Table 2.

Cox proportional hazard regression models for MACE

	HR	95% CI	p value
Ever-exposed analysis
Prespecifieda	1.533	1.103–2.131	0.011
Propensity-score adjustedb	1.176	0.929–1.490	0.177
Compared with ADAc	0.820	0.532–1.265	0.370
91-day-exposed analysis
Prespecifieda	1.193	0.917–1.553	0.189
Propensity-score adjusted	NA	NA	NA
Compared with ADAc	0.592	0.366–0.956	0.032

ADA adalimumab, CI confidence interval, HR hazard ratio, IPTW inverse probability of treatment weighting, MACE major adverse cardiovascular events, NA not applicable

^aThe prespecified analyses used Cox proportional hazards regression methodology adjusted for baseline covariates and time-varying effects of biologic therapies using non-biologics as the comparator for ustekinumab

^bPropensity-score adjustments with IPTW were used to mitigate the effect of residual imbalances in baseline characteristics between the ustekinumab and non-biologics cohorts

^cEvaluation of methodological limitations of previous analyses indicate that adalimumab is the most appropriate comparator for ustekinumab and that only incident users should be included in the analyses