Incremental Propensity Score Interventions: A Primer for Pharmacoepidemiologists

BACKGROUND: In observational pharmacoepidemiology, estimating average treatment effects (ATEs) is often challenging due to a lack of practical positivity. In highly selective clinical settings, certain patients almost always or never receive treatment, causing ATE estimators to rely on unstable extrapolation. Incremental propensity score interventions (IPSIs) offer a stochastic alternative by shifting each patient's probability of treatment, providing a more clinically realistic framework that circumvents positivity violations. METHODS: We illustrate the IPSI approach, including key identification results and inferential procedures. Using observational data from a cohort of 996 patients undergoing percutaneous coronary intervention (PCI), we evaluated the effect of shifting each patient's probability of receiving abciximab by a predetermined amount on six-month mortality. Propensity scores (PSs) and outcome predictions were estimated using a machine learning ensemble (Super Learner) with 10-fold sample splitting. RESULTS: The ATE estimate suggested that abciximab administration reduced the 6-month mortality risk by 5.9 percentage points compared with PCI alone (risk difference = -0.059, 95% CI: -0.104 to -0.015). However, the practical interpretability of the ATE estimate may be limited because it implicitly assumes that patients with a near-certain probability of treatment could realistically be assigned to withhold abciximab. In contrast, shifting each patient's treatment propensity by odds ratios ranging from 0.1 to 10 showed that 6-month mortality would be significantly reduced under a strong treatment policy promoting abciximab administration. CONCLUSIONS: IPSIs provide a robust and practical alternative to conventional causal inference methods in pharmacoepidemiology settings where treatment assignment is highly selective and the strict positivity is violated. In observational pharmacoepidemiology studies, it is often difficult to estimate treatment effects reliably because some participants are much more likely than others to receive a treatment based on their demographic and clinical characteristics. In these situations, traditional causal inference methods that compare scenarios in which all individuals are either treated or untreated may rely on unrealistic assumptions. This study demonstrates the use of incremental propensity score interventions (IPSIs), a newer causal inference approach that evaluates more realistic changes in treatment practice. Instead of assuming that treatment can be administered or withheld across all patients, IPSIs examine what would happen if the probability of receiving treatment were gradually increased or decreased for each participant.