Incorporating variant frequencies data into short-term forecasting for COVID-19 cases and deaths in the USA: a deep learning approach

Hongru Du; Ensheng Dong; Hamada S Badr; Mary E Petrone; Nathan D Grubaugh; Lauren M Gardner

doi:10.1016/j.ebiom.2023.104482

Incorporating variant frequencies data into short-term forecasting for COVID-19 cases and deaths in the USA: a deep learning approach

EBioMedicine. 2023 Mar:89:104482. doi: 10.1016/j.ebiom.2023.104482. Epub 2023 Feb 21.

Authors

Hongru Du¹, Ensheng Dong¹, Hamada S Badr², Mary E Petrone³, Nathan D Grubaugh⁴, Lauren M Gardner⁵

Affiliations

¹ Center for Systems Science and Engineering, Johns Hopkins University, Baltimore, MD, 21218, USA; Department of Civil and Systems Engineering, Johns Hopkins University, Baltimore, MD, 21218, USA.
² Center for Systems Science and Engineering, Johns Hopkins University, Baltimore, MD, 21218, USA; Department of Civil and Systems Engineering, Johns Hopkins University, Baltimore, MD, 21218, USA; Department of Earth and Planetary Sciences, Johns Hopkins University, Baltimore, MD, 21218, USA.
³ Department of Epidemiology of Microbial Diseases, Yale School of Public Health, New Haven, CT, 06510, USA.
⁴ Department of Epidemiology of Microbial Diseases, Yale School of Public Health, New Haven, CT, 06510, USA; Department of Ecology and Evolutionary Biology, Yale University, New Haven, CT, 06510, USA.
⁵ Center for Systems Science and Engineering, Johns Hopkins University, Baltimore, MD, 21218, USA; Department of Civil and Systems Engineering, Johns Hopkins University, Baltimore, MD, 21218, USA; Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, 21205, USA. Electronic address: l.gardner@jhu.edu.

Abstract

Background: Since the US reported its first COVID-19 case on January 21, 2020, the science community has been applying various techniques to forecast incident cases and deaths. To date, providing an accurate and robust forecast at a high spatial resolution has proved challenging, even in the short term.

Method: Here we present a novel multi-stage deep learning model to forecast the number of COVID-19 cases and deaths for each US state at a weekly level for a forecast horizon of 1-4 weeks. The model is heavily data driven, and relies on epidemiological, mobility, survey, climate, demographic, and SARS-CoV-2 variant frequencies data. We implement a rigorous and robust evaluation of our model-specifically we report on weekly performance over a one-year period based on multiple error metrics, and explicitly assess how our model performance varies over space, chronological time, and different outbreak phases.

Findings: The proposed model is shown to consistently outperform the CDC ensemble model for all evaluation metrics in multiple spatiotemporal settings, especially for the longer-term (3 and 4 weeks ahead) forecast horizon. Our case study also highlights the potential value of variant frequencies data for use in short-term forecasting to identify forthcoming surges driven by new variants.

Interpretation: Based on our findings, the proposed forecasting framework improves upon the available state-of-the-art forecasting tools currently used to support public health decision making with respect to COVID-19 risk.

Funding: This work was funded the NSF Rapid Response Research (RAPID) grant Award ID 2108526 and the CDC Contract #75D30120C09570.

Keywords: COVID-19; Coronavirus; Deep learning; Forecast; LSTM; Pandemic; Prediction; SARS-CoV-2; State-level; US; Variant frequencies data.

MeSH terms

Benchmarking
COVID-19*
Deep Learning*
Forecasting
Humans
SARS-CoV-2
United States

Supplementary concepts

SARS-CoV-2 variants

Grants and funding

UL1 TR001863/TR/NCATS NIH HHS/United States