Mathematical AI Predicts 40% and 57% Influenza Vaccine Effectiveness Against H1N1 and H3N2, Respectively, for the 2026--2027 U.S. Season

Abstract

Background: Clinical influenza vaccine effectiveness (VE) has often been low over the past two decades, highlighting the need for preseason VE forecasting. Timely forecasts could help health authorities plan prevention strategies and allocate healthcare resources. However, preseason forecasting of clinical influenza VE remains relatively uncommon. Methods: We obtained hemagglutinin (HA) sequences from GISAID for U.S. specimens collected in August--September before each influenza season from 2010--2011 through 2024--2025. After quality screening, we compared each virus with the corresponding vaccine target strain for the same season and subtype or lineage using two mathematical distances based on amino acid patterns in the HA protein. We calculated mean distances for each season and subtype or lineage and paired them with published clinical VE estimates, yielding 26 observations across 13 seasons. Using a mathematical AI approach, we fitted linear regression models of VE against each distance and evaluated their predictive performance by forecasting later seasons using data from earlier seasons, with the historical mean VE for each subtype or lineage as a reference. We then applied the same approach to 87 HA sequences collected in August--September 2026 to forecast VE for the 2026--2027 season. Results: We generated component-specific forecasts of influenza VE for the upcoming 2026--2027 U.S. season. Both mathematical distances were negatively associated with historical VE, indicating that greater differences between circulating viruses and vaccine strains were associated with lower VE. The topological model forecast VE of 40.3%, 56.9%, and 47.1% against A(H1N1)pdm09, A(H3N2), and B/Victoria, respectively, whereas the geometric model forecast corresponding VE values of 34.0%, 56.8%, and 51.1%.