English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Seasonal influenza causes on average 425,000 hospitalizations and 32,000deaths per year in the United States. Forecasts of influenza-like illness (ILI)-- a surrogate for the proportion of patients infected with influenza --support public health decision making. The goal of an ensemble forecast of ILIis to increase accuracy and calibration compared to individual forecasts and toprovide a single, cohesive prediction of future influenza. However, an ensemblemay be composed of models that produce similar forecasts, causing issues withensemble forecast performance and non-identifiability. To improve upon theabove issues we propose a novel Cluster-Aggregate-Pool or `CAP' ensemblealgorithm that first clusters together individual forecasts, aggregatesindividual models that belong to the same cluster into a single forecast(called a cluster forecast), and then pools together cluster forecasts via alinear pool. When compared to a non-CAP approach, we find that a CAP ensembleimproves calibration by approximately 10% while maintaining similar accuracy tonon-CAP alternatives. In addition, our CAP algorithm (i) generalizes pastensemble work associated with influenza forecasting and introduces a frameworkfor future ensemble work, (ii) automatically accounts for missing forecastsfrom individual models, (iii) allows public health officials to participate inthe ensemble by assigning individual models to clusters, and (iv) provide anadditional signal about when peak influenza may be near.

A Cluster-Aggregate-Pool (CAP) Ensemble Algorithm for Improved Forecast Performance of influenza-like illness