ISE Welcomes Michelle Alvarado on 3/3/2017
Integrated Simulation and Optimization for Decision-Making under Uncertainty with Application to Healthcare
Seminar by Dr. Michelle Alvarado, Visiting Assistant Professor
Department of Industrial and Systems Engineering, Texas A&M University
Friday, March 3rd from 11:30am – 12:30pm
210E Baker Systems, 1971 Neil Avenue
Many real applications require decision-making under uncertainty. These decisions occur at discrete points in time, influence future decisions, and have uncertainties that evolve over time. One such challenging decision-making process is the scheduling of outpatient chemotherapy appointments due to the cyclic nature of the treatment process and uncertainty of the appointment duration, acuity levels, and resource availability. I will present an integrated simulation and optimization methodology for the online scheduling and management of outpatient chemotherapy appointments. A discrete event simulation model of the clinic operations evaluates system performance and a mean-risk stochastic programming model schedules patients and resources. In this novel approach, the simulation and optimization models interact and exchange information leading to solutions that adapt to changes in system data. Data from a Texas oncology clinic was analyzed to populate and verify both the simulation and optimization model. Computational results show that the integrated simulation and optimization approach is preferred to using either methodology alone.
Dr. Michelle Alvarado is a Visiting Assistant Professor in the Department of Industrial and Systems Engineering at Texas A&M University (TAMU). She holds a M. Eng and PhD in Industrial Engineering from TAMU. Her expertise is in simulation and stochastic programming. Dr. Alvarado develops models and algorithms for healthcare decision making under uncertainty. She is currently working on problems involving remote health monitoring diabetes and other chronic diseases. In addition, Dr. Alvarado has ongoing work in the development of a health policy model for reducing hospital readmissions using a penalty-incentive model.