Accurate long-range forecasting of COVID-19 mortality in the USA

Simple item page
dc.contributor.authorRamazi, Pouria
dc.contributor.authorHaratian, Arezoo
dc.contributor.authorMeghdadi, Maryam
dc.contributor.authorOriyad, Arash Mari
dc.contributor.authorLewis, Mark A.
dc.contributor.authorMaleki, Zeinab
dc.contributor.authorVega, Roberto
dc.contributor.authorWang, Hao
dc.contributor.authorWishart, David S.
dc.contributor.authorGreiner, Russell
dc.date.accessioned2025-04-15T19:22:06Z
dc.date.available2025-04-15T19:22:06Z
dc.date.issued2021
dc.description.abstractThe need for improved models that can accurately predict COVID-19 dynamics is vital to managing the pandemic and its consequences. We use machine learning techniques to design an adaptive learner that, based on epidemiological data available at any given time, produces a model that accurately forecasts the number of reported COVID-19 deaths and cases in the United States, up to 10 weeks into the future with a mean absolute percentage error of 9%. In addition to being the most accurate long-range COVID predictor so far developed, it captures the observed periodicity in daily reported numbers. Its effectiveness is based on three design features: (1) producing different model parameters to predict the number of COVID deaths (and cases) from each time and for a given number of weeks into the future, (2) systematically searching over the available covariates and their historical values to find an effective combination, and (3) training the model using "last-fold partitioning", where each proposed model is validated on only the last instance of the training dataset, rather than being cross-validated. Assessments against many other published COVID predictors show that this predictor is 19-48% more accurate.
dc.description.reviewstatusReviewed
dc.description.scholarlevelFaculty
dc.description.sponsorshipThis work was funded by Alberta Innovates and Pfizer via project number RES0052027. ML gratefully acknowledges support from NSERC and a Canada Research Chair. RV gratefully acknowledges support from Amii and CONACYT. ZM gratefully acknowledges support from Isfahan University of Technology via project number 4300/1011. HW gratefully acknowledges support from NSERC. RG gratefully acknowledges support from Amii and NSERC.This analysis has been partially funded by the Canadian Institute of Health Research Operating Grant: COVID-19 May 2020 Rapid Research Funding Opportunity.
dc.identifier.citationRamazi, P., Haratian, A., Meghdadi, M., Oriyad, A. M., Lewis, M. A., Maleki, Z., Vega, R., Wang, H., Wishart, D. S., & Greiner, R. (2021). Accurate long-range forecasting of COVID-19 mortality in the USA. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-91365-2
dc.identifier.urihttps://doi.org/10.1038/s41598-021-91365-2
dc.identifier.urihttps://hdl.handle.net/1828/21925
dc.language.isoen
dc.publisherScientific Reports
dc.rightsCC BY 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleAccurate long-range forecasting of COVID-19 mortality in the USA
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ramazi_pouria_SciRep_2021.pdf
Size:
2.39 MB
Format:
Adobe Portable Document Format
Download

Collections

Faculty Publications (BioMed Central & Faculty of Science)
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.