Warfarin Dosing

Optimizing warfarin dosing is crucial due to its narrow therapeutic window and significant risk of adverse events from both under- and over-dosing. Current research focuses on developing personalized dosing strategies using machine learning techniques, particularly reinforcement learning algorithms (like Proximal Policy Optimization and contextual bandits) and deep learning models, often incorporating pharmacokinetic/pharmacodynamic (PK/PD) models to simulate patient responses. These approaches aim to improve the accuracy and safety of warfarin treatment by leveraging patient-specific data and learning optimal dosing regimens from observational data or simulations. Successful implementation could significantly reduce adverse events and improve patient outcomes.

Papers

September 20, 2024

OMG-RL:Offline Model-based Guided Reward Learning for Heparin Treatment
Yooseok Lim, Sujee Lee
Reinforcement Learning Model Based Offline Reinforcement Learning Optimal Treatment Reward Function Parameter Complex Reward Function Warfarin Dosing

April 26, 2024

An Explainable Deep Reinforcement Learning Model for Warfarin Maintenance Dosing Using Policy Distillation and Action Forging
Sadjad Anzabi Zadeh, W. Nick Street, Barrett W. Thomas
Deep Reinforcement Learning Proximal Policy Optimization Action Feature Policy Distillation Dosing Model Explainable Deep Reinforcement Learning Warfarin Dosing

February 16, 2024

Optimizing Warfarin Dosing Using Contextual Bandit: An Offline Policy Learning and Evaluation Method
Yong Huang, Charles A. Downs, Amir M. Rahmani
Reinforcement Learning Evaluation Method Based Policy Offline Policy Learning Contextual Bandit Setting Dosing Model Warfarin Dosing

January 18, 2024

Optimizing Medication Decisions for Patients with Atrial Fibrillation through Path Development Network
Tian Xie
Decision Making Patient Friendly Language Atrial Fibrillation Path Development Warfarin Dosing

February 7, 2022

Optimizing Warfarin Dosing using Deep Reinforcement Learning
Sadjad Anzabi Zadeh, W. Nick Street, Barrett W. Thomas
Deep Reinforcement Learning Dosing Model Warfarin Dosing

Warfarin Dosing

Papers

OMG-RL:Offline Model-based Guided Reward Learning for Heparin Treatment

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

Optimizing Warfarin Dosing Using Contextual Bandit: An Offline Policy Learning and Evaluation Method

Optimizing Medication Decisions for Patients with Atrial Fibrillation through Path Development Network

Optimizing Warfarin Dosing using Deep Reinforcement Learning