AUTHOR=Zheng Ping , Yu Ze , Li Liren , Liu Shiting , Lou Yan , Hao Xin , Yu Peng , Lei Ming , Qi Qiaona , Wang Zeyuan , Gao Fei , Zhang Yuqing , Li Yilei 

TITLE=Predicting Blood Concentration of Tacrolimus in Patients With Autoimmune Diseases Using Machine Learning Techniques Based on Real-World Evidence

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2021.727245

DOI=10.3389/fphar.2021.727245

ISSN=1663-9812

ABSTRACT=Tacrolimus is a widely used immunosuppressive drug in patients with autoimmune diseases. It has narrow therapeutic window, which needs therapeutic drug monitoring (TDM) to guide clinical regimen. The study included 193 cases of tacrolimus TDM data in patients with autoimmune diseases at Southern Medical University Nan fang Hospital from June 7, 2018, to December 31, 2020. The study identified nine important variables for tacrolimus concentration using Sequence Forward Selection, including height, tacrolimus daily dose, other immunosuppressants, low density lipoprotein cholesterol, mean corpuscular volume, mean corpuscular hemoglobin, white blood cell count, direct bilirubin, and hematocrit. Fourteen models based on regression analysis or machine learning algorithms were compared their prediction abilities. Ultimately, a prediction model of tacrolimus concentration was established through XGBoost algorithm with the best predictive ability (R2 = 0.54, MAE = 0.25 and RMSE = 0.33). Then Shapley Additive exPlanations was used to visually interpret the variables’ impacts on tacrolimus concentration. In conclusion, the XGBoost model for predicting blood concentration of tacrolimus based on real-world evidence has a good predictive performance, providing guidance for the adjustment of regimen in clinical practice.