Machine Learning Predicts Kidney Allograft Survival

Using machine learning, researchers identified serum creatinine levels, pre-transplant body weight, age of patients, and bkpyv infection as key predictors for early allograft loss in kidney transplant patients. The model achieved a high precision of 0.81, sensitivity of 0.61, specificity of 0.89, and auc value of 0.84. These findings highlight the potential of machine learning tools to aid in clinical decision-making for kidney transplantation.