METHODS: C0 were retrieved from a large neonatal vancomycin dataset. Individual estimates of AUC0-24 were obtained from Bayesian post hoc estimation. Various ML algorithms were used for model building to C0 and AUC0-24. An external dataset was used for predictive performance evaluation.
RESULTS: Before starting treatment, C0 can be predicted a priori using the Catboost-based C0-ML model combined with dosing regimen and nine covariates. External validation results showed a 42.5% improvement in prediction accuracy by using the ML model compared with the population pharmacokinetic model. The virtual trial showed that using the ML optimized dose; 80.3% of the virtual neonates achieved the pharmacodynamic target (C0 in the range of 10-20 mg/L), much higher than the international standard dose (37.7-61.5%). Once therapeutic drug monitoring (TDM) measurements (C0) in patients have been obtained, AUC0-24 can be further predicted using the Catboost-based AUC-ML model combined with C0 and nine covariates. External validation results showed that the AUC-ML model can achieve an prediction accuracy of 80.3%.
CONCLUSION: C0-based and AUC0-24-based ML models were developed accurately and precisely. These can be used for individual dose recommendations of vancomycin in neonates before treatment and dose revision after the first TDM result is obtained, respectively.
OBJECTIVE: The aim of this proof-of-concept study was to evaluate whether combining population pharmacokinetic and machine learning approaches could provide a more accurate prediction of the clearance of renally eliminated drugs in individual neonates.
METHODS: Six drugs that are primarily eliminated by the kidneys were selected (vancomycin, latamoxef, cefepime, azlocillin, ceftazidime, and amoxicillin) as 'proof of concept' compounds. Individual estimates of clearance obtained from population pharmacokinetic models were used as reference clearances, and diverse machine learning methods and nested cross-validation were adopted and evaluated against these reference clearances. The predictive performance of these combined methods was compared with the performance of two other predictive methods: a covariate-based maturation model and a postmenstrual age and body weight scaling model. Relative error was used to evaluate the different methods.
RESULTS: The extra tree regressor was selected as the best-fit machine learning method. Using the combined method, more than 95% of predictions for all six drugs had a relative error of < 50% and the mean relative error was reduced by an average of 44.3% and 71.3% compared with the other two predictive methods.
CONCLUSION: A combined population pharmacokinetic and machine learning approach provided improved predictions of individual clearances of renally cleared drugs in neonates. For a new patient treated in clinical practice, individual clearance can be predicted a priori using our model code combined with demographic data.