Probabilistic forecasting of daily COVID-19 admissions using machine learning

Rostami-Tabar, Bahman ORCID: https://orcid.org/0000-0002-3730-0045, Arora, Siddharth, Rendon-Sanchez, Juan F. and Goltsos, Thanos E. ORCID: https://orcid.org/0000-0002-5245-9775 2024. Probabilistic forecasting of daily COVID-19 admissions using machine learning. IMA Journal of Management Mathematics 35 (1) , pp. 21-43. 10.1093/imaman/dpad009

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

Accurate forecasts of daily COVID-19 admissions are critical for healthcare planners and decision-makers to better manage scarce resources during and around infection peaks. Numerous studies have focused on forecasting COVID-19 admissions at the national or global levels. Localised predictions are vital, as they allow for resource planning redistribution, but also scarce and harder to get right. Several possible indicators can be used to predict COVID-19 admissions. The inherent variability in the admissions necessitates the generation and evaluation of the forecast distri- bution of admissions, as opposed to producing only a point forecast. In this study, we propose a quantile regression forest (QRF) model for probabilistic forecasting of daily COVID-19 admissions for a local hospital trust (aggregation of 3 hospitals), up to 7-days ahead, using a multitude of different predictors. We evaluate point forecast accuracy as well as the accuracy of the forecast distribution using appro- priate measures. We provide evidence that QRF outperforms univariate time series methods and other more sophisticated benchmarks. Our findings also show that lagged admissions, total positive cases, daily tests performed, and Google grocery and Apple driving are the most salient predictors. Finally, we highlight areas where further research is needed.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Business (Including Economics)
Publisher:	Oxford University Press
ISSN:	1471-678X
Date of First Compliant Deposit:	14 April 2023
Date of Acceptance:	10 May 2023
Last Modified:	16 Jan 2024 15:58
URI:	https://orca.cardiff.ac.uk/id/eprint/158857

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item