HAS Online Seminar

Health Applications Society Online Seminar Series

Welcome to
the HAS Online Seminar Series! This seminar series welcomes a broad range of healthcare modeling research topics such as healthcare operations, medical decision making, health policy, and health analytics. 

Stay Connected!

Please join our Google Group or subscribe to our Mailing List to receive the latest announcement on the upcoming seminars!
You can also add or download our seminar calendar (Google calendar or iCalendar)
If you have any questions, please feel free to reach us at hasseminarseries@gmail.com !

When: 1-2 pm ET (10-11 am PT) on 4th Friday of each month
Where: Zoom Webinar (Watch Replay Now!

Speaker: Dr. Maria Mayorga, North Carolina State University

Seminar Title: An End-to-end Approach to Improving Population Health Outcomes in Diabetic Retinopathy Through Personalized Screening Strategies
Date and Time: May 26 (Friday), 2023, 1:00-2:00pm ET (10-11am PT)

: Diabetic retinopathy (DR) is a complication from diabetes that affects the eyes. According to the National Eye Institute, early detection, timely treatment, and appropriate follow-up can reduce the risk of severe vision loss from DR by 95%. Yet, DR remains the leading cause of blindness among Americans aged 20-74. In the US, an estimated 899,000 diabetic adults have vision-threatening DR (VTDR) despite it being preventable with timely treatment. VTDR is difficult to catch due to its slow progression and dependence on patients' care seeking behavior. Here I present an overview of a project which takes an end-to-end approach to this problem. Working with a care coordination company, we (1) use medical record and healthcare claims data to predict VTDR risk (2) identify barriers, motivators, and the effects of interventions at the patient and population level, and (3) apply agent-based simulation to guide care coordination intervention choices. I will go into detail on the prediction task, in which we leverage 20+ years of electronic health records to construct and extend ensemble classifiers to identify patients that will develop DR and VTDR within the next year with high recall. In practice this classifier can personalize care coordination to improve utilization and timing without any additional patient actions.

About Speaker: Maria E. Mayorga is a Professor of Personalized Medicine and Director of Graduate Recruitment and Success in the Edward P. Fitts Department of Industrial and Systems Engineering at North Carolina State University. She is currently serving as the Interim Director of the Operations Research Program. In 2019 she received the C.A. Anderson Award for contributions to teaching and was selected as a University Faculty Scholar for her academic leadership and research achievements. In 2021 she was selected as a Provost Faculty Fellow at NC State and was named an INFORMS MIF Fellow.  In 2022 she was named as a Fellow of the Institute of Industrial and Systems Engineers (IISE). Her research interests include predictive models in health care, health care operations management, emergency response, and humanitarian logistics. She has authored over 90 publications and currently serves on the editorial board several IISE and INFORMS journals. 

