ABSTRACT
BACKGROUND: Observational healthcare data can be used for drug safety and effectiveness research. The use of inverse probability of treatment weights (IPW) reduces measured confounding under the assumption of accurate measurement of the outcome variable; however, many datasets suffer from systematic outcome misclassification. METHODS: We introduced a modification to IPW to correct for the presence of outcome misclassification. To demonstrate the utility of these modified weights in realistic settings, we investigated postmyocardial infarction statin use and the 1-year risk of stroke in the Clinical Practice Research Datalink. RESULTS: We computed an IPW-adjusted odds ratio (OR = 0.67; 95% confidence interval (CI) = 0.48, 0.93). We employed a technique to modify IPW for the presence of outcome misclassification using linked hospital records for outcome validation (modified IPW adjusted OR = 0.77; 95% CI = 0.52, 1.15) and compared the results with a meta-analysis of randomized controlled trials (RCTs) (pooled OR = 0.80; 95% CI = 0.74, 0.87). Finally, we present simulation studies to investigate the impact of model selection on bias reduction and variability. CONCLUSION: Ignoring outcome misclassification yielded biased estimates whereas the use of the modified IPW approach produced encouraging results when compared with the meta-analytic RCT findings.
Subject(s)
Hydroxymethylglutaryl-CoA Reductase Inhibitors , Myocardial Infarction , Stroke , Bias , Humans , Hydroxymethylglutaryl-CoA Reductase Inhibitors/adverse effects , Hydroxymethylglutaryl-CoA Reductase Inhibitors/therapeutic use , Myocardial Infarction/drug therapy , Probability , Risk , Stroke/chemically induced , Stroke/epidemiology , Treatment OutcomeABSTRACT
BACKGROUND: Although the efficacy and safety of smoking cessation interventions are well established, their efficacy and safety in patients with cardiovascular disease (CVD) remain unclear. The objective of this study was to evaluate the efficacy and safety of pharmacological and behavioral smoking cessation interventions in CVD patients via a meta-analysis of randomized controlled trials. METHODS AND RESULTS: EMBASE, PsycINFO, MEDLINE, PubMed, and the Cochrane Tobacco Addiction Specialized Register were searched for randomized controlled trials evaluating the efficacy of smoking cessation pharmacotherapies and behavioral therapies in CVD patients. Outcomes of interest were smoking abstinence at 6 and 12 months, defined using the most rigorous criteria reported. Data were pooled across studies for direct comparisons using random-effects models. Network meta-analysis using a graph-theoretical approach was used to generate the indirect comparisons. Seven pharmacotherapy randomized controlled trials (n=2809) and 17 behavioral intervention randomized controlled trials (n=4666) met our inclusion criteria. Our network meta-analysis revealed that varenicline (relative risk [RR]: 2.64; 95% confidence interval [CI], 1.34-5.21) and bupropion (RR: 1.42; 95% CI, 1.01-2.01) were associated with greater abstinence than placebo. The evidence about nicotine replacement therapies was inconclusive (RR: 1.22; 95% CI, 0.72-2.06). Telephone therapy (RR: 1.47; 95% CI: 1.15-1.88) and individual counseling (RR: 1.64, 95% CI: 1.17-2.28) were both more efficacious than usual care, whereas in-hospital behavioral interventions were not (RR: 1.05; 95% CI, 0.78-1.43). CONCLUSIONS: Our meta-analysis suggests varenicline and bupropion, as well as individual and telephone counseling, are efficacious for smoking cessation in CVD patients.