Tacrolimus (TAC) is a first-line immunosuppressant for patients with refractory nephrotic syndrome (NS). However, there is a high inter-patient variability of TAC pharmacokinetics, thus therapeutic drug monitoring (TDM) is required. In this study, we aimed to employ machine learning algorithms to investigate the impact of clinical and genetic variables on the TAC dose/weight-adjusted trough concentration (C 0/D) in Chinese children with refractory NS, and then develop and validate the TAC C 0/D prediction models.
The association of 82 clinical variables and 244 single nucleotide polymorphisms (SNPs) with TAC C 0/D in the third month since TAC treatment was examined in 171 children with refractory NS. Extremely randomized trees (ET), gradient boosting decision tree (GBDT), random forest (RF), extreme gradient boosting (XGBoost), and Lasso regression were carried out to establish and validate prediction models, respectively. The best prediction models were validated on a cohort of 30 refractory NS patients.
GBDT algorithm performed best in the whole group (R 2=0.444, MSE=591.032, MAE=20.782, MedAE=18.980) and CYP3A5 nonexpresser group (R 2=0.264, MSE=477.948, MAE=18.119, MedAE=18.771), while ET algorithm performed best in the CYP3A5 expresser group (R 2=0.380, MSE=1839.459, MAE=31.257, MedAE=19.399). These prediction models included 3 clinical variables (ALB0, AGE0, and gender) and 10 SNPs ( ACTN4 rs3745859, ACTN4 rs56113315, ACTN4 rs62121818, CTLA4 rs4553808, CYP3A5 rs776746, IL2RA rs12722489, INF2 rs1128880, MAP3K11 rs7946115, MYH9 rs2239781, and MYH9 rs4821478).