Estimating Causal Effects in Observational Studies Using Electronic Health Data: Challenges and (some) Solutions
Open Access
- 1 December 2013
- journal article
- Published by Ubiquity Press, Ltd. in eGEMs (Generating Evidence & Methods to improve patient outcomes)
- Vol. 1 (3)
Abstract
Electronic health data sets, including electronic health records (EHR) and other administrative databases, are rich data sources that have the potential to help answer important questions about the effects of clinical interventions as well as policy changes. However, analyses using such data are almost always non-experimental, leading to concerns that those who receive a particular intervention are likely different from those who do not, in ways that may confound the effects of interest. This paper outlines the challenges in estimating causal effects using electronic health data, and offers some solutions, with particular attention paid to propensity score methods that help ensure comparisons between similar groups. The methods are illustrated with a case study describing the design of a study using Medicare and Medicaid administrative data to estimate the effect of the Medicare Part D prescription drug program among individuals with serious mental illness.Keywords
This publication has 31 references indexed in Scilit:
- Confounding Adjustment in Comparative Effectiveness Research Conducted Within Distributed Research NetworksMedical Care, 2013
- Caveats for the Use of Operational Electronic Health Record Data in Comparative Effectiveness ResearchMedical Care, 2013
- An Introduction to Sensitivity Analysis for Unobserved Confounding in Nonexperimental Prevention ResearchPrevention Science, 2013
- Effect of a UK Pay-for-Performance Program on Ethnic Disparities in Diabetes Outcomes: Interrupted Time Series AnalysisThe Annals of Family Medicine, 2012
- The importance of covariate selection in controlling for selection bias in observational studies.Psychological Methods, 2010
- Propensity score techniques and the assessment of measured covariate balance to test causal associations in psychological research.Psychological Methods, 2010
- Instrumental variables II: instrumental variable application—in 25 variations, the physician prescribing preference generally was strong and reduced covariate imbalanceJournal of Clinical Epidemiology, 2009
- Drug‐induced torsades de pointes: data mining of the public version of the FDA Adverse Event Reporting System (AERS)Pharmacoepidemiology and Drug Safety, 2009
- Implications Of Part D For Mentally Ill Dual Eligibles: A Challenge For MedicareHealth Affairs, 2006
- Estimating the causal effect of zidovudine on CD4 count with a marginal structural model for repeated measuresStatistics in Medicine, 2002