Chan, Alexander, Peck, Richard 
ORCID: 0000-0003-1018-9655, Gibbs, Megan and van der Schaar, Mihaela
(2023)
Synthetic Model Combination: A new machine learning method for pharmacometric model ensembling.
CPT: pharmacometrics & systems pharmacology, 12 (7).
pp. 953-962.
Abstract
When aiming to make predictions over targets in the pharmacological setting, a data-focussed approach aims to learn models based on a collection of labelled examples. Unfortunately, data sharing is not always possible, and this can result in many different models trained on disparate populations, leading to the natural question of how best to use and combine them when making a new prediction. Previous work has focused on global model selection or ensembling, with the result of a single final model across the feature space. Machine learning models perform notoriously poorly on data outside their training domain however due to a problem known as covariate shift, and so we argue that when ensembling models the weightings for individual instances must reflect their respective domains - in other words models that are more likely to have seen information on that instance should have more attention paid to them. We introduce a method for such an instance-wise ensembling of models called Synthetic Model Combination (SMC), including a novel representation learning step for handling sparse high-dimensional domains. We demonstrate the use of SMC on an example with dosing predictions for Vancomycin, although emphasise the applicability of the method to any scenario involving the use of multiple models.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Humans, Learning, Algorithms, Machine Learning |
| Divisions: | Faculty of Health and Life Sciences Faculty of Health and Life Sciences > Institute of Systems, Molecular and Integrative Biology |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 21 Apr 2023 09:11 |
| Last Modified: | 21 Jul 2023 07:13 |
| DOI: | 10.1002/psp4.12965 |
| Open Access URL: | https://doi.org/10.1002/psp4.12965 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3169823 |
Dimensions
Dimensions
