Model Ensembling and Machine Learning Approaches to Predict the First Dose of Amoxicillin in Intensive Care

Abstract

A priori model-informed precision dosing (MIPD) recommends an appropriate first dose based solely on the patient's covariates enabling faster target attainment without required concentration measurements. Population pharmacokinetic (PopPK) model ensembling and machine learning (ML) approaches were developed and evaluated to predict a first dose of amoxicillin in intensive care. Following a bibliographic review, a virtual patient population was simulated based on cohorts from four published adult amoxicillin PopPK models. Steady-state trough concentrations were simulated using cohort-specific dosing regimens. As reference methods, weighed model ensembling (WME) and classification tree (CT)-informed ensembling were implemented. Two novel ensembling strategies were developed: regression tree (RT)-informed ensembling, using RT to predict the log individual prediction/observation ratio, and factor analysis of mixed data (FAMD), assigning model weights based on patient similarity to original model cohorts. In parallel, four ML algorithms (support vector machine, k-nearest neighbors, random forest, and XGBoost) were trained to predict the dose achieving target concentrations based on covariates and dosing scheme. All approaches were compared with single-model PopPK dosing, standard dosing, a nomogram, and externally validated using clinical data. Most MIPD methods outperformed standard dosing. On simulated data, ensembling (24%–40% correct predictions) and ML (36%–39%) exceeded single-model approaches (17%–32%). ML-based ensembling eliminates the need for model selection and increases target attainment in both simulated and clinical data. However, the generalizability of such results remains hampered by the lack of high-quality clinical datasets to support model training.