Population Pharmacokinetic and Pharmacodynamic Models of Propofol in Healthy Volunteers using NONMEM and Machine Learning Methods
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Objectives: The primary objective of this study is to compare model performance of machine learning methods with that of a previous study in which a nonlinear mixed effects model was created using NONMEM? for the pharmacokinetic and pharmacodynamic data for propofol. The secondary objective was to evaluate if a pharmacodynamic model describing the relationship between the dose of propofol and bispectral index (BIS) outperform that describing the relationship between a pharmacokinetic model derived-predicted concentrations of propofol and BIS. Methods: Data were collected during a study involving the infusion of propofol into healthy volunteers. Pharmacokinetic and pharmacodynamic models were constructed using artificial neural networks (ANNs), support vector machines (SVMs), and multi-method ensembles and were compared with the nonlinear mixed effects method as implemented by NONMEM?. Model performance was assessed by goodnessoffit statistics, paired t-tests between predicted and observed values for each model and scatterplots. Results: In pharmacokinetic analysis, ensemble I, the mean of ANN and NONMEM? predictions, achieved minimal error and the highest correlation coefficient. SVM produced the highest error and the lowest correlation coefficient. In pharmacodynamic analysis, ANN exhibited the best performance. An ANN Model describing the relationship between the dose of propofol and BIS was not inferior to an ANN model describing the relationship between predicted concentrations of propofol derived from an ANN pharmacokinetic model and BIS. Conclusions: In pharmacokinetic analysis, ensemble combined with ANN achieved slightly better performance than NONMEM?. The relationship between the dose of propofol and BIS can be predicted without considering pharmacokinetics of propofol.
Abstract
Objectives: The primary objective of this study is to compare model performance of machine learning methods with that of a previous study in which a nonlinear mixed effects model was created using NONMEM? for the pharmacokinetic and pharmacodynamic data for propofol. The secondary objective was to evaluate if a pharmacodynamic model describing the relationship between the dose of propofol and bispectral index (BIS) outperform that describing the relationship between a pharmacokinetic model derived-predicted concentrations of propofol and BIS. Methods: Data were collected during a study involving the infusion of propofol into healthy volunteers. Pharmacokinetic and pharmacodynamic models were constructed using artificial neural networks (ANNs), support vector machines (SVMs), and multi-method ensembles and were compared with the nonlinear mixed effects method as implemented by NONMEM?. Model performance was assessed by goodnessoffit statistics, paired t-tests between predicted and observed values for each model and scatterplots. Results: In pharmacokinetic analysis, ensemble I, the mean of ANN and NONMEM? predictions, achieved minimal error and the highest correlation coefficient. SVM produced the highest error and the lowest correlation coefficient. In pharmacodynamic analysis, ANN exhibited the best performance. An ANN Model describing the relationship between the dose of propofol and BIS was not inferior to an ANN model describing the relationship between predicted concentrations of propofol derived from an ANN pharmacokinetic model and BIS. Conclusions: In pharmacokinetic analysis, ensemble combined with ANN achieved slightly better performance than NONMEM?. The relationship between the dose of propofol and BIS can be predicted without considering pharmacokinetics of propofol.
참고문헌 (28)
- Haidar SH, "Modeling the pharmacokinetics and pharmacodynamics of a unique oral hypoglycemic agent using neural networks", Pharm Res, 19(1), pp.87~91 (2002)
- Gaweda AE, "Pharmacodynamic population analysis in chronic renal failure using artificial neural networks--a comparative study", Neural Netw, 16(5-6), pp.841~845 (2003)
- Brier ME, "Neural network predicted peak and trough gentamicin concentrations", Pharm Res, 12(3), pp.406~412 (1995)
- Chow HH, "Application of neural networks to population pharmacokinetic data analysis", J Pharm Sci, 86(7), pp.840~845 (1997)
- Tolle KM, "Estimating drug", plasma concentration levels by applying neural networks to pharmacokinetic data sets, 2000, pp.2000, 139~151
- Kang SH, "Population Pharmacokinetic and Pharmacodynamic Models of Remifentanil in Healthy Volunteers Using Artificial Neural Network Analysis", Brit J Clin Pharmaco (2007)
- Christianini N, "An Introduction to Support Vector Machines" (2000), Cambridge University Press
- Dreiseitl S, "A comparison of machine learning methods for the diagnsosis of pigmented skin lesions", Journal of Biomedical Informatics, 34, pp.28~36 (2001)
- Guler NF, "Use of support vector machines and neural network in diagnosis of neuromuscular disorders", J Med Syst, 29(3), pp.271~284 (2005)
- Liu HX, "Diagnosing breast cancer based on support vector machines", J Chem Inf Comput Sci, 43(3), pp.900~907 (2003)
- Wei L, "A study on several machine‐learning methods for classification of malignant and benign clustered microcalcification", IEEE Trans Med Imaging, 24(3), pp.371~380 (2005)
- Hornik K, "Multilayer feedforward networks are universal approximators", Neural Networks, 2, pp.359~366 (1989)
- Sharkey A, "On combining artificial neural nets", Connection Science, 8, pp.299~313 (1996)
- Perrone M, "Improving Regression Estimation: Averaging Methods for Variance Reduction with Extensions to General Convex Measure Optimization: Department of Physics", pp.1993
- Han J, "Physical properties and stability of two emulsion formulations of propofol", Int J Pharm, 215(1-2), pp.207~220 (2001)
- Kim KM, "Pharmacokinetics and Pharmacodynamics of Propofol Microemulsion and Lipid Emulsion Following an Intravenous Bolus and Variable Rate Infusion", Anesthesiology (2007)
- Bard JW, "The BIS monitor: a review and technology assessment", AAAN J, 69(6), pp.477~483 (2001)
- Matignon R, "Neural Network Modeling using SAS Enterprise Miner" (2005), Authorhouse
- A tutorial on support vector regression 1998, "Smola AJ", NeuroCOLT2, ~, pp.NC2‐TR‐1998‐030 (1998)
- Arana E, "Validation procedures in radiologic diagnostic models. Neural network and logistic regression", Invest Radiol, 34(10), pp.636~642 (1999)
- Sheiner LB, "Some suggestions for measuring predictive performance", J Pharmacokinet Biopharm, 9, pp.503~512 (1981)
- Martelli PL, "An ENSEMBLE machine learning approach for the prediction of all-alpha membrane proteins", Bioinformatics, 19(1), pp.i205~211 (2003)
- Green M, "Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room", Artif Intell Med, 38, pp.305~318 (2006)
- Burges C, "A Tutorial on Support Vector Machines for Pattern Recognition, In Data Mining and Knowledge discovery 2", Kluwer Academic Publishers
- Support Vectro Machines: Training and Applications, "Osunam E", MIT AI lab, ~ (1997)
- Solomon I, "Applying an artificial neural network to warfarin maintenance dose prediction", Isr Med Assoc J, 6, pp.732~735 (2004)
- Roe DJ, "Estimating parameters in non-linear mixed effects models: a comparison using clinical data in children", Proceedings of the Biopharmaceutical Section, American Statistical Association, pp.318~ (1994)
- Mager DE, "Mapping the dose-effect relationship of orbofiban from sparse data with an artificial neural network", J Pharm Sci, 94, pp.2475~2486 (2005)