An Explainable Deep Reinforcement Learning Model for Warfarin Maintenance Dosing Using Policy Distillation and Action Forging
This provides an explainable dosing protocol for clinicians managing warfarin therapy, though it is incremental as it builds on existing methods for interpretability.
The paper tackled the problem of black-box deep reinforcement learning models in warfarin maintenance dosing by proposing an explainable protocol using policy distillation and action forging, resulting in a model that is as easy to understand and deploy as current protocols and outperforms baseline dosing algorithms.
Deep Reinforcement Learning is an effective tool for drug dosing for chronic condition management. However, the final protocol is generally a black box without any justification for its prescribed doses. This paper addresses this issue by proposing an explainable dosing protocol for warfarin using a Proximal Policy Optimization method combined with Policy Distillation. We introduce Action Forging as an effective tool to achieve explainability. Our focus is on the maintenance dosing protocol. Results show that the final model is as easy to understand and deploy as the current dosing protocols and outperforms the baseline dosing algorithms.