Controlling confounding of treatment effects in administrative data in the presence of time-varying baseline confounders

• Published in: Pharmacoepidemiology and drug safety 2016-03, Vol.25 (3), p.269-277
• Main Authors: Gilbertson, David T., Bradbury, Brian D., Wetmore, James B., Weinhandl, Eric D., Monda, Keri L., Liu, Jiannong, Brookhart, M. Alan, Gustafson, Sally K., Roberts, Tricia, Collins, Allan J., Rothman, Kenneth J.
• Format: Article
• Language: English
• Subjects: Acute Disease - mortality; administrative claims data; Chronic Disease - mortality; comorbid conditions; confounding; Confounding Factors (Epidemiology); Databases, Factual - statistics & numerical data; Epidemiology; Humans; Insurance Claim Reporting - statistics & numerical data; Medicare - statistics & numerical data; Mortality; nonexperimental research; Outcome Assessment (Health Care) - methods; Outcome Assessment (Health Care) - statistics & numerical data; pharmacoepidemiology; Pharmacoepidemiology - methods; Pharmacoepidemiology - statistics & numerical data; Pharmacology; Proportional Hazards Models; Renal Dialysis - mortality; Renal Dialysis - statistics & numerical data; Risk factors; Side effects; Time Factors; United States
• ISSN: 1053-8569; 1099-1557
• DOI: 10.1002/pds.3922

Purpose Confounding, a concern in nonexperimental research using administrative claims, is nearly ubiquitous in claims‐based pharmacoepidemiology studies. A fixed‐length look‐back window for assessing comorbidity from claims is common, but it may be advantageous to use all historical claims. We assessed how the strength of association between a baseline‐identified condition and subsequent mortality varied by when the condition was measured and investigated methods to control for confounding. Methods For Medicare beneficiaries undergoing maintenance hemodialysis on 1 January 2008 (n = 222 343), we searched all Medicare claims, 1 January 2001 to 31 December 2007, for four conditions representing chronic and acute diseases, and classified claims by number of months preceding the index date. We used proportional hazard models to estimate the association between time of condition and subsequent mortality. We simulated a confounded comorbidity–exposure relationship and investigated an alternative method of adjustment when the association between the condition and mortality varied by proximity to follow‐up start. Results The magnitude of the mortality hazard ratio estimates for each condition investigated decreased toward unity as time increased between index date and most recent manifestation of the condition. Simulation showed more biased estimates of exposure–outcome associations if proximity to follow‐up start was not considered. Conclusions Using all‐available claims information during a baseline period, we found that for all conditions investigated, the association between a comorbid condition and subsequent mortality varied considerably depending on when the condition was measured. Improved confounding control may be achieved by considering the timing of claims relative to follow‐up start. Copyright © 2015 John Wiley & Sons, Ltd.