Warfarin dose estimation on multiple datasets with automated hyperparameter optimisation and a novel software framework
This work addresses the problem of individualizing warfarin dosing for patients with thromboembolism, but it is incremental as it builds on existing techniques with new datasets and automation.
The study evaluated machine learning algorithms for warfarin dose estimation on two datasets, finding support vectors and linear regression performed comparably to stacked ensembles, while neural networks performed poorly, and introduced genetic programming for automated hyperparameter optimization that matched expert-crafted models.
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.