2015 Informs Annual Meeting

MB37

INFORMS Philadelphia – 2015

3 - Introducing Pro Bono Analytics David Hunt, Manager, Oliver Wyman, One University Square, Suite 100, Princeton, NJ, 08540, United States of America, David.Hunt@oliverwyman.com, Michael P. Johnson Pro Bono Analytics is a new initiative within INFORMS to match INFORMS members willing to volunteer their operations research and advanced analytical skills with non-profit organizations working in underserved and developing communities. This presentation will provide an overview of the Pro Bono Analytics program, describe how OR/analytics professionals can make a difference, and show how you can become a Pro Bono Analytics volunteer. 4 - Predicting Areas of Low HPV Vaccination Coverage to Target Vaccination Promotion Efforts Brittany Green, University of Cincinnati, Carl H. Linder School of Business, 2925 Campus Green Dr., Cincinnati, OH, 45221, United States of America, brittanydianeg@gmail.com, Josh Haupt, Louis Luangkesorn The Jewish Healthcare Foundation is trying to promote Human Papillomavirus (HPV) vaccination efforts in southwestern Pennsylvania. HPV is a sexually transmitted disease which can be prevented with a three dose vaccine. However, vaccination rates among adolescents is short of target rates. We develop a predictive model of vaccination coverage based on the National Immunization Survey. We then apply this model to census data to identify zip codes to target for HPV vaccination promotion programs. MB37 37-Room 414, Marriott Health Care Modeling and Optimization V Contributed Session Chair: Karti Puranam, Assistant Professor, La Salle University, 1900 W Olney Ave, Philadelphia, PA, 19141, United States of America, puranam@lasalle.edu 1 - Differential Impact of Health it on Duplicate Testing Sezgin Ayabakan, Assistant Professor, University of Baltimore, 1420 N Charles St, Baltimore, MD, 21201, United States of America, sayabakan@ubalt.edu, Indranil Bardhan, Zhiqiang Zheng, Kirk Kirksey We investigate and compare the impact of intra- and inter- hospital information sharing technologies on duplicate radiology and laboratory tests for Congestive Heart Failure patients. We use a comprehensive dataset of 39,600+ visits across outpatient clinics of 68 hospitals in North Texas from 2005 to 2012 in our quasi- experimental approach. Our results support the need for implementation of health information exchanges as a potential solution to reduce incidences of duplicate tests. 2 - Manpower Planning for Health Care Services Utpal Bhattacharya, Dr., Indian Institute of Management Indore, Prabandh Sikhar, Indore, MP, 453556, India, utpalb@iimidr.ac.in The article Manpower planning for health care services “ introduces various key issues on management of manpower system for health care services. The motivation in this article is to make a study on how to choose proper type of manpower as and when required, upgrading the existing people, managing the attrition rate by using various measures, giving promotions to the employees, in order to keep healthy atmosphere in the organization. 3 - Optimal Block Scheduling for the Operating Room Suite: From Tactical to Strategic Planning Thomas Sexton, Professor, Stony Brook University, College of Business, Stony Brook, NY, 11794-3775, United States of America, thomas.sexton@stonybrook.edu, Kenneth Rosenfeld, Melissa Dolan, Kelly Stickle, Herbert Lewis We present a multicriteria nonlinear optimization model for allocating operating room time among surgical services in a major academic medical center. The model incorporates three objectives: the hospital’s financial success; its overall mission; and its contribution to community needs. These factors elevate OR scheduling from the tactical realm, with its focus on utilization, to the strategic realm, in which the OR suite is viewed as central to the hospital’s higher-level objectives. 4 - Can Obesity be Completely Eradicated by Physical Activity?

5 - An Ordering Heuristic for RBCS under Multiple Independent Sources of Supply Karti Puranam, Assistant Professor, La Salle University, 1900 W Olney Ave, Philadelphia, PA, 19141, United States of America, puranam@lasalle.edu, Marilyn Lucas, David Novak We introduce a multi-period, perishable inventory model under two independent sources of supply, where blood is randomly transferred from hospitals to a large blood bank. We formulate a dynamic program to solve the multi-period cost minimization problem. We compare our results to the ordering policy that was followed in practice.

MB38 38-Room 415, Marriott Applied Probability II Contributed Session

Chair: Chiel Van Oosterom, PhD Student, Eindhoven University of Technology, P.O. Box 513, Eindhoven, 5600MB, Netherlands, c.d.v.oosterom@tue.nl 1 - Statistical Inference Theory using Truncated Statistics with Applications Byung Rae Cho, Professor, Clemson University, 152 Freeman Hall, Clemson, SC, 29634, United States of America, bcho@clemson.edu, Russell Krenek There are many production situations where specification limits on a process are implemented externally, and the end product is typically reworked or scrapped if its performance does not fall in the tolerance range. As such, the actual distribution after inspection becomes truncated. The purpose of this presentation is to develop a set of hypothesis testing procedures under this truncated environment and explore application areas. 2 - Development of Convolutions for Industrial and Service Processes Russell Krenek, Graduate Student, Clemson University, 129 Freeman Hall, Clemson, SC, 29634, United States of America, rkrenek@g.clemson.edu, Byung Rae Cho Understanding truncated random variables and their roles in production inspection processes is a key to modern industry, as this type of review arises in many engineering applications. It is important to note that these production inspection processes require the convolution of truncated distributions due to multiple production stages. This paper focuses on the development of the convolutions resulting from truncated normal and truncated skew normal random variables, and their applications. 3 - Condition-based Repair Prioritization in Repairable Inventory Supply Chains Chiel Van Oosterom, PhD Student, Eindhoven University of Technology, P.O. Box 513, Eindhoven, 5600MB, Netherlands, c.d.v.oosterom@tue.nl, Geert-jan Van Houtum We propose a model for exploiting condition information to dynamically prioritize repairs in a capacitated repair shop. The repair shop supports a system with a number of different repairable components. The system is down whenever a component fails and no ready-for-use spare part is available for that component. The objective in prioritizing repairs is to maximize the long-run availability of the system. 4 - Calendar-based Age Replacement Policy with Dependent Renewal Cycles Maliheh Aramon Bajestani, University of Toronto, Unit 804, 141 We introduce an age-based replacement policy in which the preventive replacements are restricted to specific calendar times. This policy is logistically applicable in industries, having large and geographically diverse populations of deteriorating assets with different installation times. Using the theory of Markov chains with general state space and a suitably defined ergodic measure, we analyze the policy, minimizing the long-run expected cost per time unit. Davisville Ave, Toronto, ON, M4S 1G7, Canada, maramon@mie.utoronto.ca, Dragan Banjevic

He Huang, Beijing Institute of Technology, Beijing, 100081, China, huanghe@bit.edu.cn, Yaohui Pan, Yahong Chen, Tianmei Wang, Zhijun Yan

The inter-person dynamics of obesity epidemic have rarely been revealed. We develop a belief decision model to simulate the spreading of two competing obesity-related behaviors from people to people. Results show that both behaviors have thresholds, below which obesity will be quickly eradicated, and that social discrimination may play contrary effects in different cases.

184