The use of propensity scores in pharmacoepidemiologic research

Abstract

Purpose Ð To describe the application of propensity score analysis in pharmacoepidemiologic research using a study comparing the renal eects of two commonly prescribed non-steroidal anti-in¯ammatory drugs (NSAIDs).Method Ð Observational data were collected on the change in renal function, as measured by serum creatinine concentration, before and after use of two NSAIDs, Ibuprofen and Sulindac. To estimate the treatment eect of the dierent NSAIDs, we used the propensity score methodology to reduce the potential confounding eects caused by unbalanced covariates. After estimating the propensity scores (the probabilities of each patient being prescribed Sulindac) from a logistic regression model, we strati®ed the data based on sample quintiles of the propensity score distribution. The ®nal estimate of the treatment eect was then obtained by averaging the treatment estimates from the strati®ed samples.Results Ð Initially, 23 covariates diered signi®cantly between the two treatment groups. Using the propensity score methodology, we were able to balance the distributions of 16 covariates. The imbalances in the remaining seven covariates were also greatly reduced. Although the use of either drug resulted in a decrease in renal function, overall dierences between them were not statistically signi®cant with respect to their eect on creatinine concentrations based on the propensity score analysis.Conclusion Ð Observational studies often produce treatment groups that are not directly comparable due to imbalances in covariate distributions between the treatment groups. Propensity score analysis provides a simple and eective way of controlling the eects of these covariates and obtaining a less biased estimate of the treatment eect.

Iatrogenic Gastric Acid Suppression and the Risk of Nosocomial Clostridium difficile Infection

“…30,31 Fourth, we controlled for the likelihood of administration of moreintense acid suppression therapy using techniques commonly recommended in pharmacoepidemiology. 32 Finally, our results were resilient to the specific analytic technique applied, with remarkably similar estimates of the dose-response relationship.…”

Protease inhibitor-based direct-acting antivirals are associated with increased risk of aminotransferase elevations but not hepatic dysfunction or decompensation

“…To reduce the potential for selection bias in examining rates of ALI events between PIbased DAA therapy (glecaprevir/pibrentasvir, elbasvir/grazoprevir, or PRO/PROD) and non-PIbased regimens (sofosbuvir/ledipasvir or sofosbuvir/velpatasvir), we developed propensity scores, which determine each patient's probability of being assigned to a particular treatment given their observed set of baselined covariates. 24 Propensity score methods allow for the reduction of bias when estimating treatment effects by accounting for the differential probability of receiving PI-based or non-PI-based DAA therapy. The propensity score model was developed using logistic regression, with potential determinants of PI-based DAA therapy as independent variables and PI-based DAA treatment exposure as the dependent variable.…”

Effect of calcineurin inhibitor on post-endoscopic retrograde cholangiopancreatography pancreatitis in patients with liver transplantation: a propensity-matched cohort study

“…Because this was a retrospective cohort study, patients were not randomized before the interventions. Therefore, we used a propensity score matching method to reduce the bias due to confounding [17]. A logistic regression model was created to calculate the propensity score.…”