Osthus D, Moran KR. Multiscale influenza forecasting. Nat Commun. 2021 May 20;12(1):2991
Influenza forecasting in the United States (US) is complex and challenging due to spatial and temporal variability, nested geographic scales of interest, and heterogeneous surveillance participation. Here we present Dante, a multiscale influenza forecasting model that learns rather than prescribes spatial, temporal, and surveillance data structure and generates coherent forecasts across state, regional, and national scales. We retrospectively compare Dante´s short-term and seasonal forecasts for previous flu seasons to the Dynamic Bayesian Model (DBM), a leading competitor. Dante outperformed DBM for nearly all spatial units, flu seasons, geographic scales, and forecasting targets. Dante´s sharper and more accurate forecasts also suggest greater public health utility. Dante placed 1st in the Centers for Disease Control and Prevention´s prospective 2018/19 FluSight challenge in both the national and regional competition and the state competition. The methodology underpinning Dante can be used in other seasonal disease forecasting contexts having nested geographic scales of interest.
See Also:
Latest articles in those days:
- Influenza D Virus Infection in China, 2022-2023 11 hours ago
- Evidence of reassortment of avian influenza A (H2) viruses in Brazilian shorebirds 11 hours ago
- Epitopes in the HA and NA of H5 and H7 avian influenza viruses that are important for antigenic drift 2 days ago
- Assessment of CD8+ T-cell mediated immunity in an influenza A(H3N2) human challenge model in Belgium: a single centre, randomised, double-blind phase 2 study 2 days ago
- Dual N-linked glycosylation at residues 133 and 158 in the hemagglutinin are essential for the efficacy of H7N9 avian influenza virus like particle vaccine in chickens and mice 2 days ago
[Go Top] [Close Window]