, Alakwaa W. Hybrid deep-learning and machine-learning models for predicting COVID-19. Comput Intell Neurosci. 2021;2021. https:\/\/doi.org\/10.1155\/2021\/9996737","DOI":"10.1155\/2021\/9996737"},{"key":"12305_CR17","doi-asserted-by":"publisher","unstructured":"Zhang Y, Tang S, Yu G. An interpretable hybrid predictive model of COVID-19 cases using autoregressive model and LSTM. Sci Rep. 2023, Dec;13(1). https:\/\/doi.org\/10.1038\/s41598-023-33685-z","DOI":"10.1038\/s41598-023-33685-z"},{"key":"12305_CR18","doi-asserted-by":"publisher","unstructured":"C. Tulli S. Comparative analysis of traditional and AI-based demand forecasting models. Int J Emerging Trends in Sci Technol. 2020, Jun.6933\u201356. https:\/\/doi.org\/10.18535\/ijetst\/v7i6.02","DOI":"10.18535\/ijetst\/v7i6.02"},{"key":"12305_CR19","doi-asserted-by":"publisher","unstructured":"Cheng Y, Cheng R, Xu T, Tan X, Bai Y. \u201cMachine learning techniques applied to COVID-19 prediction: a systematic literature review,\u201d May 01, 2025, Multidiscip Digit Publishing Inst (MDPI). https:\/\/doi.org\/10.3390\/bioengineering12050514","DOI":"10.3390\/bioengineering12050514"},{"key":"12305_CR20","doi-asserted-by":"publisher","unstructured":"Shahen MA, Ahmed R. Challenges for health Care services in Bangladesh: an overview. Issue 1 Ser. I. 9:13\u201324. https:\/\/doi.org\/10.9790\/1959-0901011324","DOI":"10.9790\/1959-0901011324"},{"key":"12305_CR21","doi-asserted-by":"publisher","unstructured":"Wilson GT. Time series analysis: forecasting and control. In: Box GEP, Jenkins GM, Reinsel GC, Ljung GM, editors. J Time Ser Anal. 5th. Vol. 37(5), 709-711, 2015. 2016. Published by John Wiley and Sons Inc., Hoboken, New Jersey, pp. https:\/\/doi.org\/10.1111\/jtsa.12194 Sep. p. 712. ISBN: 978-1-118-67502-1","DOI":"10.1111\/jtsa.12194"},{"issue":"2","key":"12305_CR22","doi-asserted-by":"publisher","first-page":"28","DOI":"10.24018\/ejmath.2022.3.2.100","volume":"3","author":"TM Wanjuki","year":"2022","unstructured":"Wanjuki TM, Wagala A, Muriithi DK. Evaluating the predictive ability of seasonal autoregressive integrated moving average (SARIMA) models using food and beverages price index in Kenya. Eur J Math And Stat. 2022;3(2):28\u201338","journal-title":"Eur J Math And Stat"},{"key":"12305_CR23","doi-asserted-by":"publisher","unstructured":"Makridakis S, Spiliotis E, Assimakopoulos V. Statistical and machine learning forecasting methods: concerns and ways forward. PLoS One. 2018, Mar;13(3). https:\/\/doi.org\/10.1371\/journal.pone.0194889","DOI":"10.1371\/journal.pone.0194889"},{"key":"12305_CR24","doi-asserted-by":"publisher","unstructured":"Jofipasi CA, Miftahuddin, Hizir. Selection for the best ETS (error, trend, seasonal) model to forecast weather in the Aceh Besar District. IOP Conference Series: Materials Science and Engineering. Institute of Physics Publishing; 2018 May. https:\/\/doi.org\/10.1088\/1757-899X\/352\/1\/012055","DOI":"10.1088\/1757-899X\/352\/1\/012055"},{"key":"12305_CR25","volume-title":"Forecasting: principles and practice","author":"RJ Hyndman","year":"2018","unstructured":"Hyndman RJ, Athanasopoulos G. Forecasting: principles and practice. OTexts; 2018"},{"key":"12305_CR26","doi-asserted-by":"publisher","unstructured":"Naher S, Rabbi F, Hossain MM, Banik R, Pervez S, Boitchi AB. Forecasting the incidence of dengue in bangladesh-application of time series model. Health Sci Rep. 