Fig. 2

Multivariable-adjusted* Hazard ratios of duration of allopurinol use with incident stroke by age (2a), gender (2b) and race (2c). Legend: *For the multivariable-adjusted subgroup analyses by age, gender and race, the main model was adjusted for all factors (age, gender, race and Charlson-Romano comrobidity score) except the factor of interest, respectively, which was used to perform stratified analysis (age, gender, race). We found that several subgroups had statistically significantly reduced hazard with allopurinol use, namely: Age group 65–75 years, 181 days to 2 years; Age group 75–84 years, >2 years; female gender, 181 days to 2 years; White race, 181 days to 2 years and >2 years. As expected, most of the subgroups had very few events, and therefore most subgroup analyses did not have power to detect significant differences within each subgroup