Stanford researchers use RL for pediatric echo lab resource allocation

Researchers from Stanford University and Lucile Packard Children's Hospital have developed a simulation model to optimize resource allocation in a pediatric echocardiography lab. They compared on-the-fly patient allocation with reservation-based systems, finding that on-the-fly allocation significantly reduced waiting times. A Dueling Double Deep Q-Network was trained to approximate an optimal dynamic on-the-fly policy, which performed comparably to the best rule-based on-the-fly policy. AI

IMPACT This research demonstrates the application of reinforcement learning for optimizing operational efficiency in healthcare settings.

RANK_REASON The cluster contains an academic paper detailing a simulation study using reinforcement learning for resource allocation. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• Daniele Schiavazzi
• Deep Q-Network
• Dueling Double Deep Q-Network
• gymnasium
• Lucile Packard Children's Hospital
• SimPy
• Stanford University

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →