Optimizing vancomycin dosing in pediatrics: a machine learning approach to predict trough concentrations in children under four years of age.

BACKGROUND: Vancomycin trough concentration is closely associated with clinical efficacy and toxicity. Predicting vancomycin trough concentrations in pediatric patients is challenging due to significant inter-individual variability and rapid physiological changes during maturation. AIM: This study aimed to develop a machine learning model to predict vancomycin trough concentrations and determine optimal dosing regimens for pediatric patients < 4 years of age using ML algorithms. METHOD: A single-center retrospective observational study was conducted from January 2017 to March 2020. Pediatric patients who received intravenous vancomycin and underwent therapeutic drug monitoring were enrolled. Seven ML models [linear regression, gradient boosted decision trees, support vector machine, decision tree, random forest, Bagging, and extreme gradient boosting (XGBoost)] were developed using 31 variables. Performance metrics including R-squared (R2), mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) were compared, and important features were ranked. RESULTS: The study included 120 eligible trough concentration measurements from 112 patients. Of these, 84 measurements were used for training and 36 for testing. Among the seven algorithms tested, XGBoost showed the best performance, with a low prediction error and high goodness of fit (MAE = 2.55, RMSE = 4.13, MSE = 17.12, and R2 = 0.59). Blood urea nitrogen, serum creatinine, and creatinine clearance rate were identified as the most important predictors of vancomycin trough concentration. CONCLUSION: An XGBoost ML model was developed to predict vancomycin trough concentrations and aid in drug treatment predictions as a decision-support technology.

Leonurine alleviates vancomycin nephrotoxicity via activating PPARγ and inhibiting the TLR4/NF-κB/TNF-α pathway.

Vancomycin (VCM) is the first-line antibiotic for severe infections, but nephrotoxicity limits its use. Leonurine (Leo) has shown protective effects against kidney damage. However, the effect and mechanism of Leo on VCM nephrotoxicity remain unclear. In this study, mice and HK-2 cells exposed to VCM were treated with Leo. Biochemical and pathological analysis and fluorescence probe methods were performed to examine the role of Leo in VCM nephrotoxicity. Immunohistochemistry, q-PCR, western blot, FACS, and Autodock software were used to verify the mechanism. The present results indicate that Leo significantly alleviates VCM-induced renal injury, morphological damage, and oxidative stress. Increased intracellular and mitochondrial ROS in HK-2 cells and decreased mitochondrial numbers in mouse renal tubular epithelial cells were reversed in Leo-administrated groups. In addition, molecular docking analysis using Autodock software revealed that Leo binds to the PPARγ protein with high affinity. Mechanistic exploration indicated that Leo inhibited VCM nephrotoxicity via activating PPARγ and inhibiting the TLR4/NF-κB/TNF-α inflammation pathway. Taken together, our results indicate that the PPARγ inhibition and inflammation reactions were implicated in the VCM nephrotoxicity and provide a promising therapeutic strategy for renal injury.

Cost-effectiveness analysis of dinutuximab ß for the treatment of high-risk neuroblastoma in China.

BACKGROUND: Dinutuximab ß can be used to treat children with high-risk neuroblastoma (NB). Due to its high price, whether dinutuximab ß is cost-effective for the treatment of high-risk NB remains uncertain. Therefore, assessing the cost-effectiveness of dinutuximab ß in children with high-risk NB is of high importance. METHODS: The health utilities and economic outcomes in children with high-risk NB were projected using a partitioned survival model. The individual patient data (IPD) of add-on treatment with dinutuximab ß (GD2 group) were derived from the literature, while the IPD of traditional therapy (TT group) were obtained from retrospective data of Shanghai Children's Medical Center. Treatment costs included drugs, adverse event-related expenses, and medical resource use. Utility values were obtained from the literature. Costs and quality-adjusted life-years (QALYs) were measured over a 10-year time horizon. Deterministic sensitivity analyses (DSA) and probabilistic sensitivity analyses (PSA) were also conducted. RESULTS: Compared with the TT group, QALY increased in the GD2 group by 0.72 with an increased cost of $171,269.70, leading to an incremental cost-effectiveness ratio of 236,462.75$/QALY. DSA showed that the price of dinutuximab ß was the main factor on the results than other parameters. Compared with the TT group, the GD2 group could not be cost-effective in the PSA at the $37,920/QALY threshold. CONCLUSION: Results found that dinutuximab ß is not a cost-effective treatment option for children with high-risk NB unless its price is significantly reduced.