Does spatial information improve forecasting of influenza-like illness?
Seasonal influenza forecasting is critical for public health and individual decision making. We investigate whether the inclusion of data about influenza activity in neighboring states can improve point predictions and distribution forecasting of influenza-like illness (ILI) in each US state using s...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Epidemics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1755436525000088 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850067485271785472 |
|---|---|
| author | Gabrielle Thivierge Aaron Rumack F. William Townes |
| author_facet | Gabrielle Thivierge Aaron Rumack F. William Townes |
| author_sort | Gabrielle Thivierge |
| collection | DOAJ |
| description | Seasonal influenza forecasting is critical for public health and individual decision making. We investigate whether the inclusion of data about influenza activity in neighboring states can improve point predictions and distribution forecasting of influenza-like illness (ILI) in each US state using statistical regression models. Using CDC FluView ILI data from 2010–2019, we forecast weekly ILI in each US state with quantile, linear, and Poisson autoregressive models fit using different combinations of ILI data from the target state, neighboring states, and the US population-weighted average. Scoring with root mean squared error and weighted interval score indicated that the covariate sets including neighbors and/or the US weighted average ILI showed slightly higher accuracy than models fit only using lagged ILI in the target state, on average. Additionally, the improvement in performance when including neighbors was similar to the improvement when including the US average instead, suggesting the proximity of the neighboring states is not the driver of the slight increase in accuracy. There is also clear within-season and between-season variability in the effect of spatial information on prediction accuracy. |
| format | Article |
| id | doaj-art-adcb0ce622f2409d9bc020f5a5f45d8b |
| institution | DOAJ |
| issn | 1755-4365 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Epidemics |
| spelling | doaj-art-adcb0ce622f2409d9bc020f5a5f45d8b2025-08-20T02:48:18ZengElsevierEpidemics1755-43652025-06-015110082010.1016/j.epidem.2025.100820Does spatial information improve forecasting of influenza-like illness?Gabrielle Thivierge0Aaron Rumack1F. William Townes2Department of Statistics & Data Science, Carnegie Mellon University, Pittsburgh, 15213, PA, USA; Corresponding author.Machine Learning Department, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, 15213, PA, USADepartment of Statistics & Data Science, Carnegie Mellon University, Pittsburgh, 15213, PA, USASeasonal influenza forecasting is critical for public health and individual decision making. We investigate whether the inclusion of data about influenza activity in neighboring states can improve point predictions and distribution forecasting of influenza-like illness (ILI) in each US state using statistical regression models. Using CDC FluView ILI data from 2010–2019, we forecast weekly ILI in each US state with quantile, linear, and Poisson autoregressive models fit using different combinations of ILI data from the target state, neighboring states, and the US population-weighted average. Scoring with root mean squared error and weighted interval score indicated that the covariate sets including neighbors and/or the US weighted average ILI showed slightly higher accuracy than models fit only using lagged ILI in the target state, on average. Additionally, the improvement in performance when including neighbors was similar to the improvement when including the US average instead, suggesting the proximity of the neighboring states is not the driver of the slight increase in accuracy. There is also clear within-season and between-season variability in the effect of spatial information on prediction accuracy.http://www.sciencedirect.com/science/article/pii/S1755436525000088SpatialInfluenzaForecastingAutoregressiveInfectious diseaseInfluenza-like illness |
| spellingShingle | Gabrielle Thivierge Aaron Rumack F. William Townes Does spatial information improve forecasting of influenza-like illness? Epidemics Spatial Influenza Forecasting Autoregressive Infectious disease Influenza-like illness |
| title | Does spatial information improve forecasting of influenza-like illness? |
| title_full | Does spatial information improve forecasting of influenza-like illness? |
| title_fullStr | Does spatial information improve forecasting of influenza-like illness? |
| title_full_unstemmed | Does spatial information improve forecasting of influenza-like illness? |
| title_short | Does spatial information improve forecasting of influenza-like illness? |
| title_sort | does spatial information improve forecasting of influenza like illness |
| topic | Spatial Influenza Forecasting Autoregressive Infectious disease Influenza-like illness |
| url | http://www.sciencedirect.com/science/article/pii/S1755436525000088 |
| work_keys_str_mv | AT gabriellethivierge doesspatialinformationimproveforecastingofinfluenzalikeillness AT aaronrumack doesspatialinformationimproveforecastingofinfluenzalikeillness AT fwilliamtownes doesspatialinformationimproveforecastingofinfluenzalikeillness |