An Explainable Deep Reinforcement Learning Model for Warfarin Maintenance Dosing Using Policy Distillation and Action Forging

TL;DR

This paper presents an explainable deep reinforcement learning model for warfarin dosing that combines policy distillation and action forging, making the protocol transparent while outperforming existing algorithms.

Contribution

It introduces an explainable reinforcement learning framework for warfarin dosing using policy distillation and action forging, enhancing transparency and performance.

Findings

Model is as understandable as current protocols

Outperforms baseline dosing algorithms

Maintains effectiveness in warfarin maintenance dosing

Abstract

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.