AI Insight
This study investigated how to optimally select and combine multiple pharmacokinetic models to predict drug dosing, using tacrolimus as the primary case with validation in cefepime and infliximab. Researchers found that combining 3-4 carefully selected models performs as well as larger ensembles, and that the best model combinations depend on what patient data is available. Score-based selection methods proved more reliable across different clinical scenarios than ensembles optimized for specific observation patterns.
Why it matters
This research provides practical guidance for implementing model-informed precision dosing in clinical settings, potentially improving drug therapy individualization while avoiding unnecessary computational complexity. The findings suggest clinicians can achieve accurate dose predictions with smaller, strategically selected model ensembles rather than using all available models.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Model averaging combines the predictions of several population pharmacokinetic models to support model-informed precision dosing, but how to select ensemble models remains unexplored. Using tacrolimus as a case study, we first evaluated all possible ensembles of 27 models in 37 kidney and liver transplant recipients with full pharmacokinetic profiles at occasions 1 and 5 and trough concentrations at occasions 2, 3 and 4. Models were weighted by individual objective function value. Predictive performance for the occasion 5 area under the curve was assessed with individual parameters estimated from the occasion 5 trough concentration or from occasion 1 to 4 observations. Then, seven ensembles, selected a priori from relevance and external evaluation scores or as the best-performing ensembles previously identified, were compared across ten sets of observations, from a single trough concentration to dense sampling. Mean imprecision per ensemble size reached a plateau beyond 3-4 models. The best ensembles depended on the set of observations, comprising three models with the occasion 5 trough concentration and seven or eight models with occasions 1 to 4 observations. Across all sets, the ensemble optimised on the occasion 5 trough concentration was among the most precise, and score-based ensembles remained consistently precise, whereas the ensemble optimised on occasions 1 to 4 generalised poorly. Only a limited sampling strategy at occasion 5 kept imprecision below 20% for all ensembles. The plateau effect generalised to infliximab and cefepime. Ensemble composition matters more than ensemble size. Model averaging should rely on well-chosen ensembles rather than all available models.