Past Seminars

  • June 25, 2021: Dr. Alvin Roth, Stanford University, View Recording
      Abstract: Many patients in need of a kidney transplant have a willing but incompatible (or poorly matched) living donor. Kidney exchange programs arrange exchanges among such patient-donor pairs, in cycles and chains of exchange, so each patient receives a compatible kidney. Kidney exchange has become a standard form of transplantation in the United States and a few other countries, in large part because of continued attention to the operational details that arose as obstacles were overcome and new obstacles became relevant. We review some of the key operational issues in the design of successful kidney exchange programs. Kidney exchange has yet to reach its full potential, and the paper further describes some open questions that we hope will continue to attract attention from researchers interested in the operational aspects of dynamic exchange.
    • August 27, 2021: Dr. Edward Kaplan, Yale University, View Recording
        Abstract: This talk reviews some simple analyses that were developed in real time to support local decision-making. We start with Bernoulli models for capping the size of gatherings, and then consider applications of queueing models for assessing hospital ICU capacity. We then discuss using wastewater-based epidemiology to monitor local outbreaks. We also examine gateway and repeat viral testing to prevent coronavirus transmission on campus. Throughout we will illustrate how these analysis were used to inform local decisions.
      • September 24, 2021: Dr. Mark Van Oyen, University of Michigan, View Recording
          Abstract: Improving patient experience requires us to incorporate the perspective of the patient and their personalized care needs and desires. Examples include timely access to a future visit, personalized bed unit assignment, coordinated care, and personalized scheduling to care providers. Past models have usually emphasized system efficiency. It is important to include both efficiency and patient experience. Health systems are increasingly sensitive to patient experience, thereby presenting research opportunities. This talk emphasizes timely patient access/scheduling and either stratified or individualized care models for resource allocation. Recent advances are frequently too limited to allow direct application to healthcare for reasons such as personalization as well as the medical, ethical, organizational, and social dimensions. We present approaches to key problems using models with uncertainty/robustness, machine learning, online learning (e.g., multi-armed bandits), and their integration with optimization. Online methods offer a way to cope with limited historical data and to mitigate unpredictable shocks to the system, such as the COVID-19 pandemic.
        • January 28, 2022: Dr. John R. Birge, The University of Chicago Booth School of Business, View Recording
            Abstract: Many operations researchers have studied various issues concerned with controlling the COVID-19 pandemic (and, hopefully not too soon, future pandemics). This talk will discuss some of the areas in which OR has been applied such as forecasting and pharmaceutical and non-pharmaceutical mitigation measures. The discussion will consider the relative impact of these efforts and lessons for future research.
          • February 25, 2022: Dr. Ebru Bish, The University of Alabama Culverhouse College of Business, View Recording
              Abstract: The COVID-19 pandemic continues to demonstrate the importance of public health screening. My talk will draw upon the body of research that my collaborators and I have conducted in a variety of screening contexts, ranging from newborn screening for genetic disorders to population-level infectious disease screening, including COVID-19. I will discuss the challenges and opportunities for operations researchers.
            • March 25, 2022: Dr. Dávid Papp, North Carolina State University, View Recording
                Abstract: Optimization models and algorithms have played a critical role in radiotherapy treatments of cancer since the advent of intensity modulated radiotherapy in the 1990s, perfecting both the mathematical models and computational methods used in standard radiotherapy modalities. This talk will focus on another family of questions aimed at moving beyond conventional treatment planning: how optimization models can help with the selection, and possible combination, of treatment modalities, and in determining the ideal dose prescriptions for patients through a concept called biologically effective dose.
              • April 22, 2022: Dr. Andrew Li, Carnegie Mellon University, View Recording
                  Abstract: An accurate blood test for early-stage cancer (a “liquid biopsy”) is arguably the most important open problem in oncology, and the race to a solution is tantalizingly close to the finish. In this talk, we will discuss the state of this race as of 2022, particularly how technology and data have enabled progress so far, and how optimization will play a role in reaching the finish line.
                • May 27, 2022: Dr. Oguzhan Alagoz, University of Wisconsin-Madison, View Recording
                    Abstract: This talk describes the use of partially observable Markov decision processes (POMDPs) for personalizing cancer screening. POMDP models can be used to address several controversial open research questions in cancer screening, such as when to start and stop screening and how often to screen. We demonstrate the development and application of a POMDP-based personalized cancer screening policy using breast cancer as an example. In addition, we briefly describe how nonadherence to the screening recommendations, limited screening resources, and existence of chronic conditions could be addressed using the POMDP modeling framework. Finally, we describe successful POMDP applications in other cancers including personalizing colorectal and lung cancer screening.
                  • June 24, 2022: Dr. Vishal Gupta, USC Marshall School of Business, View Recording
                      Abstract: On July 1st, 2020, members of the European Union gradually lifted earlier COVID-19 restrictions on non-essential travel. In response, we designed and deployed “Eva” – a novel reinforcement learning system – across all Greek borders to identify asymptomatic travelers infected with SARS-CoV-2. Eva allocates Greece’s limited testing resources based on demographic characteristics and results from previously tested travelers to (i) limit the influx of new cases and (ii) provide real-time estimates of COVID-19 prevalence to inform border policies. Counterfactual analysis shows that Eva identified 1.85x as many asymptomatic, infected travelers as random surveillance testing, with up to 2-4x as many during peak travel. Moreover, Eva identified approximately 1.25-1.45x as many infected travelers as policies that require similar infrastructure as Eva, but make allocations based on population-level epidemiological metrics (cases/deaths/positivity rates) rather than reinforcement learning. This talk discusses some of the main design decisions behind Eva, the key elements of the reinforcement learning algorithm, and the measured impact of the system in the summer of 2020. 
                    • July 22, 2022: Dr. Carri Chan, Columbia Business School, View Recording
