Due to the special nature of medical device clinical studies, observational comparative studies play important roles in the pre-market safety/effectiveness evaluation of medical devices. While historical data have been used to serve as controls in some comparative studies, registry data are emerging to provide opportunities for the pre-market device evaluations. However, in such studies, various biases could be introduced in every stage and aspect of study and may compromise the objectivity of study design and validity of study results. In this presentation, challenges and opportunities in the design of such studies using propensity score methodology will be discussed from regulatory perspectives.