Reinforcement learning for healthcare operations management: methodological framework, recent developments, and...

Area of Science:

• Data Science
• Operations Research
• Healthcare Systems Engineering

Background:

• Reinforcement learning (RL) is a powerful computational tool for complex decision-making.
• Research on RL for healthcare operations has significantly increased, particularly during the COVID-19 pandemic.
• RL aids in optimizing decisions under uncertainty in healthcare systems.

Purpose of the Study:

• To provide a tutorial on the reinforcement learning framework.
• To review recent advances in RL for healthcare operations management (HOM).
• To analyze current trends and identify future research directions for RL in HOM.

Main Methods:

• Literature review of reinforcement learning applications in healthcare operations.
• Tutorial on RL components, training models, and approximators.
• Analysis of trends and challenges in RL for HOM.

Main Results:

• RL offers a robust framework for optimizing healthcare operations.
• Significant progress has been made in applying RL to various HOM challenges.
• The pandemic highlighted RL's critical role in managing healthcare uncertainty.

Conclusions:

• RL is a rapidly advancing field with substantial potential in healthcare operations management.
• Further research is needed to address existing challenges and explore future directions.
• Interdisciplinary collaboration is key to advancing RL in healthcare.