Evidence-driven spatiotemporal COVID-19 hospitalization prediction with Ising dynamics
Open Access
- 29 May 2023
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-14
Abstract
In this work, we aim to accurately predict the number of hospitalizations during the COVID-19 pandemic by developing a spatiotemporal prediction model. We propose HOIST, an Ising dynamics-based deep learning model for spatiotemporal COVID-19 hospitalization prediction. By drawing the analogy between locations and lattice sites in statistical mechanics, we use the Ising dynamics to guide the model to extract and utilize spatial relationships across locations and model the complex influence of granular information from real-world clinical evidence. By leveraging rich linked databases, including insurance claims, census information, and hospital resource usage data across the U.S., we evaluate the HOIST model on the large-scale spatiotemporal COVID-19 hospitalization prediction task for 2299 counties in the U.S. In the 4-week hospitalization prediction task, HOIST achieves 368.7 mean absolute error, 0.6 $${R}^{2}$$ and 0.89 concordance correlation coefficient score on average. Our detailed number needed to treat (NNT) and cost analysis suggest that future COVID-19 vaccination efforts may be most impactful in rural areas. This model may serve as a resource for future county and state-level vaccination efforts.
Keywords
Funding Information
- National Science Foundation (SCH-2205289, SCH-2014438, IIS-1838042)
This publication has 30 references indexed in Scilit:
- Charlson Comorbidity Index Score and Risk of Severe Outcome and Death in Danish COVID-19 PatientsJournal of General Internal Medicine, 2020
- Metapopulation Network Models for Understanding, Predicting, and Managing the Coronavirus Disease COVID-19Frontiers in Physics, 2020
- An interactive web-based dashboard to track COVID-19 in real timeThe Lancet Infectious Diseases, 2020
- Initial Simulation of SARS-CoV2 Spread and Intervention Effects in the Continental USmedRxiv, 2020
- Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventionsJournal of Thoracic Disease, 2020
- Epidemic modeling in metapopulation systems with heterogeneous coupling pattern: Theory and simulationsJournal of Theoretical Biology, 2008
- New ICD-10 version of the Charlson comorbidity index predicted in-hospital mortalityJournal of Clinical Epidemiology, 2004
- A Blau space primer: prolegomenon to an ecology of affiliationIndustrial and Corporate Change, 2004
- A trust region method based on interior point techniques for nonlinear programmingMathematical Programming, 2000
- An Introduction to the Ising ModelThe American Mathematical Monthly, 1987