Immunosuppressive therapy is vital for the success of a kidney transplant, yet it entails potential risks and side effects. The challenge lies in finding the right balance between suppressing the immune response enough to prevent rejection while minimizing the risk of infections, organ toxicity, and other complications associated with long-term immunosuppression. This study leverages machine learning to predict optimal immunosuppressive therapies in kidney transplantation. Using data from the United Network of Organ Sharing (UNOS) national registry (2010-2021), diverse patient cohorts were examined to assess predictive model generalizability. Model performance was evaluated using diverse metrics, with Shapley Additive Explanation (SHAP) values adding interpretation through summary plots. This research sheds light on the potential of data-driven approaches to enhance personalized medicine in the field of kidney transplantation, ultimately aiming to improve patient outcomes and long-term graft survival. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://bibliotheek.ehb.be:2222/en-US/products/dissertations/individuals.shtml.]