Applying predictive modeling to improve emergency-room wait times

Kuang Xu (MIT EECS and LIDS)

It is well known that resource pooling (or, equivalently, the use of flexible resources that can serve multiple types of requests) significantly improves the performance of service systems. On the other hand, complete resource pooling often results in higher infrastructure (communication and coordination) costs. This research explores the benefits that can be derived by a limited amount of resource pooling, and the question whether a limited amount of pooled resources can deliver most of the benefits of complete resource pooling. Applications in skill-based call centers, flexible supply chains, and healthcare—including congestion control for emergency departments—are among our main motivations.

This research demonstrates, in the context of some concrete models, that a very small amount of flexibility can be surprisingly powerful in improving performance, both in terms of queueing delay and system capacity. However, to harness the benefits of flexibility, one should carefully architect network topologies, scheduling policies, and how to properly leverage (predictive) information in making dynamic resource allocation decisions. Stochastic models and analytical results provide interesting insights on these challenges.

References and Related Content:
“On the power of (even a little) resource pooling”Stochastic Systems, Issue 1/Volume 2, 2012.

“From theory to practice” – MIT News, August 2013.

“Valuing versatility” – MIT News, May 2013.

MIT Institute for Data, Systems, and Society
Massachusetts Institute of Technology
77 Massachusetts Avenue
Cambridge, MA 02139-4307