Value of Disease Risk Scores for Comparative Effectiveness Research with Emerging Therapies

• Activity Number: 22
• Type: Topic Contributed
• Date/Time: Sunday, July 29, 2012 : 2:00 PM to 3:50 PM
• Sponsor: Health Policy Statistics Section
• Author(s): Robert Glynn*+
• Companies: Harvard Medical School
• Keywords: propensity score ; confounding ; multivariable models ; matching ; trimming

Abstract

Use of propensity scores to balance potential confounders at treatment initiation may be limited for newly introduced therapies with evolving use patterns, as early adopters may be very different from later users of the therapy. In this setting, the disease risk score has theoretical advantages as a balancing score in comparative effectiveness research, because of stability of disease risk and the presence of ample historical data on outcomes in people treated before availability of the new therapy. One matching strategy in this context would use a disease risk score and a time-varying propensity score. In early follow-up, more weight could be placed on similarity of disease risk. We illustrate development of a disease risk score and the joint matching approach in the context of the introduction of atorvastatin and the use of high-dose statin therapy beginning in 1997, based on data from 5,668 older survivors of myocardial infarction who filled a statin prescription within 30 days after discharge from 1995 until 2004. The disease risk score also provides a natural scale for evaluation of possible treatment effect heterogeneity.