Real-time Elective Admissions Planning for Health Care Providers

Abstract

Efficient management of patient admissions plays a critical role in increasing a hospital's resource utilization and reducing health care costs. We consider the problem of fi nding the best available admission policy for elective hospital admissions under real time constraints. The problem is modeled as a Markov Decision Process (MDP) and we investigate current state-of-the art real time planning methods.

Due to the complexity of the model, traditional mode-based planners are limited in scalability since they require an explicit enumeration of the model dynamics. To overcome this challenge, we apply sample-based planners along with efficient simulation techniques that given an initial start state, generate an action on-demand while avoiding portions of the model that are irrelevant to the start state.

Results show that given reasonable resources, our approach generates improved deci- sions over existing alternatives that fail to scale as model complexity increases. We also propose a parameter tuning method that can be easily and efficiently implemented.