2022, Jul;5(4). https:\/\/doi.org\/10.1002\/hsr2.666","DOI":"10.1002\/hsr2.666"},{"key":"12305_CR27","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1873\/1\/012067","volume-title":"Journal of physics: conference series","author":"L Zhang","year":"2021","unstructured":"Zhang L, Bian W, Qu W, Tuo L, Wang Y. Time series forecast of sales volume based on XGBoost. In: Journal of Physics: conference series. IOP Publishing Ltd; 2021 Apr. https:\/\/doi.org\/10.1088\/1742-6596\/1873\/1\/012067"},{"key":"12305_CR28","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. Xgboost: a scalable tree boosting system. Proc ACM SIGKDD Int Conf On Knowl Discov And Data Min, Assoc For Comput Machinery. 2016, Aug.785\u201394. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"12305_CR29","doi-asserted-by":"publisher","unstructured":"Siami-Namini S, Tavakoli N, Namin AS. A comparison of ARIMA and LSTM in forecasting time series. Institute of Electrical and Electronics Engineers Inc; 2018 Jul, pp. 1394\u2013401. doi: https:\/\/doi.org\/10.1109\/ICMLA.2018.00227 in Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018","DOI":"10.1109\/ICMLA.2018.00227"},{"key":"12305_CR30","unstructured":"Hochreiter S, Schmidhuber JU. Long short-term memory"},{"key":"12305_CR31","unstructured":"Lipton ZC, Berkowitz J, Elkan C. A critical review of recurrent neural networks for sequence learning. Oct. 2015, [Online]. Available: http:\/\/arxiv.org\/abs\/1506.00019"},{"key":"12305_CR32","unstructured":"Schmidt RM. Recurrent neural networks (RNNs): a gentle introduction and overview. 2019, [Online]. Available: Nov. http:\/\/arxiv.org\/abs\/1912.05911"},{"key":"12305_CR33","unstructured":"Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. Dec. 2014, [Online]. Available: http:\/\/arxiv.org\/abs\/1412.3555"},{"key":"12305_CR34","unstructured":"Dey R, Salem FM. Gate-variants of gated recurrent unit (GRU) neural networks"},{"issue":"10","key":"12305_CR35","doi-asserted-by":"publisher","first-page":"7585","DOI":"10.1016\/j.aej.2022.01.011","volume":"61","author":"KE ArunKumar","year":"2022","unstructured":"ArunKumar KE, Kalaga DV, Kumar CMS, Kawaji M, Brenza TM. Comparative analysis of gated recurrent units (GRU), long short-term memory (LSTM) cells, autoregressive integrated moving average (ARIMA), seasonal autoregressive integrated moving average (SARIMA) for forecasting COVID-19 trends. Alexandria Eng J. 2022, Oct;61(10):7585\u2013603. https:\/\/doi.org\/10.1016\/j.aej.2022.01.011","journal-title":"Alexandria Eng J"},{"issue":"18","key":"12305_CR36","doi-asserted-by":"publisher","first-page":"e2103302119","DOI":"10.1073\/pnas.2103302119","volume":"119","author":"J Paireau","year":"2022","unstructured":"Paireau J, et al. An ensemble model based on early predictors to forecast COVID-19 health care demand in France. Proc Natl Acad Sci. 2022;119(18):e2103302119","journal-title":"Proc Natl Acad Sci"},{"issue":"1","key":"12305_CR37","doi-asserted-by":"publisher","first-page":"6708","DOI":"10.1038\/s41598-023-33685-z","volume":"13","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Tang S, Yu G. An interpretable hybrid predictive model of COVID-19 cases using autoregressive model and LSTM. Sci Rep. 2023;13(1):6708","journal-title":"Sci Rep"},{"issue":"1","key":"12305_CR38","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1038\/s41541-023-00773-0","volume":"8","author":"BA Williams","year":"2023","unstructured":"Williams BA, Jones CH, Welch V, True JM. Outlook of pandemic preparedness in a post-COVID-19 world. NPJ Vaccines. 