Saved in:
Bibliographic Details
Main Authors: Zadeh, Sadjad Anzabi, Street, W. Nick, Thomas, Barrett W.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.17187
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917651455934464
author Zadeh, Sadjad Anzabi
Street, W. Nick
Thomas, Barrett W.
author_facet Zadeh, Sadjad Anzabi
Street, W. Nick
Thomas, Barrett W.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_17187
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Explainable Deep Reinforcement Learning Model for Warfarin Maintenance Dosing Using Policy Distillation and Action Forging
Zadeh, Sadjad Anzabi
Street, W. Nick
Thomas, Barrett W.
Machine Learning
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.
title An Explainable Deep Reinforcement Learning Model for Warfarin Maintenance Dosing Using Policy Distillation and Action Forging
topic Machine Learning
url https://arxiv.org/abs/2404.17187