Research
Integrating distributed lag non-linear models and deep learning reveals meteorological drivers of influenza A and B positivity in a 6-year subtropical surveillance study
eLife · By Hai-Yong Pan ·
The Brief
- A six-year subtropical influenza surveillance study combines distributed lag non-linear models with deep learning to examine meteorological drivers of influenza A and B positivity.
- The study addresses non-linear, lagged weather associations and surveillance bias from pandemic-era testing fluctuations.
- The approach aims to both characterize lagged environmental associations and provide forecasting capacity, which existing methods lack.
Why it matters
It offers a method for linking weather with influenza positivity in subtropical settings while accounting for testing bias, which can inform forecasting for public health planning.
Who’s affected
- public health researchers and epidemiologists
- health authorities monitoring seasonal influenza in subtropical regions
Subtropical influenza forecasting is complicated by non-linear meteorological dynamics and surveillance bias stemming from pandemic-era testing fluctuations. Existing approaches either characterize lagged environmental associations without forecasting capacity or apply deep…