213 Influence of Demographic and Clinical Variables on Vancomycin Trough Values in Pediatric Burn Patients

Ivanova, Xenia; Tran, Nam K.; Lui, Xiaoxi; Sullivan, Katie; Neely, Alice N.; Kagan, Richard J.; Healy, Daniel P.; Sherwin, Catherine M.T.; Wead, Stephanie

doi:10.1093/jbcr/iry006.135

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 5 At present, studies about vancomycin concentration analysis commonly adopt the population pharmacokinetic (PPK) models, which are affected by a few factors, such as age, weight and creatinine/creatinine clearance rate. 1 , 6 According to the guideline on vancomycin monitoring, trough concentrations in the range 15–20 mg/L were recommended for serious infections to improve clinical outcomes and prevent drug resistance. 7 , 8 Based on the daily monitoring of vancomycin concentration, we found that great individual variation exists among children, with generally low concentrations of vancomycin, most of which cannot reach the effective blood drug concentration, hence the PPK model may not be suitable to predict the dosage for children.…”

Section: Introductionmentioning

confidence: 99%

“…As it is challenging to achieve recommended trough concentrations in children, therapeutic drug monitoring (TDM) in pediatric patients is necessary. 6 …”

Section: Introductionmentioning

confidence: 99%

“…As it is challenging to achieve recommended trough concentrations in children, therapeutic drug monitoring (TDM) in pediatric patients is necessary. 6 So far, some vancomycin concentration prediction algorithms were developed using linear regression analysis in adult and pediatric patients. 9,10 The rapidly developing machine learning methods can help promote data-driven estimation when predicting from multiple variables and capture non-linear variable relations to achieve high accuracy in predicting clinical outcomes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Ensemble Model for Prediction of Vancomycin Trough Concentrations in Pediatric Patients

Huang¹,

Yu²,

Bu³

et al. 2021

DDDT

View full text Add to dashboard Cite

Purpose This study aimed to establish an optimal model to predict vancomycin trough concentrations by using machine learning. Patients and Methods We enrolled 407 pediatric patients (age < 18 years) who received vancomycin intravenously and underwent therapeutic drug monitoring from June 2013 to April 2020 at Xinhua Hospital affiliated to Shanghai Jiaotong University School of Medicine. The median (interquartile range) age and weight of the patients were 2 (0.63–5) years and 12 (7.8–19) kg. Vancomycin trough concentrations were considered as the target variable, and eight different algorithms were used for predictive performance comparison. The whole dataset (407 cases) was divided into training group and testing group at the ratio of 80%: 20%, which were 325 and 82 cases, respectively. Results Ultimately, five algorithms (XGBoost, GBRT, Bagging, ExtraTree and decision tree) with high R 2 (0.657, 0.514, 0.468, 0.425 and 0.450, respectively) were selected and further ensembled to establish the final model and achieve an optimal result. For missing data, through filling the missing values and model ensemble, we obtained R 2 =0.614, MAE=3.32, MSE=24.39, RMSE=4.94 and a prediction accuracy of 51.22% (predicted trough concentration within ±30% of the actual trough concentration). In comparison with the pharmacokinetic models ( R 2 =0.3), the machine learning model works better in model fitting and has better prediction accuracy. Conclusion Therefore, the ensemble model is useful for the vancomycin concentration prediction, especially in the population of children with great individual variation. As machine learning methods evolve, the clinical value of the ensemble model will be demonstrated in the clinical practice.

show abstract

Section: Introductionmentioning

confidence: 99%

“…As it is challenging to achieve recommended trough concentrations in children, therapeutic drug monitoring (TDM) in pediatric patients is necessary. 6 …”

Section: Introductionmentioning

confidence: 99%