Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction
Background Population pharmacokinetic evaluations have been widely used in neonatal pharmacokinetic studies, while machine learning has become a popular approach to solving complex problems in the current era of big data. Objective The aim of this proof-of-concept study was to evaluate whether combi...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Published: |
Adis
2021
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/34712/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.um.eprints.34712 |
|---|---|
| record_format |
eprints |
| spelling |
my.um.eprints.347122022-07-22T06:37:58Z http://eprints.um.edu.my/34712/ Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction Tang, Bo-Hao Guan, Zheng Allegaert, Karel Wu, Yue-E. Manolis, Efthymios Leroux, Stephanie Yao, Bu-Fan Shi, Hai-Yan Li, Xiao Huang, Xin Wang, Wen-Qi Shen, A. -Dong Wang, Xiao-Ling Wang, Tian-You Kou, Chen Xu, Hai-Yan Zhou, Yue Zheng, Yi Hao, Guo-Xiang Xu, Bao-Ping Thomson, Alison H. Capparelli, Edmund V. Biran, Valerie Simon, Nicolas Meibohm, Bernd Lo, Yoke-Lin Marques, Remedios Peris, Jose-Esteban Lutsar, Irja Saito, Jumpei Burggraaf, Jacobus Jacqz-Aigrain, Evelyne van den Anker, John Zhao, Wei R Medicine (General) Background Population pharmacokinetic evaluations have been widely used in neonatal pharmacokinetic studies, while machine learning has become a popular approach to solving complex problems in the current era of big data. Objective The aim of this proof-of-concept study was to evaluate whether combining population pharmacokinetic and machine learning approaches could provide a more accurate prediction of the clearance of renally eliminated drugs in individual neonates. Methods Six drugs that are primarily eliminated by the kidneys were selected (vancomycin, latamoxef, cefepime, azlocillin, ceftazidime, and amoxicillin) as `proof of concept' compounds. Individual estimates of clearance obtained from population pharmacokinetic models were used as reference clearances, and diverse machine learning methods and nested cross-validation were adopted and evaluated against these reference clearances. The predictive performance of these combined methods was compared with the performance of two other predictive methods: a covariate-based maturation model and a postmenstrual age and body weight scaling model. Relative error was used to evaluate the different methods. Results The extra tree regressor was selected as the best-fit machine learning method. Using the combined method, more than 95% of predictions for all six drugs had a relative error of < 50% and the mean relative error was reduced by an average of 44.3% and 71.3% compared with the other two predictive methods. Conclusion A combined population pharmacokinetic and machine learning approach provided improved predictions of individual clearances of renally cleared drugs in neonates. For a new patient treated in clinical practice, individual clearance can be predicted a priori using our model code combined with demographic data. Adis 2021-11 Article PeerReviewed Tang, Bo-Hao and Guan, Zheng and Allegaert, Karel and Wu, Yue-E. and Manolis, Efthymios and Leroux, Stephanie and Yao, Bu-Fan and Shi, Hai-Yan and Li, Xiao and Huang, Xin and Wang, Wen-Qi and Shen, A. -Dong and Wang, Xiao-Ling and Wang, Tian-You and Kou, Chen and Xu, Hai-Yan and Zhou, Yue and Zheng, Yi and Hao, Guo-Xiang and Xu, Bao-Ping and Thomson, Alison H. and Capparelli, Edmund V. and Biran, Valerie and Simon, Nicolas and Meibohm, Bernd and Lo, Yoke-Lin and Marques, Remedios and Peris, Jose-Esteban and Lutsar, Irja and Saito, Jumpei and Burggraaf, Jacobus and Jacqz-Aigrain, Evelyne and van den Anker, John and Zhao, Wei (2021) Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction. Clinical Pharmacokinetics, 60 (11). pp. 1435-1448. ISSN 0312-5963, DOI https://doi.org/10.1007/s40262-021-01033-x <https://doi.org/10.1007/s40262-021-01033-x>. 10.1007/s40262-021-01033-x |
| institution |
Universiti Malaya |
| building |
UM Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Malaya |
| content_source |
UM Research Repository |
| url_provider |
http://eprints.um.edu.my/ |
