Renal transplantation is the best treatment for end-stage renal disease. Transplanted patients need to take immunosuppressant drugs to keep long-term survival. However, the cost of immunosuppressant drugs is high in China, so it is necessary to conduct a cost-effectiveness analysis of immunosuppressant drugs to provide guidance for medical decision. Transition probabilities estimation is a key step in cost-effectiveness analysis. In order to obtain accurate estimations of transition probabilities from small sample, a Markov model and genetic algorithm based method is proposed in this paper. Then, this method is applied in a case study. The results of case study show that the effectiveness of cyclosporine and tacrolimus are comparable in the following five years after transplantation. Meanwhile, the results of the case study also show that Markov model and genetic algorithm based method is effective for cost effectiveness analysis and can be used in other cost-effectiveness analysis studies.