Precision Immunosuppression and Long-Term Kidney Transplant Outcomes: A Dual Survival Modeling Framework

Optimizing immunosuppressive therapy remains central to improving long-term outcomes after kidney transplantation. Both induction and maintenance therapies are widely used, yet their comparative effectiveness across heterogeneous populations requires further evaluation. To this end, this national retrospective cohort study analyzed 228,855 deceased-donor kidney transplant recipients using the over two-decade data (2000-2024). We employed multivariable Cox proportional hazards (PH) models for clinical inference and four machine learning (ML) survival models: random survival forest (RSF), support vector machine (SVM), penalized Cox regression (CoxNet), and extreme gradient boosting optimized with the Cox partial likelihood (XGBoost-Cox) to assess predictive performance of death-censored graft failure and all-cause patient mortality. Model performance was evaluated using the concordance index (C-index) and time-dependent area under the curve (tdAUC). Maintenance regimens with calcineurin inhibitors (CNI) and mycophenolate mofetil (MMF) demonstrated protective effects for both graft failure (CNI+MMF: hazard ratio [HR] 0.72, 95% confidence interval [CI] 0.70-0.74; CNI+MMF+steroids: HR 0.84, 95% CI 0.82-0.87) and patient mortality (CNI+MMF: HR 0.78, 95% CI 0.76-0.81; CNI+MMF+steroids: HR 0.90, 95% CI 0.88-0.93). Among induction therapies, antithymocyte globulin (ATG) showed protective associations (HR 0.93 for both outcomes), while interleukin-2 receptor (IL-2R) antagonists and Alemtuzumab demonstrated neutral effects. Combined ATG + IL-2R therapy comparatively increased the hazard of graft failure (HR 1.09). Recipient diabetes, dialysis dependence, older age, and higher Kidney Donor Profile Index (KDPI) were strong adverse predictors. Traditional Cox regression achieved robust discrimination (graft failure concordance index: 0.685; patient mortality concordance index: 0.704) comparable to ML survival models. These findings reinforce CNI and MMF maintenance regimens as foundational to contemporary immunosuppression while demonstrating differential effectiveness across induction strategies. The dual analytical framework, which integrates classical Cox PH modeling with ML survival models, shows that Cox models remain highly competitive for clinical inference while ML approaches offer complementary predictive value to support individualized post-transplant risk stratification.