METHODS: The warfarin maintenance doses for 140 patients were predicted using the dosing tool and compared with the observed maintenance dose. The impact of genotype was assessed by predicting maintenance doses with prior parameter values known to be altered by genetic variability (eg, EC50 for VKORC1 genotype). The prior population was evaluated by fitting the published kinetic-pharmacodynamic model, which underpins the Bayesian tool, to the observed data using NONMEM and comparing the model parameter estimates with published values.
RESULTS: The Bayesian tool produced positively biased dose predictions in the new cohort of patients (mean prediction error [95% confidence interval]; 0.32 mg/d [0.14-0.5]). The bias was only observed in patients requiring ≥7 mg/d. The direction and magnitude of the observed bias was not influenced by genotype. The prior model provided a good fit to our data, which suggests that the bias was not caused by different prior and posterior populations.
CONCLUSIONS: Maintenance doses for patients requiring ≥7 mg/d were overpredicted. The bias was not due to the influence of genotype nor was it related to differences between the prior and posterior populations. There is a need for a more mechanistic model that captures warfarin dose-response relationship at higher warfarin doses.
METHODS: Gentamicin, amikacin and vancomycin are thought to be predominantly excreted by the kidneys. A mixed-effects joint model of the pharmacokinetics of these drugs was developed, with a wide dispersion of weight, age and serum creatinine. A dataset created from 18 sources resulted in 27,338 drug concentrations from 9,901 patients. Body size and composition, maturation and renal function were used to describe differences in drug clearance and volume of distribution.
RESULTS: This study demonstrates that GFR is a predictor of two distinct components of renal elimination clearance: (1) GFR clearance associated with normal GFR and (2) non-GFR clearance not associated with normal GFR. All three drugs had GFR clearance estimated as a drug-specific percentage of normal GFR (gentamicin 39%, amikacin 90% and vancomycin 57%). The total clearance (sum of GFR and non-GFR clearance), standardized to 70 kg total body mass, 176 cm, male, renal function 1, was 5.58 L/h (95% confidence interval [CI] 5.50-5.69) (gentamicin), 7.77 L/h (95% CI 7.26-8.19) (amikacin) and 4.70 L/h (95% CI 4.61-4.80) (vancomycin).
CONCLUSIONS: GFR provides a physiological basis for renal drug elimination. It has been used to distinguish two elimination components. This physiological approach has been applied to describe clearance and volume of distribution from premature neonates to elderly adults with a wide dispersion of size, body composition and renal function. Dose individualization has been implemented using target concentration intervention.
METHODS: A pooled population-pharmacokinetic model was built in NONMEM based on data from 14 different studies in different patient populations. Steady-state exposure was simulated and compared across patient subgroups for two US Food and Drug Administration/European Medicines Agency-approved drug labels and optimised doses were derived.
RESULTS: The final model uses postmenstrual age, weight and serum creatinine as covariates. A 35-year-old, 70-kg patient with a serum creatinine level of 0.83 mg dL-1 (73.4 µmol L-1) has a V1, V2, CL and Q2 of 42.9 L, 41.7 L, 4.10 L h-1 and 3.22 L h-1. Clearance matures with age, reaching 50% of the maximal value (5.31 L h-1 70 kg-1) at 46.4 weeks postmenstrual age then declines with age to 50% at 61.6 years. Current dosing guidelines failed to achieve satisfactory steady-state exposure across patient subgroups. After optimisation, increased doses for the Food and Drug Administration label achieve consistent target attainment with minimal (± 20%) risk of under- and over-dosing across patient subgroups.
CONCLUSIONS: A population model was developed that is useful for further development of age and kidney function-stratified dosing regimens of vancomycin and for individualisation of treatment through therapeutic drug monitoring and Bayesian forecasting.
METHODS: A 'meta-model' with 4894 concentrations from 1631 neonates was built using NONMEM, and Monte Carlo simulations were performed to design an optimal intermittent infusion, aiming to reach a target AUC0-24 of 400 mg·h/L at steady-state in at least 80% of neonates.
RESULTS: A two-compartment model best fitted the data. Current weight, postmenstrual age (PMA) and serum creatinine were the significant covariates for CL. After model validation, simulations showed that a loading dose (25 mg/kg) and a maintenance dose (15 mg/kg q12h if <35 weeks PMA and 15 mg/kg q8h if ≥35 weeks PMA) achieved the AUC0-24 target earlier than a standard 'Blue Book' dosage regimen in >89% of the treated patients.
CONCLUSIONS: The results of a population meta-analysis of vancomycin data have been used to develop a new dosing regimen for neonatal use and to assist in the design of the model-based, multinational European trial, NeoVanc.
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.