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

Abstract

Tacrolimus is a widely used immunosuppressive drug in patients with autoimmune diseases. It has a narrow therapeutic window, thus requiring therapeutic drug monitoring (TDM) to guide the clinical regimen. This study included 193 cases of tacrolimus TDM data in patients with autoimmune diseases at Southern Medical University Nanfang Hospital from June 7, 2018, to December 31, 2020. The study identified nine important variables for tacrolimus concentration using sequential 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. The prediction abilities of 14 models based on regression analysis or machine learning algorithms were compared. Ultimately, a prediction model of tacrolimus concentration was established through eXtreme Gradient Boosting (XGBoost) algorithm with the best predictive ability (R ² = 0.54, mean absolute error = 0.25, and root mean square error = 0.33). Then, SHapley Additive exPlanations was used to visually interpret the variable's impacts on tacrolimus concentration. In conclusion, the XGBoost model for predicting blood concentration of tacrolimus on the basis of real-world evidence has good predictive performance, providing guidance for the adjustment of regimen in clinical practice.

Keywords: autoimmune disease; blood concentration prediction; machine learning; tacrolimus; therapeutic drug monitoring.

FIGURE 1

Workflow of patients selection.

FIGURE 2

R ² (A), MAE, and RMSE (B) corresponding to the number of ranked variables.

FIGURE 3

Scatter plot of actual and predicted tacrolimus TDM value.

FIGURE 4

SHAP values of the important risk factors. The dot color is redder when the feature value gets higher and bluer when the feature value gets lower. When the SHAP value gets higher, the impact of the variable on model output is larger.