AI Article Synopsis

  • Accurate forecasts improve public health responses to seasonal influenza, with 26 teams providing predictions for hospital admissions in 2021-22 and 2022-23.
  • Six out of 23 models performed better than the baseline in 2021-22, while 12 out of 18 models did so in 2022-23, with the FluSight ensemble being highly ranked in both seasons.
  • Despite its accuracy, the FluSight ensemble and other models struggled with longer forecast periods, especially during times of rapid change in influenza patterns.

Article Abstract

Accurate forecasts can enable more effective public health responses during seasonal influenza epidemics. For the 2021-22 and 2022-23 influenza seasons, 26 forecasting teams provided national and jurisdiction-specific probabilistic predictions of weekly confirmed influenza hospital admissions for one-to-four weeks ahead. Forecast skill is evaluated using the Weighted Interval Score (WIS), relative WIS, and coverage. Six out of 23 models outperform the baseline model across forecast weeks and locations in 2021-22 and 12 out of 18 models in 2022-23. Averaging across all forecast targets, the FluSight ensemble is the 2 most accurate model measured by WIS in 2021-22 and the 5 most accurate in the 2022-23 season. Forecast skill and 95% coverage for the FluSight ensemble and most component models degrade over longer forecast horizons. In this work we demonstrate that while the FluSight ensemble was a robust predictor, even ensembles face challenges during periods of rapid change.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11282251PMC
http://dx.doi.org/10.1038/s41467-024-50601-9DOI Listing

Publication Analysis

Top Keywords

flusight ensemble
12
2021-22 2022-23
8
forecast skill
8
influenza
5
forecast
5
title evaluation
4
flusight
4
evaluation flusight
4
flusight influenza
4
influenza forecasting
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!