Key result
Matching on the high-dimensional propensity score achieved adequate balance (ASDD <0.1) on all 18 examined characteristics, including those hidden to the algorithm, supporting its ability to adjust for unmeasured confounders.
Population
Patients initiated on statins
Comparison
High-dimensional propensity score matching using… vs Unmatched cohort
Design
Cohort
Authors
Loading...
May improve confounder adjustment in observational cohorts; leaves open whether hdPS yields unbiased statin effect estimates.
Observational (n=404,129)
The high-dimensional propensity score method can adjust for at least some unmeasured confounders, as demonstrated in a statin initiation cohort.
Guertin et al. (2016) conducted an observational in New statin users (n=404,129). High-dose statins vs. Low-dose statins was evaluated on Balance of 18 baseline patient characteristics measured by absolute standardized differences (ASDD). Matching on the high-dimensional propensity score achieved adequate balance (ASDD <0.1) on all 18 examined characteristics, including those hidden to the algorithm, supporting its ability to adjust for unmeasured confounders.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: