Intervention effects in observational survival studies with an application in total hip replacements

Time to revision is a common and clinically relevant endpoint for studies of patients with total hip replacement. Because failures occur rarely within the first years after replacement, new surgical techniques and materials are often implemented without evidence of their effectiveness from randomized trials. Observational data may be available but this relies on the use of historical controls which has been heavily criticized. Instead the use of changepoint methods has been suggested to detect changes caused by successfully implemented interventions. In the setting of a proportional hazards model we develop a semi-parametric changepoint method to detect changes in baseline hazard. The procedure is motivated by and applied to a clinical study in patients with total hip replacements, where the effect of a new cement type is of interest. Power properties of the proposed method are investigated.