H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, 30309, USA.
Sci Rep. 2022 Jun 11;12(1):9661. doi: 10.1038/s41598-022-13162-9.
As the COVID-19 spread over the globe and new variants of COVID-19 keep occurring, reliable real-time forecasts of COVID-19 hospitalizations are critical for public health decisions on medical resources allocations. This paper aims to forecast future 2 weeks national and state-level COVID-19 new hospital admissions in the United States. Our method is inspired by the strong association between public search behavior and hospitalization admissions and is extended from a previously-proposed influenza tracking model, AutoRegression with GOogle search data (ARGO). Our LASSO-penalized linear regression method efficiently combines Google search information and COVID-19 related time series information with dynamic training and rolling window prediction. Compared to other publicly available models collected from COVID-19 forecast hub, our method achieves substantial error reduction in a retrospective out-of-sample evaluation from Jan 4, 2021, to Dec 27, 2021. Overall, we showed that our method is flexible, self-correcting, robust, accurate, and interpretable, making it a potentially powerful tool to assist healthcare officials and decision making for the current and future infectious disease outbreaks.
随着 COVID-19 在全球范围内的传播和新的 COVID-19 变体不断出现，对 COVID-19 住院的可靠实时预测对于公共卫生部门关于医疗资源分配的决策至关重要。本文旨在预测美国未来两周的全国和州级 COVID-19 新住院人数。我们的方法受到公众搜索行为与住院人数之间的强烈关联的启发，并从之前提出的流感跟踪模型（AutoRegression with GOogle search data，ARGO）扩展而来。我们的 LASSO 惩罚线性回归方法有效地结合了 Google 搜索信息和 COVID-19 相关时间序列信息，并进行动态训练和滚动窗口预测。与从 COVID-19 预测中心收集的其他公开可用模型相比，我们的方法在 2021 年 1 月 4 日至 2021 年 12 月 27 日的回顾性样本外评估中大幅降低了误差。总体而言，我们表明我们的方法灵活、自我修正、稳健、准确且可解释，使其成为一种潜在的强大工具，可以帮助医疗保健官员和决策者应对当前和未来的传染病爆发。
