INFORMS 2021 Program Book

INFORMS Anaheim 2021

SC01

General Session Chair: Sanyukta Deshpande, University of Illinois at Urbana- Champaign, Champaign, IL, United States 1 - Fair Scheduling of Heterogeneous Customer Populations Justin Mulvany, University of Southern California, Los Angeles, CA, 90007-2558, United States, Ramandeep Randhawa When managing congested service systems, it is common to use priority rules based on some operational criteria. In this paper, we consider the societal implications of such individual-focused priority policies, when individuals are considered as members of broader population groups. We find that optimal resource allocation policies such as the c -rule in scheduling can lead to significant inequity across different population groups. We propose policies that can mitigate this inequity and can even generate completely equitable outcomes across populations with little, or at times, even no additional system cost. Thus, we find that it can be possible to achieve more equitable outcomes while ensuring operational efficiency. 2 - Capacity Management in a Pandemic Incorporating Patient Choices and Evolving Severities Sanyukta Deshpande, University of Illinois at Urbana-Champaign, Champaign, IL, United States, Siddharth Prakash Singh, Lavanya Marla, Alan Scheller-Wolf Motivated by Emergency Department (ED) operations under COVID-19, we study a medical provider that operates both an ED and a clinic in a pandemic. Patients can be COVID or non-COVID, and can belong to one of three severities. All patients enter queues after comparing their own risk perceptions for entering a queue (e.g., wait time, contagion) versus their anticipated benefits: they enter a facility with highest anticipated benefit. The hospital system’s objective is to allocate service capacity across facilities and direct patients to minimize costs from loss of patients due to mortality or impatience. We model the system using a fluid approximation over multiple periods; preliminary results suggest that optimal capacity allocation trades off current high severity patients with preventative care of medium severity patients whose severity could later increase SB46 CC Room 213D In Person: Health Care, Public Health II Contributed Session Chair: Surya Bhaskar Ayyalasomayajula, Oklahoma State University, Stillwater, OK, 74074, United States 1 - Optimal Distribution of Mass Doxycycline Prophylaxis for Plague Control in a Resource-constrained Setting Giovanni S.P. Malloy, Stanford University, Stanford, CA, United States, Margaret L. Brandeau Plague has caused some of humanity’s worst pandemics. Recent outbreaks have in some cases caused substantial numbers of illness and deaths. Plague control measures include insecticide to control flea populations, treatment of infected individuals with doxycycline, and doxycycline prophylaxis for uninfected individuals. We develop an analytical decision rule to determine when mass prophylaxis is cost-effective. We evaluate the decision rule performance using Monte Carlo simulations of a stochastic SEIR model and compare the performance to popular machine learning classification algorithms. 2 - Enabling Mental Healthcare Delivery to Underserved Populations: An Empirical Analysis of the Equity Advancing Effect of Mobile Apps Yi Tang, Carlson School of Management, Minneapolis, MN, United States, Adam Moen, Kingshuk K. Sinha The gap between the supply and demand for mental health care is raising alarms in the U.S. and around the world. Certain populations are suffering more by having significantly less-than-average treatment rates and treatment efficacy. Mobile health technologies such as mobile apps are believed to have the potential to reduce the disparities by breaking the geographical and temporal barriers and by reducing stigma through a psychologically safe environment for people in need. In this study, we document empirical evidences that mobile apps can create capacity in a mental healthcare supply chain so as to reduce the disparities associated with gender, sexual orientation, and race-ethnicity. 3 - Continually Improving Diabetes Education Based on Patients Social Media Interactions Using Text Analytics Surya Bhaskar Ayyalasomayajula, Oklahoma State University, Stillwater, OK, United States, Dursun Delen The pressing need for diabetes patient’s education is addressing their concerns about medicines, insulin injection, and usage of glucose monitoring devices. In this paper, we employ text mining on a popular diabetes support group used by diabetes patients in UK. We find that the expert advice and education based on research and clinical trials, is not sufficient for addressing the diabetes patient concerns. We describe and evaluate a new process and decision support system for diabetes patient concerns identification and prioritization. Our findings

provide insights into how text analytics can improve diabetes education for patients and healthcare providers.

