Probabilistic forecasting of prefecture-level influenza in Japan accounting for surveillance data release histories
- 1Central Medience.Co.,Ltd., Tokyo, Japan, Medical Corporation Soshinkai Kyoto, Japan, Medical Corporation Hakuwakai, Nagano, Japan,
Abstract
BackgroundPublic-health use of influenza surveillance - situational awareness, planning for clinical surge, and issuing advisories or warnings - needs more than an accurate point estimate of next weeks count. What matters operationally is whether a rise is caught early, whether the direction of change is right, and whether an alert threshold is about to be crossed, all with honest uncertainty. For such use a forecast must also respect reporting delay, later data revision, and the calibration of its prediction intervals. Using Japans sentinel surveillance, we evaluated short-term probabilistic forecasts that respect the data release history, and we measured what adding other surveillance series contributes, focusing on the properties that matter for public-health decisions.
MethodsThe target was the number of influenza reports per sentinel site in each of the 47 prefectures. For each forecast we predicted, as quantiles, the value 1-4 weeks after the most recent observed week. We compared three models: a ridge regression trained jointly across prefectures; a gradient-boosting quantile regression (GBQR) that learns from many surveillance series; and their equal-weight combination on the log scale. Six seasons were used to develop the models. The 2025/26 season was held out as a temporal evaluation period after the specification was fixed; because its epidemic profile had already been seen, it is not a fully independent prospective test. We scored forecasts with the weighted interval score (WIS) and checked prediction-interval coverage. For the Japanese target series we used the value first published for each week; some auxiliary series were taken as retrieved and therefore include later revisions.
ResultsIn 2025/26, the combinations WIS relative to a persistence forecast was 0.841, 0.811, 0.794 and 0.818 at horizons of 1-4 observed weeks - that is, 16-21% lower than persistence. Coverage of the 80% prediction interval was 79.7%, 77.1%, 74.5% and 75.1%, and of the 95% interval 94.3%, 93.4%, 92.6% and 91.8%. Adding auxiliary series improved the GBQR over the development period. However, on the original scale the combinations edge over ridge regression was not statistically clear, and in some low-level rising phases the combination did worse than ridge.
ConclusionsOver the period studied, models that share information across regions scored better than a persistence forecast. For public-health use, however, the operative questions are the real lead time once reporting delay is accounted for, whether rises from low levels and threshold exceedances are caught in time, and whether the upper prediction intervals are wide enough; on these, the present evidence is not yet sufficient. The 2025 change to the sentinel system also means that pre-change advisory and warning thresholds cannot be read mechanically. A prospective evaluation with strictly controlled data availability is needed before such forecasts are used to support advisories or planning.
Related
- 2018–2025 Serological study on avian influenza among occupationally exposed populations in the Poyang Lake area — the region with the highest environmental surveillance positive rate in China
- Viral circulation patterns and hospitalisation burden of SARS-CoV-2 and influenza in the post-pandemic period: an analysis of surveillance data from the United States, England and Europe, 2022-2025
- Use of Metagenomic Next-Generation Sequencing to Investigate Respiratory Pathogens in Influenza-Negative Nasopharyngeal Swabs From Cameroon's National Influenza Surveillance.
- Large‐Scale Genomic Surveillance of Swine Influenza A Viruses in Europe Highlights Increased Reassortment Potential and Field‐Based Associations With Clinical Manifestations
- Utility of Rt epidemic trend categories for influenza surveillance: alignment with observed emergency department trends across two influenza seasons in the United States
BibTeX
@misc{nakagawa2026probabilistic,
title = {{Probabilistic forecasting of prefecture-level influenza in Japan accounting for surveillance data release histories}},
author = {R. NAKAGAWA and N. Yamamura},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.09.26364706},
url = {https://www.medrxiv.org/content/10.64898/2026.10.09.26364706v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Probabilistic forecasting of prefecture-level influenza in Japan accounting for surveillance data release histories
AU - R. NAKAGAWA
AU - N. Yamamura
PY - 2026
DA - 2026/10/09
PB - medRxiv
DO - 10.64898/2026.10.09.26364706
UR - https://www.medrxiv.org/content/10.64898/2026.10.09.26364706v1
AB - BackgroundPublic-health use of influenza surveillance - situational awareness, planning for clinical surge, and issuing advisories or warnings - needs more than an accurate point estimate of next weeks count. What matters operationally is whether a rise is caught early, whether the direction of change is right, and whether an alert threshold is about to be crossed, all with honest uncertainty. For such use a forecast must also respect reporting delay, later data revision, and the calibration of its prediction intervals. Using Japans sentinel surveillance, we evaluated short-term probabilistic forecasts that respect the data release history, and we measured what adding other surveillance series contributes, focusing on the properties that matter for public-health decisions. MethodsThe target was the number of influenza reports per sentinel site in each of the 47 prefectures. For each forecast we predicted, as quantiles, the value 1-4 weeks after the most recent observed week. We compared three models: a ridge regression trained jointly across prefectures; a gradient-boosting quantile regression (GBQR) that learns from many surveillance series; and their equal-weight combination on the log scale. Six seasons were used to develop the models. The 2025/26 season was held out as a temporal evaluation period after the specification was fixed; because its epidemic profile had already been seen, it is not a fully independent prospective test. We scored forecasts with the weighted interval score (WIS) and checked prediction-interval coverage. For the Japanese target series we used the value first published for each week; some auxiliary series were taken as retrieved and therefore include later revisions. ResultsIn 2025/26, the combinations WIS relative to a persistence forecast was 0.841, 0.811, 0.794 and 0.818 at horizons of 1-4 observed weeks - that is, 16-21% lower than persistence. Coverage of the 80% prediction interval was 79.7%, 77.1%, 74.5% and 75.1%, and of the 95% interval 94.3%, 93.4%, 92.6% and 91.8%. Adding auxiliary series improved the GBQR over the development period. However, on the original scale the combinations edge over ridge regression was not statistically clear, and in some low-level rising phases the combination did worse than ridge. ConclusionsOver the period studied, models that share information across regions scored better than a persistence forecast. For public-health use, however, the operative questions are the real lead time once reporting delay is accounted for, whether rises from low levels and threshold exceedances are caught in time, and whether the upper prediction intervals are wide enough; on these, the present evidence is not yet sufficient. The 2025 change to the sentinel system also means that pre-change advisory and warning thresholds cannot be read mechanically. A prospective evaluation with strictly controlled data availability is needed before such forecasts are used to support advisories or planning.
ER -