Truda, Gianluca and Marais, Patrick (2021) Evaluating warfarin dosing models on multiple datasets with a novel software framework and evolutionary optimisation, Journal of Biomedical Informatics, 113, Elsevier.
Text (Arxiv preprint)
1907.05363(1).pdf - Accepted Version Download (1MB) |
Abstract
Warfarin is an effective preventative treatment for arterial and venous thromboembolism, but requires individualised dosing due to its narrow therapeutic range and high individual variation. Many machine learning techniques have been demonstrated in this domain. This study evaluated the accuracy of the most promising algorithms on the International Warfarin Pharmacogenetics Consortium dataset and a novel clinical dataset of South African patients. Support vectors and linear regression were amongst the top performers in both datasets and performed comparably to recent stacked ensemble approaches, whilst neural networks were one of the worst performers in both datasets. We also introduced genetic programming to automatically optimise model architectures and hyperparameters without human guidance. Remarkably, the generated models were found to match the performance of the best models hand-crafted by human experts. Finally, we present a novel software framework (Warfit-learn) for warfarin dosing research. It leverages the most successful techniques in preprocessing, imputation, and parallel evaluation, with the goal of accelerating research and making results in this domain more reproducible.
Item Type: | Journal article (online only) |
---|---|
Uncontrolled Keywords: | Warfarin, Machine learning, Genetic programming, Python, Supervised learning, Anticoagulant, Pharmacogenetics, Software |
Subjects: | Computing methodologies > Machine learning Applied computing > Life and medical sciences > Health informatics Applied computing > Life and medical sciences > Bioinformatics |
Alternate Locations: | https://doi.org/10.1016/j.jbi.2020.103634, https://www.sciencedirect.com/science/article/pii/S1532046420302628 |
Date Deposited: | 03 Dec 2021 10:51 |
Last Modified: | 03 Dec 2021 10:51 |
URI: | https://pubs.cs.uct.ac.za/id/eprint/1464 |
Actions (login required)
View Item |