Sunday, 9:45AM=10:45AM

Plenary - 01 CC Ballroom E /Virtual Theater 1 Plenary: Challenges and Opportunities in Crowdsourced Delivery Planning and Operations Plenary Session 1 - Plenary: Challenges and Opportunities in Crowdsourced Delivery Planning and Operations Martin W.P. Savelsbergh, ISyE Georgia Tech, School of Industrial and Systems Engineering, Atlanta, GA, 30332-0205, United States Some of the most visible and impactful societal changes of the last decade are the rapid evolution of the shared and gig economy. Companies at the forefront of these changes are AirBNB and Uber. Their business models have fundamentally changed our society. We focus on one aspect of the evolving gig economy: crowdsourced delivery. How to best deliver goods to consumers has been a logistics question since time immemorial. However, almost all traditional delivery models involved a form of company employees, whether employees of the company manufacturing the goods or whether employees of the company transporting the goods. With the growth of the gig economy, however, a new model not involving company employees has emerged: crowdsourced delivery. The Oxford dictionary defines crowdsourcing as ``the practice of obtaining information or input into a task or project by enlisting the services of a large number of people, either paid or unpaid, typically via the internet’’. Crowdsourced delivery, therefore, involves enlisting individuals to deliver goods and interacting with these individuals using the internet. In crowdsourced delivery, the interaction with the individuals typically occurs through a so-called platform. A prototypical example of such a platform is the one provided by Grubhub, which links restaurants, diners, and individuals willing to deliver meals from a restaurant to a diner. The platform handles everything from facilitating the ordering of meals, to the scheduling of the delivery of the meal, to the associated payments (collecting payments for meals, distributing payments to restaurants, and distributing payments to crowdsourced drivers). Importantly, the crowdsourced drivers are not employed by the platform or by the restaurants. Crowdsourced delivery has fundamentally changed the planning and execution of the delivery of goods: the delivery capacity is no longer under (full) control of the company managing the delivery. This implies that certain aspects of goods delivery that were simple and straightforward in the traditional model are no longer so simple and straightforward. How do you plan when delivery capacity is uncertain? How do you execute when delivery capacity is uncertain? How can you ensure that you meet your service promises to your customers? Does it make sense to rely on (only) crowdsourced delivery capacity? Etc. Etc. These, and many other questions will be raised and partially answered in this presentation. SC01 CC Ballroom A / Virtual Theater 1 INFORMS TutORial Response-guided Dosing in Cancer Radiotherapy Tutorial Session Chair: John Gunnar Carlsson, University of Southern California, Los Angeles, CA, 90089, United States 1 - Response-guided Dosing in Cancer Radiotherapy Archis Ghate, University of Washington, Seattle, WA, 98105, United States The goal in radiotherapy for cancer is to maximize tumor-kill while limiting toxic effects on nearby healthy anatomies. This is attempted via spatial localization of radiation dose, temporal dispersion of radiation dose, and radiation modality selection. The spatial component involves prescribing a high dose to the tumor and putting upper limits on the dose delivered to the healthy anatomies. The radiation intensity profile is then optimized to meet this treatment protocol as closely as possible. This is called fluence-map optimization. The temporal component of the problem involves breaking the total planned dose into several treatment sessions called fractions, which are administered over multiple weeks. This gives the healthy tissue some time to recover between sessions, as it possesses better damage-repair capabilities than the tumor. The key challenge on this temporal side is to choose an optimal number of fractions and the corresponding dosing schedule. This is called the optimal fractionation problem, and has been studied clinically for over a hundred years. Radiotherapy can be Sunday, 11:00AM-12:30PM

15