ABSTRACT
To study the e¢ cacy of a test drug for progressive disease such as cancer or HIV, a parallel-group active-control randomized clinical trial is often used. Under the study design, quali…ed patients are randomly assigned to receive either an active control or the test treatment under investigation. Patients are allowed to switch from one treatment to another due to ethical considerations such as lack of response or if there is evidence of disease progression. In practice, it is not uncommon that up to 80% of patients may switch from one treatment to another. This certainly has an impact on the evaluation of the e¢ cacy of the test treatment. Despite the switching between di¤erent treatments or interventions, many clinical studies are to compare the test drug with the active control agent as if no patients had ever switched. The e¤ect of treatment switching will impact the survival curve. The
patterns of the curves before and after switching are expected to be different, for example, they may follow a mixed exponential distribution with di¤erent hazard rates before and after switching. Sommer and Zeger (1991) referred to the treatment e¤ect among pa-
tients who complied with treatment as biological e¢ cacy. The survival time of a patient who switched from the active control to the test treatment might be on the average longer than his/her survival time that would have been if he/she had adhered to the original treatment, if switching is based on prognosis to optimally assign patients’treatments over time. We refer to the di¤erence caused by treatment switch as switching e¤ect. The purpose of this chapter is to provide useful models for modeling
clinical trials with response-adaptive treatment switching. The remaining of this chapter is organized as follows. A mixed exponential model is considered to assess the total survival time in Section 13.2. A mixture of Wiener
of hazard rate is considered by incorporating the switching e¤ect in the latent hazard functions. Summary and discussions will be presented in Section 13.5.
