Comparison of different approaches to confounding adjustment in a study on the association of antipsychotic medication with mortality in older nursing home patients

Abstract

Selective prescribing of conventional antipsychotic medication (APM) to frailer patients is thought to have led to overestimation of the association with mortality in pharmacoepidemiologic studies relying on claims data. The authors assessed the validity of different analytic techniques to address such confounding. The cohort included 82,012 persons initiating APM use after admission to a nursing home in 45 states with 2001-2005 Medicaid/Medicare data, linked to clinical data (Minimum Data Set) and institutional characteristics. The authors compared the association between APM class and 180-day mortality with multivariate outcome modeling, propensity score (PS) adjustment, and instrumental variables. The unadjusted risk difference (per 100 patients) of 10.6 (95% confidence interval (CI): 9.4, 11.7) comparing use of conventional medication with atypical APM was reduced to 7.8 (95% CI: 6.6, 9.0) and 7.0 (95% CI: 5.8, 8.2) after PS adjustment and high-dimensional PS (hdPS) adjustment, respectively. Results were similar in analyses limited to claims-based Medicaid /Medicare variables (risk difference = 8.2 for PS, 7.1 for hdPS). Instrumental-variable estimates were imprecise (risk difference = 8.8, 95% CI: -1.3, 19.0) because of the weak instrument. These results suggest that residual confounding has a relatively small impact on the effect estimate and that hdPS methods based on claims alone provide estimates at least as good as those from conventional analyses using claims enriched with clinical information.

Figure 1.

Risk of death among nursing home residents within 180 days of the start of antipsychotic medication use (conventional vs. atypical) according to different analytic approaches representing increasing levels of adjustment. For ease of interpretation, the y-axis does not start at the null value. (MDS, Minimum Data Set; OSCAR, Online Survey, Certification and Reporting; PS, propensity score; hdPS, high-dimensional propensity score).

Figure 2.

Example of sensitivity analysis of residual confounding (rule-out approach) for an estimated relative risk (RR) of 1.34 and different levels of confounder prevalence (open circle: prevalence of confounder (P_c) = 0.25; filled square: P_c = 0.05; filled circle: P_c = 0.01). Each line splits the area into two. The upper right area represents all combinations of an association (odds ratio (OR)) between exposure and confounder (OR_EC) and an association between confounder and outcome (RR_CO) that would create confounding by an unmeasured factor strong enough to move the point estimate of RR to the null value (RR = 1) or beyond. The area to the lower left represents all parameter combinations that would not be able to move the estimated RR toward the null.