This study focused on creating and testing a machine learning model(MLL) to predict the risk of sepsis after a procedure used to treat kidney stones called flexible ureteroscopic lithotripsy (fURL). This was a retrospective study that used patient records from 1,990 patients who had undergone fURL in order to train and test many MLLs. Eight pieces of information were used to base the MLLs’ predictions on:white blood cell count (WBC), albumin, creatinine (CR), alanine transaminase (ALT), Double-J stent duration, urinary white blood cell count (uWBC), surgical duration, and stone burden. After evaluating the fifteen trained models for their accuracy and precision, it was found that Extra Trees (ET) showed superior performance. This model made its predictions by forming many randomized decision trees, which allowed it to have high generalizability. Although ET had the “black box effect”(the ambiguity of process that is present in many MLs), the study addressed that using the Shapley Additive Explanations (SHAP) method in order to rationalize its decisions. Overall, this study successfully created and validated a clinically useful machine learning model that could be used to predict sepsis risk after fURL, and in order to make the model more accessible, the researchers deployed it as a web-based application.