High-dimensional propensity score algorithm in comparative effectiveness research with time-varying interventions
- PMID: 25488047
- DOI: 10.1002/sim.6377
High-dimensional propensity score algorithm in comparative effectiveness research with time-varying interventions
Abstract
The high-dimensional propensity score (hdPS) algorithm was proposed for automation of confounding adjustment in problems involving large healthcare databases. It has been evaluated in comparative effectiveness research (CER) with point treatments to handle baseline confounding through matching or covariance adjustment on the hdPS. In observational studies with time-varying interventions, such hdPS approaches are often inadequate to handle time-dependent confounding and selection bias. Inverse probability weighting (IPW) estimation to fit marginal structural models can adequately handle these biases under the fundamental assumption of no unmeasured confounders. Upholding of this assumption relies on the selection of an adequate set of covariates for bias adjustment. We describe the application and performance of the hdPS algorithm to improve covariate selection in CER with time-varying interventions based on IPW estimation and explore stabilization of the resulting estimates using Super Learning. The evaluation is based on both the analysis of electronic health records data in a real-world CER study of adults with type 2 diabetes and a simulation study. This report (i) establishes the feasibility of IPW estimation with the hdPS algorithm based on large electronic health records databases, (ii) demonstrates little impact on inferences when supplementing the set of expert-selected covariates using the hdPS algorithm in a setting with extensive background knowledge, (iii) supports the application of the hdPS algorithm in discovery settings with little background knowledge or limited data availability, and (iv) motivates the application of Super Learning to stabilize effect estimates based on the hdPS algorithm.
Keywords: Super Learning; comparative effectiveness; diabetes; high-dimensional propensity score; inverse probability weighting; marginal structural model.
Copyright © 2014 John Wiley & Sons, Ltd.
Similar articles
-
Targeted learning in real-world comparative effectiveness research with time-varying interventions.Stat Med. 2014 Jun 30;33(14):2480-520. doi: 10.1002/sim.6099. Epub 2014 Feb 17. Stat Med. 2014. PMID: 24535915
-
Super learning to hedge against incorrect inference from arbitrary parametric assumptions in marginal structural modeling.J Clin Epidemiol. 2013 Aug;66(8 Suppl):S99-109. doi: 10.1016/j.jclinepi.2013.01.016. J Clin Epidemiol. 2013. PMID: 23849160 Free PMC article.
-
Methods for Improving Confounding Control in Comparative Effectiveness Research Using Electronic Healthcare Databases [Internet].Washington (DC): Patient-Centered Outcomes Research Institute (PCORI); 2019 Jul. Washington (DC): Patient-Centered Outcomes Research Institute (PCORI); 2019 Jul. PMID: 38315782 Free Books & Documents. Review.
-
Studies with many covariates and few outcomes: selecting covariates and implementing propensity-score-based confounding adjustments.Epidemiology. 2014 Mar;25(2):268-78. doi: 10.1097/EDE.0000000000000069. Epidemiology. 2014. PMID: 24487209
-
A methodological review of the high-dimensional propensity score in comparative-effectiveness and safety-of-interventions research finds incomplete reporting relative to algorithm development and robustness.J Clin Epidemiol. 2024 May;169:111305. doi: 10.1016/j.jclinepi.2024.111305. Epub 2024 Feb 28. J Clin Epidemiol. 2024. PMID: 38417583 Review.
Cited by
-
Targeted Maximum Likelihood Estimation for Pharmacoepidemiologic Research.Epidemiology. 2016 Jul;27(4):570-7. doi: 10.1097/EDE.0000000000000487. Epidemiology. 2016. PMID: 27031037 Free PMC article.
-
Comparative Effectiveness of the Sodium-Glucose Cotransporter 2 Inhibitor Empagliflozin Versus Other Antihyperglycemics on Risk of Major Adverse Kidney Events.Diabetes Care. 2020 Nov;43(11):2785-2795. doi: 10.2337/dc20-1231. Epub 2020 Sep 10. Diabetes Care. 2020. PMID: 32912850 Free PMC article.
-
Using primary care data to assess comparative effectiveness and safety of apixaban and rivaroxaban in patients with nonvalvular atrial fibrillation in the UK: an observational cohort study.BMJ Open. 2022 Oct 17;12(10):e064662. doi: 10.1136/bmjopen-2022-064662. BMJ Open. 2022. PMID: 36253039 Free PMC article.
-
High-dimensional propensity scores for empirical covariate selection in secondary database studies: Planning, implementation, and reporting.Pharmacoepidemiol Drug Saf. 2023 Feb;32(2):93-106. doi: 10.1002/pds.5566. Epub 2022 Nov 22. Pharmacoepidemiol Drug Saf. 2023. PMID: 36349471 Free PMC article.
-
Matching with time-dependent treatments: A review and look forward.Stat Med. 2020 Jul 30;39(17):2350-2370. doi: 10.1002/sim.8533. Epub 2020 Apr 3. Stat Med. 2020. PMID: 32242973 Free PMC article. Review.