Integration of urine retinol-binding protein and genetic markers for early prediction of tacrolimus nephrotoxicity using machine learning.

Abstract

Background: The use of tacrolimus (TAC) in clinical settings is hindered by its nephrotoxic effects, which can vary significantly among individuals. Urine retinol-binding protein (RP), as a novel biochemical marker, is a potential indicator for early detection of renal tubular injury caused by TAC. The objective was to develop and validate a machine learning model that combines clinical features with genetic markers for predicting TAC nephrotoxicity in children with nephrotic syndrome (NS).

Methods: A retrospective cohort of 203 children diagnosed with NS who were admitted between June 2013 and December 2018 was used for model development, while 12 children were prospectively recruited for external validation. The model incorporated 38 clinical features and 80 genetic variables, with changes in urine RP levels pre- and post-TAC administration indicating renal tubular toxicity. Five machine learning algorithms were employed: Extra Random Trees (ET), Gradient Boosting Decision Tree (GBDT), random forests (RF), and eXtreme Gradient Boosting (XGBoost), and logistic regression (LR).

Results: The LR model, including six genetic markers (CYP3A5*3 rs776746_*3/*3, NFATC1 rs1660144_AA, NFKB1 rs230526_AG, NFKBIA rs696_TC, CD2AP rs12664637_CT and PLCE1 rs2274223_AG), exhibited the best performance with a sensitivity of 78.6%, specificity of 63.8%, accuracy of 67.2%, and area under the curve (AUC) of 76.1%.

Conclusions: By employing RP as a marker of renal toxicity, we established and validated the renal tubular toxicity prediction model for the use of TAC using machine learning incorporating genetic factors of NS patients. This model allows physicians to evaluate the risk of nephrotoxic effects and adjust treatment plans accordingly to prevent kidney injury.