| topic |
R Medicine (General) |
| spellingShingle |
R Medicine (General) Tang, Bo-Hao Guan, Zheng Allegaert, Karel Wu, Yue-E. Manolis, Efthymios Leroux, Stephanie Yao, Bu-Fan Shi, Hai-Yan Li, Xiao Huang, Xin Wang, Wen-Qi Shen, A. -Dong Wang, Xiao-Ling Wang, Tian-You Kou, Chen Xu, Hai-Yan Zhou, Yue Zheng, Yi Hao, Guo-Xiang Xu, Bao-Ping Thomson, Alison H. Capparelli, Edmund V. Biran, Valerie Simon, Nicolas Meibohm, Bernd Lo, Yoke-Lin Marques, Remedios Peris, Jose-Esteban Lutsar, Irja Saito, Jumpei Burggraaf, Jacobus Jacqz-Aigrain, Evelyne van den Anker, John Zhao, Wei Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction |
| description |
Background Population pharmacokinetic evaluations have been widely used in neonatal pharmacokinetic studies, while machine learning has become a popular approach to solving complex problems in the current era of big data. Objective The aim of this proof-of-concept study was to evaluate whether combining population pharmacokinetic and machine learning approaches could provide a more accurate prediction of the clearance of renally eliminated drugs in individual neonates. Methods Six drugs that are primarily eliminated by the kidneys were selected (vancomycin, latamoxef, cefepime, azlocillin, ceftazidime, and amoxicillin) as `proof of concept' compounds. Individual estimates of clearance obtained from population pharmacokinetic models were used as reference clearances, and diverse machine learning methods and nested cross-validation were adopted and evaluated against these reference clearances. The predictive performance of these combined methods was compared with the performance of two other predictive methods: a covariate-based maturation model and a postmenstrual age and body weight scaling model. Relative error was used to evaluate the different methods. Results The extra tree regressor was selected as the best-fit machine learning method. Using the combined method, more than 95% of predictions for all six drugs had a relative error of < 50% and the mean relative error was reduced by an average of 44.3% and 71.3% compared with the other two predictive methods. Conclusion A combined population pharmacokinetic and machine learning approach provided improved predictions of individual clearances of renally cleared drugs in neonates. For a new patient treated in clinical practice, individual clearance can be predicted a priori using our model code combined with demographic data. |
| format |
Article |
| author |
Tang, Bo-Hao Guan, Zheng Allegaert, Karel Wu, Yue-E. Manolis, Efthymios Leroux, Stephanie Yao, Bu-Fan Shi, Hai-Yan Li, Xiao Huang, Xin Wang, Wen-Qi Shen, A. -Dong Wang, Xiao-Ling Wang, Tian-You Kou, Chen Xu, Hai-Yan Zhou, Yue Zheng, Yi Hao, Guo-Xiang Xu, Bao-Ping Thomson, Alison H. Capparelli, Edmund V. Biran, Valerie Simon, Nicolas Meibohm, Bernd Lo, Yoke-Lin Marques, Remedios Peris, Jose-Esteban Lutsar, Irja Saito, Jumpei Burggraaf, Jacobus Jacqz-Aigrain, Evelyne van den Anker, John Zhao, Wei |
| author_facet |
Tang, Bo-Hao Guan, Zheng Allegaert, Karel Wu, Yue-E. Manolis, Efthymios Leroux, Stephanie Yao, Bu-Fan Shi, Hai-Yan Li, Xiao Huang, Xin Wang, Wen-Qi Shen, A. -Dong Wang, Xiao-Ling Wang, Tian-You Kou, Chen Xu, Hai-Yan Zhou, Yue Zheng, Yi Hao, Guo-Xiang Xu, Bao-Ping Thomson, Alison H. Capparelli, Edmund V. Biran, Valerie Simon, Nicolas Meibohm, Bernd Lo, Yoke-Lin Marques, Remedios Peris, Jose-Esteban Lutsar, Irja Saito, Jumpei Burggraaf, Jacobus Jacqz-Aigrain, Evelyne van den Anker, John Zhao, Wei |
| author_sort |
Tang, Bo-Hao |
| title |
Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction |
| title_short |
Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction |
| title_full |
Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction |
| title_fullStr |
Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction |
| title_full_unstemmed |
Drug clearance in neonates: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction |
| title_sort |
drug clearance in neonates: a combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction |
| publisher |
Adis |
| publishDate |
2021 |
| url |
http://eprints.um.edu.my/34712/ |
| _version_ |
1739828489935126528 |
| score |
13.211869 |