18 Use of machine learning for dosage individualization of vancomycin in neonates

Le résumé fourni par la source

Introduction High variability in vancomycin exposure in neonates requires advanced individualized dosing regimens. Achieving steady-state trough concentration (C0) and steady-state area-under-curve (AUC0-24) targets are important to optimize treatment. The objective was to evaluate whether machine learning (ML) can be used in clinical practice to predict these treatment targets to calculate optimal individual dosing regimens.Methodology C0 values 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 9 covariates. External validation results showed a 42.2% improvement in prediction accuracy by using the ML model compared to the population pharmacokinetic model. The results of the virtual trial showed that using the ML optimised 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 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 9 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 recommendation of vancomycin in neonates before treatment and dose revision after the first TDM result is obtained, respectively.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.