2023;8(1):178","journal-title":"NPJ Vaccines"},{"issue":"5","key":"12305_CR39","doi-asserted-by":"publisher","first-page":"514","DOI":"10.3390\/bioengineering12050514","volume":"12","author":"Y Cheng","year":"2025","unstructured":"Cheng Y, Cheng R, Xu T, Tan X, Bai Y. Machine learning techniques applied to COVID-19 prediction: a systematic literature review. Bioengineering. 2025;12(5):514","journal-title":"Bioengineering"},{"key":"12305_CR40","doi-asserted-by":"crossref","unstructured":"Wise J. Covid-19: WHO declares end of global health emergency. Br Med J Publishing Group. 2023","DOI":"10.1136\/bmj.p1041"},{"issue":"10","key":"12305_CR41","doi-asserted-by":"publisher","first-page":"7917","DOI":"10.1016\/j.aej.2022.01.013","volume":"61","author":"HM Alshanbari","year":"2022","unstructured":"Alshanbari HM, Gemeay AM, El-Bagoury A-A-AH, Khosa SK, Hafez EH, Muse AH. A novel extension of Fr\u00e9chet distribution: application on real data and simulation. Alexandria Eng J. 2022;61(10):7917\u201338","journal-title":"Alexandria Eng J"},{"key":"12305_CR42","doi-asserted-by":"publisher","first-page":"105560","DOI":"10.1016\/j.compbiomed.2022.105560","volume":"146","author":"W Jin","year":"2022","unstructured":"Jin W, Dong S, Yu C, Luo Q. A data-driven hybrid ensemble AI model for COVID-19 infection forecast using multiple neural networks and reinforced learning. Comput Biol Med. 2022;146:105560","journal-title":"Comput Biol Med"},{"issue":"2","key":"12305_CR43","doi-asserted-by":"publisher","first-page":"e97","DOI":"10.1002\/puh2.97","volume":"2","author":"RM Mary","year":"2023","unstructured":"Mary RM, Alam F, Miranda AV, Lucero-Prisno DE III, Bulbul MMI. Achieving COVID-19 herd immunity in Bangladesh. Public Health Challenges. 2023;2(2):e97","journal-title":"Public Health Challenges"},{"issue":"1","key":"12305_CR44","first-page":"1556025","volume":"2022","author":"S Sah","year":"2022","unstructured":"Sah S, Surendiran B, Dhanalakshmi R, Mohanty SN, Alenezi F, Polat K. Forecasting COVID-19 pandemic using Prophet, ARIMA, and hybrid stacked LSTM-GRU models in India. Comput Math Methods Med. 2022;2022(1):1556025","journal-title":"Comput Math Methods Med"},{"issue":"7","key":"12305_CR45","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.3390\/v16071077","volume":"16","author":"SD Lytton","year":"2024","unstructured":"Lytton SD, Ghosh AK. SARS-CoV-2 variants and COVID-19 in Bangladesh-Lessons learned. Viruses. 2024;16(7):1077","journal-title":"Viruses"}],"container-title":["BMC Infectious Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12879-025-12305-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12879-025-12305-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12879-025-12305-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:28:36Z","timestamp":1781627316000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12879-025-12305-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["12305"],"URL":"https:\/\/doi.org\/10.1186\/s12879-025-12305-3","relation":{},"ISSN":["1471-2334"],"issn-type":[{"value":"1471-2334","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"19 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable, as the study used publicly available anonymized data and involved no human participants.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"The authors declare no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"80"}}