Paulina Kaiser1, Alice M Arnold2, David Benkeser2, Adina Zeki Al Hazzouri3, Calvin H Hirsch4, Bruce M Psaty5, Michelle C Odden1. 1. College of Public Health & Human Sciences, Oregon State University, Corvallis, OR, USA. 2. Department of Biostatistics, School of Public Health, University of Washington, Seattle, WA, USA. 3. Department of Public Health Sciences, Miller School of Medicine, University of Miami, Miami, FL, USA. 4. Center for Healthcare Policy and Research, University of California Davis, Davis, CA, USA. 5. Cardiovascular Health Research Unit, Department of Medicine, Epidemiology, and Health Services, University of Washington, Seattle, Washington and Kaiser Permanente Washington Health Research Institute, Seattle, WA, USA.
Abstract
Background: The theoretical conditions under which causal estimates can be derived from observational data are challenging to achieve in the real world. Applied examples can help elucidate the practical limitations of methods to estimate randomized-controlled trial effects from observational data. Methods: We used six methods with varying design and analytic features to compare the 5-year risk of incident myocardial infarction among statin users and non-users, and used non-cardiovascular mortality as a negative control outcome. Design features included restriction to a statin-eligible population and new users only; analytic features included multivariable adjustment and propensity score matching. Results: We used data from 5294 participants in the Cardiovascular Health Study from 1989 to 2004. For non-cardiovascular mortality, most methods produced protective estimates with confidence intervals that crossed the null. The hazard ratio (HR) was 0.92, 95% confidence interval: 0.58, 1.46 using propensity score matching among eligible new users. For myocardial infarction, all estimates were strongly protective; the propensity score-matched analysis among eligible new users resulted in a HR of 0.55 (0.29, 1.05)-a much stronger association than observed in randomized controlled trials. Conclusions: In designs that compare active treatment with non-treated participants to evaluate effectiveness, methods to address bias in observational data may be limited in real-world settings by residual bias.
Background: The theoretical conditions under which causal estimates can be derived from observational data are challenging to achieve in the real world. Applied examples can help elucidate the practical limitations of methods to estimate randomized-controlled trial effects from observational data. Methods: We used six methods with varying design and analytic features to compare the 5-year risk of incident myocardial infarction among statin users and non-users, and used non-cardiovascular mortality as a negative control outcome. Design features included restriction to a statin-eligible population and new users only; analytic features included multivariable adjustment and propensity score matching. Results: We used data from 5294 participants in the Cardiovascular Health Study from 1989 to 2004. For non-cardiovascular mortality, most methods produced protective estimates with confidence intervals that crossed the null. The hazard ratio (HR) was 0.92, 95% confidence interval: 0.58, 1.46 using propensity score matching among eligible new users. For myocardial infarction, all estimates were strongly protective; the propensity score-matched analysis among eligible new users resulted in a HR of 0.55 (0.29, 1.05)-a much stronger association than observed in randomized controlled trials. Conclusions: In designs that compare active treatment with non-treated participants to evaluate effectiveness, methods to address bias in observational data may be limited in real-world settings by residual bias.
Authors: Sebastian Schneeweiss; Amanda R Patrick; Til Stürmer; M Alan Brookhart; Jerry Avorn; Malcolm Maclure; Kenneth J Rothman; Robert J Glynn Journal: Med Care Date: 2007-10 Impact factor: 2.983
Authors: Rozenn N Lemaitre; Bruce M Psaty; Susan R Heckbert; Richard A Kronmal; Anne B Newman; Gregory L Burke Journal: Arch Intern Med Date: 2002-06-24
Authors: Jeff Y Yang; Tiansheng Wang; Virginia Pate; Emily W Gower; Matthew J Crowley; John B Buse; Til Stürmer Journal: Diabetes Obes Metab Date: 2019-03-04 Impact factor: 6.577
Authors: Adina Zeki Al Hazzouri; Neal Jawadekar; Leslie Grasset; Paulina Kaiser; Katrina Kezios; Sebastian Calonico; Maria Glymour; Calvin Hirsch; Alice M Arnold; Ravi Varadhan; Michelle C Odden Journal: J Gerontol A Biol Sci Med Sci Date: 2022-05-05 Impact factor: 6.591