Exploring Ensemble Selection for Model Averaging in Model-informed Precision Dosing: A Tacrolimus Case Study Extended to Cefepime and InfliximabExploring Ensemble Selection for Model Averaging in Model-informed Precision Dosing: A Tacrolimus Case Study Extended to Cefepime and Infliximab
- 1Univ Rennes, Inserm, EHESP, Irset (Institut de recherche en sante, environnement et travail), UMR_S 1085, F-35000 Rennes, France and FHU SUPORT, F-35000, Rennes
Abstract
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.
Related
- Relevance‐Based Score for MIPD Model Selection: Systematic Review and External Evaluation of popPK Tacrolimus Models in Adult Transplant Recipients
- Exploring self-supervised deep sparse autoencoders for robust feature selection in radiomics analysis
- Intraarticular Injection of Infliximab-Loaded Thermosensitive Hydrogel Alleviates Pain and Protects Cartilage in Rheumatoid Arthritis [Retraction].
- Infliximab Monotherapy as First-Line Treatment for Hepatic, Splenic, and Pulmonary Sarcoidosis in a Patient With High Cardiometabolic Risk.
- Superior sagittal sinus thrombosis with intracranial hemorrhage in a patient on infliximab: a case report.
BibTeX
@misc{baroudi2026exploring,
title = {{Exploring Ensemble Selection for Model Averaging in Model-informed Precision Dosing: A Tacrolimus Case Study Extended to Cefepime and InfliximabExploring Ensemble Selection for Model Averaging in Model-informed Precision Dosing: A Tacrolimus Case Study Extended to Cefepime and Infliximab}},
author = {S. Baroudi and B. Franck and J.-B. Woillard and A. Destere and E. Comets and F. LEMAITRE},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.26363867},
url = {https://www.medrxiv.org/content/10.64898/2026.09.24.26363867v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Exploring Ensemble Selection for Model Averaging in Model-informed Precision Dosing: A Tacrolimus Case Study Extended to Cefepime and InfliximabExploring Ensemble Selection for Model Averaging in Model-informed Precision Dosing: A Tacrolimus Case Study Extended to Cefepime and Infliximab
AU - S. Baroudi
AU - B. Franck
AU - J.-B. Woillard
AU - A. Destere
AU - E. Comets
AU - F. LEMAITRE
PY - 2026
DA - 2026/09/24
PB - medRxiv
DO - 10.64898/2026.09.24.26363867
UR - https://www.medrxiv.org/content/10.64898/2026.09.24.26363867v1
AB - 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.
ER -