Yong Chen1, Becky A Briesacher. 1. University of Massachusetts Medical School, and Meyers Primary Care Institute, Worcester, MA 01605, USA. yong.chen@umassmed.edu
Abstract
OBJECTIVE: Instrumental variable (IV) analysis may offer a useful approach to the problem of unmeasured confounding in prescription drug research if the IV is: (1) strongly and unbiasedly associated to treatment assignment; and (2) uncorrelated with factors predicting the outcome (key assumptions). STUDY DESIGN AND METHODS: We conducted a systematic review of the use of IV methods in prescription drug research to identify the major types of IVs and the evidence for meeting IV assumptions. We searched MEDLINE, OVID, PsychoInfo, EconLit, and economic databases from 1961 to 2009. RESULTS: We identified 26 studies. Most (n=16) were published after 2007. We identified five types of IVs: regional variation (n=8), facility-prescribing patterns (n=5), physician preference (n=8), patient history/financial status (n=3), and calendar time (n=4). Evidence supporting the validity of IV was inconsistent. All studies addressed the first IV assumption; however, there was no standard for demonstrating that the IV sufficiently predicted treatment assignment. For the second assumption, 23 studies provided explicit argument that IV was uncorrelated with the outcome, and 16 supported argument with empirical evidence. CONCLUSIONS: Use of IV methods is increasing in prescription drug research. However, we did not find evidence of a dominant IV. Future research should develop standards for reporting the validity and strength of IV according to key assumptions.
OBJECTIVE: Instrumental variable (IV) analysis may offer a useful approach to the problem of unmeasured confounding in prescription drug research if the IV is: (1) strongly and unbiasedly associated to treatment assignment; and (2) uncorrelated with factors predicting the outcome (key assumptions). STUDY DESIGN AND METHODS: We conducted a systematic review of the use of IV methods in prescription drug research to identify the major types of IVs and the evidence for meeting IV assumptions. We searched MEDLINE, OVID, PsychoInfo, EconLit, and economic databases from 1961 to 2009. RESULTS: We identified 26 studies. Most (n=16) were published after 2007. We identified five types of IVs: regional variation (n=8), facility-prescribing patterns (n=5), physician preference (n=8), patient history/financial status (n=3), and calendar time (n=4). Evidence supporting the validity of IV was inconsistent. All studies addressed the first IV assumption; however, there was no standard for demonstrating that the IV sufficiently predicted treatment assignment. For the second assumption, 23 studies provided explicit argument that IV was uncorrelated with the outcome, and 16 supported argument with empirical evidence. CONCLUSIONS: Use of IV methods is increasing in prescription drug research. However, we did not find evidence of a dominant IV. Future research should develop standards for reporting the validity and strength of IV according to key assumptions.
Authors: Sylvia P B Ramirez; Justin M Albert; Margaret J Blayney; Francesca Tentori; David A Goodkin; Robert A Wolfe; Eric W Young; George R Bailie; Ronald L Pisoni; Friedrich K Port Journal: J Am Soc Nephrol Date: 2009-04-08 Impact factor: 10.121
Authors: Soko Setoguchi; Philip S Wang; M Alan Brookhart; Claire F Canning; Liljana Kaci; Sebastian Schneeweiss Journal: J Am Geriatr Soc Date: 2008-08-04 Impact factor: 5.562
Authors: Jaclyn L F Bosco; Rebecca A Silliman; Soe Soe Thwin; Ann M Geiger; Diana S M Buist; Marianne N Prout; Marianne Ulcickas Yood; Reina Haque; Feifei Wei; Timothy L Lash Journal: J Clin Epidemiol Date: 2009-05-19 Impact factor: 6.437
Authors: Lauren E Cain; Stephen R Cole; Sander Greenland; Todd T Brown; Joan S Chmiel; Lawrence Kingsley; Roger Detels Journal: Am J Epidemiol Date: 2009-03-24 Impact factor: 4.897
Authors: Francesca Tentori; Justin M Albert; Eric W Young; Margaret J Blayney; Bruce M Robinson; Ronald L Pisoni; Takashi Akiba; Roger N Greenwood; Naoki Kimata; Nathan W Levin; Luis M Piera; Rajiv Saran; Robert A Wolfe; Friedrich K Port Journal: Nephrol Dial Transplant Date: 2008-11-21 Impact factor: 5.992
Authors: Sonja A Swanson; Sonia Hernandez-Diaz; Kristin Palmsten; Helen Mogun; Mark Olfson; Krista F Huybrechts Journal: Pharmacoepidemiol Drug Saf Date: 2015-06-04 Impact factor: 2.890
Authors: Md Jamal Uddin; Rolf H H Groenwold; Mohammed Sanni Ali; Anthonius de Boer; Kit C B Roes; Muhammad A B Chowdhury; Olaf H Klungel Journal: Int J Clin Pharm Date: 2016-04-18
Authors: Michel Jadoul; Angelo Karaboyas; David A Goodkin; Francesca Tentori; Yun Li; Laura Labriola; Bruce M Robinson Journal: Am J Nephrol Date: 2014-03-08 Impact factor: 3.754