Defining influenza epidemic zones through temporal clustering of global surveillance data

IntroductionModeling when influenza epidemics typically occur can help countries optimize surveillance, time clinical and public health interventions, and reduce the burden of influenza. MethodsWe used influenza virus detections reported during 2011-2024 by 180 countries to the Global Influenza Surveillance and Response System, excluding COVID-19 pandemic impacted years (2020-2023). We analyzed data by calendar year (week 1-52) or shifted year (week 30-29) time windows, based on when most influenza detections occurred in each country. For countries with sufficient data, we computed generalized additive models (GAMs) of each countrys weekly influenza-positive tests to smooth and impute time series distributions. From these GAMs, we calculated each countrys normalized weekly influenza burden. Country-specific normalized time series were grouped using hierarchical k-means clustering reducing the Euclidean distance between time series within clusters. We calculated cluster-specific GAMs to estimate average seasonal timing. Countries without sufficient data were assigned to a cluster based on population-weighted latitudinal distance to a clusters mean latitude. ResultsWe identified five clusters, or epidemic zones, from 111 countries with sufficient data. The influenza burden in epidemic zones A and B was consistent with a northern hemisphere pattern, with most influenza detections occurring during October-April (A) and September-March (B), while epidemic zones D and E were characterized by southern hemisphere-like seasonal timing, with most influenza burden occurring during May-November. Epidemic zone C had most influenza burden occurring during September-March; most countries assigned to this cluster were in the tropics. ConclusionEpidemic zones may serve as a useful tool to strengthen and optimize influenza surveillance for global health decision-making (e.g., during vaccine strain composition discussions) and to guide country preparedness efforts for seasonal influenza epidemics, including the timing of enhanced surveillance, as well as the procurement and delivery of vaccines and antivirals. What is already known on this topicPrevious initiatives to provide a framework for describing global influenza patterns and to support national and regional prevention and control strategies have classified countries into influenza transmission zones, based primarily on geographic proximity. Many countries have improved their surveillance systems for respiratory viruses, providing an opportunity to re-assess patterns of influenza dynamics using analytic approaches focused on influenza detection data and maximizing global coverage. What this study addsOptimal clustering of influenza surveillance data from 111 countries and proximal assignment by latitude of countries lacking sufficient data grouped countries into five epidemic zones. How this study might affect research, practice or policyBy providing improved resolution on the temporal and geographical dynamics of influenza activity, this study offers an evidence base to aid national and global decision-making on enhanced surveillance strategies, vaccine strain selection, seasonal epidemic preparedness, and resource allocation, thereby strengthening efforts to prevent and control influenza worldwide. This data-driven framework for characterizing global patterns of influenza virus circulation can be leveraged to reexamine patterns as new data become available.