                        Abstract: Rationing of healthcare resources is a challenging decision that policy makers and providers may be forced to make during a pandemic, natural disaster, or mass casualty event. Well-defined guidelines to triage scarce life-saving resources must be designed to promote transparency, trust and consistency. To facilitate buy-in and use during high stress situations, these guidelines need to be interpretable and operational.  We propose a novel data-driven model to compute interpretable triage guidelines based on policies for Markov Decision Process that can be represented as simple sequences of decision trees (tree policies).  In particular, we characterize the properties of optimal tree policies and present an algorithm based on dynamic programming recursions to compute good tree policies.  We utilize this methodology to obtain simple, novel triage guidelines for ventilator allocations for COVID-19 patients, based on real patient data from Montefiore hospitals. We also compare the performance of our guidelines to the official New York State guidelines that were developed in 2015 (well before the COVID-19 pandemic). Our empirical study shows that the number of excess deaths associated with ventilator shortages could be reduced significantly using our policy.  Our work highlights the limitations of the existing official triage guidelines, which need to be adapted specifically to COVID-19 before being successfully deployed. 
                      • August 25, 2022: Dr. Rafael Araos, Universidad del Desarrollo in Santiago, Chile, (Link for recording coming soon)
                          Abstract: During the Covid-19 pandemic, countries needed to develop SARS-CoV-2 surveillance platforms rapidly and leverage already existing administrative datasets to design and execute their responses. Thus, timely access to representative data for decision-making and evaluating interventions emerged as a critical need for managing current and future health threats. Using real-time frequentist and Bayesian approaches for data analysis and modeling and leveraging an electronic, country-wide, prospective cohort, we developed tools for allocating testing resources, guiding isolation measures, and estimating hospitalization needs and vaccine effectiveness. Providing the authorities with scientific evidence to support their decisions was crucial for increasing public trust and engagement. Based on our and others’ experience, we foresee that electronic, administrative cohorts will become invaluable public health tools. To integrate these efforts and maximize funding opportunities, stakeholders should be aware of the available platforms.  
                        • September 23, 2022: Dr. Stefan Scholtes, University of Cambridge, View Recording
                            Abstract: Most papers in empirical healthcare operations are based on observational data. The limitations in terms of making causal inferences are well known and researchers will typically resort to one of a handful of “identification strategies” popularised in the econometrics literature. These methods are based on untestable assumptions and referees will often question their validity. Editors then end up having to make a judgement call whether or not there is reason to believe that the assumptions are valid beyond reasonable doubt. That’s an unsatisfactory state of affairs. Is there an alternative to this “single model” evidence production? I will argue that it can be more informative if researchers present a well-documented journey through different model specifications, including some traditional causal models. This allows them to shed light on the data from different angles and enables readers to form a more robust judgement of the validity of the estimated effect directions and sizes. I will use a recent paper to exemplify this approach. 
                          • Januaray 27, 2023: Dr. Hrayer Aprahamian, Texas A&M University, View Recording
                              Abstract: In this work, we study the problem of designing optimal targeted mass screening of non-uniform populations. Mass screening is an essential tool that is widely utilized in a variety of settings, e.g., preventing infertility through screening programs for sexually transmitted diseases, ensuring a safe blood supply for transfusion, and mitigating the transmission of infectious diseases. The objective of mass screening is to maximize the overall classification accuracy under limited budget. In this work, we address this problem by proposing a proactive optimization-based framework that factors in population heterogeneity, limited budget, different testing schemes, the availability of multiple assays, and imperfect assays. By analyzing the resulting optimization problem, which is a mixed integer nonlinear programming problem, we establish key structural properties which enable us to develop an efficient solution scheme. To achieve this, we take advantage of a reformulation of the problem as a multi-dimensional fractional knapsack problem and identify an efficient globally convergent threshold-style solution scheme that fully characterizes an optimal solution across the entire budget spectrum. Using real-world data, we conduct a geographic-based nationwide case study on targeted COVID-19 screening in the United States. Our results reveal that the identified screening strategies substantially outperform conventional practices by significantly lowering misclassifications while utilizing the same amount of budget. Moreover, our results provide valuable managerial insights with regards to the distribution of testing schemes, assays, and budget across different geographic regions.
                            • February 24, 2023: Dr. Jagpreet Chhatwal, Harvard Medical School, View Recording
                                Abstract: Over the course of past 12 years, Jagpreet Chhatwal’s team has developed multiple mathematical models and tools to inform health policy decision-making, which have been utilized by the White House, the Centers for Disease Control and Prevention (CDC), and the World Health Organization (WHO). In this talk, he will discuss how such collaborations were initiated, progressed, and lessons learned that could help the INFORMS community increase the impact of their work. He will also share his thoughts on how to make operations research and data analytics work more visible to relevant stakeholders, and how the academic community could incentivize junior researchers to pursue high-impact projects.
                              • March 24, 2023: Dr. Pinar Keskinocak, Georgia Tech, View Recording
                                  Infectious diseases continue to affect millions of people around the world every year, despite the progress in science and medicine. This presentation will provide an overview of our research team’s work on modeling various of infectious diseases, such as pandemic flu, cholera, malaria, polio, Guinea worm, and Covid-19. To understand the spread of infectious diseases and evaluate the impact of interventions, we utilized different modeling approaches, such as SEIR or agent-based, depending on the research questions or decision-support needs in practice. Our research results provide insights to decision-makers regarding the impact of combinations of interventions, considering factors such as compliance with public health recommendations, as well as the allocation of scare resources such as vaccines.

                                Seminar Organizers and Advisory Board

                                This seminar series is organized by Sanjay Mehrotra (Northwestern University), Lauren Steimle (Georgia Tech), Qiushi Chen (Pennsylvania State University).
                                The advisory board of the Year 2022 includes Mark Van Oyen (University of Michigan), Maria Mayorga (North Carolina State University), and Timothy Chan (University of Toronto).

                                Special thanks to INFORMS Health Applications Society and all board members for their enormous support!