ObjectiveTo establish an optimal model to predict the teicoplanin trough concentrations by machine learning, and explain the feature importance in the prediction model using the SHapley Additive exPlanation (SHAP) method.MethodsA retrospective study was performed on 279 therapeutic drug monitoring (TDM) measurements obtained from 192 patients who were treated with teicoplanin intravenously at the First Affiliated Hospital of Army Medical University from November 2017 to July 2021. This study included 27 variables, and the teicoplanin trough concentrations were considered as the target variable. The whole dataset was divided into a training group and testing group at the ratio of 8:2, and predictive performance was compared among six different algorithms. Algorithms with higher model performance (top 3) were selected to establish the ensemble prediction model and SHAP was employed to interpret the model.ResultsThree algorithms (SVR, GBRT, and RF) with high R2 scores (0.676, 0.670, and 0.656, respectively) were selected to construct the ensemble model at the ratio of 6:3:1. The model with R2 = 0.720, MAE = 3.628, MSE = 22.571, absolute accuracy of 83.93%, and relative accuracy of 60.71% was obtained, which performed better in model fitting and had better prediction accuracy than any single algorithm. The feature importance and direction of each variable were visually demonstrated by SHAP values, in which teicoplanin administration and renal function were the most important factors.ConclusionWe firstly adopted a machine learning approach to predict the teicoplanin trough concentration, and interpreted the prediction model by the SHAP method, which is of great significance and value for the clinical medication guidance.

ObjectivesBody surface area (BSA) is an important parameter in clinical practice for children. To find out the most accurate BSA formula for Chinese children, nine formulas were compared.MethodsThis single-center study comprised children who were diagnosed with acute lymphoblastic leukemia and treated with anticancer agents in a specialized children's hospital in China from January 2017 to December 2020. The BSA values were calculated using the formulas from Boyd, Banerjee and Bhattacharya, Costeff, Fujimoto and Watanabe, Haycock, Gehan and George, Mosteller, Stevenson and a Pediatrics textbook. The arithmetic mean of formulas was calculated as the “gold standard” for comparison.ResultsA total of 666 children (389 males and 277 females) were included. All nine formulas showed a strong positive correlation with the “gold standard.” Underestimation was observed with the Banerjee and Bhattacharya, Fujimoto and Watanabe formulas. The Gehan and George formula showed overestimation. Values estimated from the Haycock and Mosteller formulas were the closest to the mean BSA.ConclusionThe Haycock and Mosteller formulas are the most recommended formulas for Chinese children with hematological malignancies.