Dose-Dependent Negative Effects of Prior Multiple Vaccinations Against Influenza A and Influenza B Among Schoolchildren: A Study of Kamigoto Island in Japan During the 2011-2012, 2012-2013, and 2013-2014 Influenza Seasons

Background. We investigated the negative effects of prior multiple vaccinations on influenza vaccine effectiveness (VE) and analyzed the association of VE with prior vaccine doses. Methods. Patients aged 9-18 years presenting with influenza-like illness at a community hospital on a remote Japanese island during the 2011-2012, 2012-2013, and 2013-2014 influenza seasons were tested for influenza using a rapid diagnostic test (RDT). A test-negative, case-control study design was used to estimate the VEs of trivalent inactivated influenza vaccine. Histories of vaccination and medically attended influenza (MA-flu) A and B during 3 previous seasons were collected from registry systems. VE was calculated using multilevel mixed-effects logistic regression models adjusted for the history of RDT-confirmed MA-flu. Results. During 3 influenza seasons, 1668 influenza-like illness episodes were analyzed, including 421 and 358 episodes of MA-fluA and MA-fluB, respectively. The adjusted VE (95% confidence interval) yielded significant dose-dependent attenuations by prior vaccinations against both MA-fluA (0 doses during previous 3 seasons: 96% [69%-100%], 1 dose: 48% [-7% to 74%], 2 doses: 52% [11%-74%], 3 doses: 21% [-25% to 51%]; P for trend < .05) and MA-fluB (0 doses: 66% [-5% to 89%], 1 dose: 48% [-14% to 76%], 2 doses: 34% [-33% to 67%], 3 doses: -7% [-83% to 37%]; P for trend < .05). After excluding episodes of MA-flu during prior 3 seasons, similar trends were observed. Conclusions. Repeated previous vaccinations over multiple seasons had significant dose-dependent negative impacts on VE against both MA-fluA and MA-fluB. Further studies to confirm this finding are necessary.