Prediction of Tacrolimus Dose/Weight-Adjusted Trough Concentration in Pediatric Refractory Nephrotic Syndrome: A Machine Learning Approach

Abstract

Xiaolan Mo,1,2,* Xiujuan Chen,3,* Xianggui Wang,2,* Xiaoli Zhong,2 Huiying Liang,3 Yuanyi Wei,1 Houliang Deng,1 Rong Hu,1 Tao Zhang,1 Yilu Chen,1 Xia Gao,4 Min Huang,2 Jiali Li2 1Department of Pharmacy, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University, Guangzhou, 510623, People’s Republic of China; 2Institute of Clinical Pharmacology, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, 510080, People’s Republic of China; 3Department of clinical Data Center, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Guangzhou, 510080, People’s Republic of China; 4Division of Nephrology, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University, Guangzhou, 510623, People’s Republic of China*These authors contributed equally to this workCorrespondence: Jiali Li; Min Huang, Tel [phone], Fax [phone], Email [email protected]; [email protected]: 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 (C0/D) in Chinese children with refractory NS, and then develop and validate the TAC C0/D prediction models.Patients and Methods: The association of 82 clinical variables and 244 single nucleotide polymorphisms (SNPs) with TAC C0/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.Results: GBDT algorithm performed best in the whole group (R2=0.444, MSE=591.032, MAE=20.782, MedAE=18.980) and CYP3A5 nonexpresser group (R2=0.264, MSE=477.948, MAE=18.119, MedAE=18.771), while ET algorithm performed best in the CYP3A5 expresser group (R2=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, ACTN 4 rs62121818, CTLA4 rs4553808, CYP3A5 rs776746, IL2RA rs12722489, INF2 rs1128880, MAP3K11 rs7946115, MYH9 rs2239781, and MYH9 rs4821478).Conclusion: The association between the clinical and genetic variables and TAC C0/D was described, and three TAC C0/D prediction models integrating clinical and genetic variables were developed and validated using machine learning, which may support individualized TAC dosing.Keywords: tacrolimus, nephrotic syndrome, machine learning, prediction model, genetic polymorphism

Keywords

• tacrolimus
• nephrotic syndrome
• machine learning
• prediction model
• genetic polymorphism