학술논문
A Hybrid Model Associating Population Pharmacokinetics with Machine Learning: A Case Study with Iohexol Clearance Estimation.
Document Type
Academic Journal
Author
Destere A; Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 rue du Pr Descottes, 87000, Limoges, France.; Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France.; Department of Pharmacology and Toxicology, University Hospital of Nice, Nice, France.; Marquet P; Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 rue du Pr Descottes, 87000, Limoges, France.; Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France.; Gandonnière CS; Médecine Intensive Réanimation, INSERM CIC 1415, CRICS-TriggerSep Research Network, CHRU de Tours, Tours, France.; Åsberg A; Department of Transplantation Medicine, Oslo University Hospital Rikshospitalet, Oslo, Norway.; Department of Pharmacy, University of Oslo, Oslo, Norway.; Loustaud-Ratti V; Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 rue du Pr Descottes, 87000, Limoges, France.; Department of Hepato-Gastro-Enterology, University Hospital of Limoges, Limoges, France.; Carrier P; Department of Hepato-Gastro-Enterology, University Hospital of Limoges, Limoges, France.; Ehrmann S; Médecine Intensive Réanimation, INSERM CIC 1415, CRICS-TriggerSep Research Network, CHRU de Tours, Tours, France.; Centre d'Etude des Pathologies Respiratoires INSERM U1100, Faculté de Médecine, Université de Tours, Tours, France.; Guellec CB; Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 rue du Pr Descottes, 87000, Limoges, France.; Premaud A; Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 rue du Pr Descottes, 87000, Limoges, France.; Woillard JB; Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 rue du Pr Descottes, 87000, Limoges, France. jean-baptiste.woillard@unilim.fr.; Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France. jean-baptiste.woillard@unilim.fr.
Source
Publisher: Country of Publication: Switzerland NLM ID: 7606849 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1179-1926 (Electronic) Linking ISSN: 03125963 NLM ISO Abbreviation: Clin Pharmacokinet Subsets: MEDLINE
Subject
Language
English
Abstract
Background: Maximum a posteriori Bayesian estimation (MAP-BE) based on a limited sampling strategy and a population pharmacokinetic model is frequently used to estimate pharmacokinetic parameters in individuals, however with some uncertainty (bias). Recent works have shown that the performance in individual estimation or pharmacokinetic parameters can be improved by combining population pharmacokinetic and machine learning algorithms.
Objective: The objective of this work was to investigate the use of a hybrid machine learning/population pharmacokinetic approach to improve individual iohexol clearance estimation.
Methods: The reference iohexol clearance values were derived from 500 simulated profiles (samples collected between 0.1 and 24.7 h) using a population pharmacokinetic model we recently developed in Monolix and obtained using all the concentration timepoints available. Xgboost and glmnet algorithms able to predict the error of MAP-BE clearance estimates based on a limited sampling strategy (0.1 h, 1 h, and 9 h) versus reference values were developed in a training subset (75%) and were evaluated in a testing subset (25%) and in 36 real patients.
Results: The MAP-BE limited sampling strategy estimated clearance was corrected by the machine learning predicted error leading to a decrease in root mean squared error by 29% and 24%, and in the percentage of profiles with the mean prediction error out of the ± 20% bias by 60% and 40% in the external validation dataset for the glmnet and Xgboost machine learning algorithms, respectively. These results were attributable to a decrease in the eta-shrinkage (shrinkage for a MAP-BE limited sampling strategy = 32.4%, glmnet = 18.2%, and Xgboost = 19.4% in the external dataset).
Conclusions: In conclusion, this hybrid algorithm represents a significant improvement in comparison to MAP-BE estimation alone.
(© 2022. The Author(s), under exclusive licence to Springer Nature Switzerland AG.)
Objective: The objective of this work was to investigate the use of a hybrid machine learning/population pharmacokinetic approach to improve individual iohexol clearance estimation.
Methods: The reference iohexol clearance values were derived from 500 simulated profiles (samples collected between 0.1 and 24.7 h) using a population pharmacokinetic model we recently developed in Monolix and obtained using all the concentration timepoints available. Xgboost and glmnet algorithms able to predict the error of MAP-BE clearance estimates based on a limited sampling strategy (0.1 h, 1 h, and 9 h) versus reference values were developed in a training subset (75%) and were evaluated in a testing subset (25%) and in 36 real patients.
Results: The MAP-BE limited sampling strategy estimated clearance was corrected by the machine learning predicted error leading to a decrease in root mean squared error by 29% and 24%, and in the percentage of profiles with the mean prediction error out of the ± 20% bias by 60% and 40% in the external validation dataset for the glmnet and Xgboost machine learning algorithms, respectively. These results were attributable to a decrease in the eta-shrinkage (shrinkage for a MAP-BE limited sampling strategy = 32.4%, glmnet = 18.2%, and Xgboost = 19.4% in the external dataset).
Conclusions: In conclusion, this hybrid algorithm represents a significant improvement in comparison to MAP-BE estimation alone.
(© 2022. The Author(s), under exclusive licence to Springer Nature Switzerland AG.)