We consider a stylized, discrete-time model for an Intensive Care Unit (ICU) in which patients’ health conditions change over time with Markovian probabilities. At any point in time, each patient is in one of two possible health stages, one representing a more serious and the other representing a less serious condition in regards to eventual survival. Arriving patients also present in one of two health stages. The ICU has limited bed availability and therefore when a patient arrives at a full ICU, a decision needs to be made as to which patients should be kept in the ICU and which ones should be transferred to general care. Our objective is to make that decision so that the long-run average rate with which patients survive is maximized. We first identify mathematical conditions under which the ICU is always more preferable than general care. Then, under these conditions, which one can assume to hold in practice, we give an almost complete characterization of the optimal patient admission/discharge policy. We find that the optimal policy, in general, depends on the composition of the patients currently in the ICU but our numerical study suggests that even simple policies that do not take such dependence into account, perform quite well. This is joint work with Professor Nilay Tanik Argon and Professor Serhan Ziya at the University of North Carolina at Chapel Hill.
Biography
Dr. Huiyin Ouyang is a postdoctoral researcher in the Department of Industrial Engineering and Management Sciences, Northwestern University. She holds a bachelor degree in Industrial Engineering from Tsinghua University, an M.Sc. and a Ph.D. in Statistics and Operations Research from the University of North Carolina Chapel Hill. Dr. Ouyang is interested in the modeling and analysis of stochastic systems with applications in health care management, and simulation analytics. She is a recipient of George E. Nicholson Award from Department of Statistics and Operations Research at UNC.
Date: 25 January, 2017 (Wednesday)
Time: 11:00 am – 12:30 pm
Venue: Room 7-208, 7/F, Lau Ming Wai Academic Building
City University of Hong Kong
Enquiry: 34428595
