The Institute for Pandemics (IfP) invites University of Toronto graduate students to learn about pandemic research in different disciplines. Two IfP members will give presentations that describe the research involved in their recently awarded IfP catalyst grants.
Interpretable surrogate modelling for agent-based simulations to better inform COVID-19 decision-making
SARS-CoV-2 (COVID-19) was officially declared a pandemic in March 2020 and infections spread rapidly around the world. Researchers, healthcare practitioners, and government officials recognized the need for effective mitigation strategies to reduce the incidence of infection. The Medical Operations Research Lab’s Pandemic Outbreak Planner (morPOP) is an agent-based simulation (ABS) model utilized to illustrate the potential outcomes of COVID-19 mitigation strategies at various compliance rates. Despite numerous applications of ABSs in the peer-reviewed literature, important gaps remain, with the high dimensional nature of these models resulting in high computational complexity and prohibitively long run times. Applications of surrogate machine learning (ML) have been implemented to overcome these challenges and demonstrated the ability to accurately predict ABS outputs while reducing overall run time.
This study aims to develop an interpretable ML surrogate model for the morPOP agent-based simulation model. Four model architectures are proposed – logistic regression, eXtreme Gradient Boosted trees, Support Vector Machines, and Artificial Neural Networks. Model performance will be evaluated using F1 Score and sensitivity and specificity metrics. The goal of the ML model is to accurately predict the number of cases resulting from implementing a specific mitigation strategy at a range of compliance rates. This information can be used by decision-makers about the potential efficacy of these strategies and therefore inform the selection of the optimal mitigation methods. Due to its intended use in public health decision-making, the focus is on maintaining interpretability and efficiency in the ML model while achieving high accuracy.
Pandemic impact statements: Addressing workplace inequities to facilitate an equitable recovery
The COVID-19 pandemic exposed and intensified workplace inequalities, disproportionately affecting women and racialized workers. Organizations have widely adopted pandemic impact statements to contextualize employee performance, aiming to foster fairer evaluations and a more equitable pandemic recovery. However, the effectiveness of these statements in addressing inequities remains uncertain. One concern is that these statements might draw attention to caregiving roles and thus reinforce stereotypes that harm women and racialized workers in caregiver roles. Additionally, employees from marginalized groups may be less likely to use these statements, potentially amplifying—rather than ameliorating—existing inequities. This research assesses the effect of pandemic impact statements on workplace inequities and provides evidence-based best practices for organizations considering their use. We seek to understand if these statements contribute to an equitable recovery or exacerbate disparities and how decision-makers can implement more equitable employee performance evaluations during future pandemics.
About the presenters
Dionne Aleman is an Associate Professor in the Department of Mechanical and Industrial Engineering at the University of Toronto, and holds appointments in the Institute of Health Policy, Management and Evaluation (U of T); the Institute for Pandemics (U of T); and the UHN Techna Institute. She is also co-Lead for the Joint Translational Centre for Digital Health, a collaboration between the University of Toronto and the University of Manchester. Dr. Aleman received her PhD in Industrial and Systems Engineering from the University of Florida (2007), MSc from the University of Florida (2006), and BSc from the University of Florida (2003).
Dr. Aleman’s research focuses on the application of operations research to medical and healthcare systems to improve the quality, timeliness, and efficiency of care. This research includes using optimization, simulation, machine learning, and graph theory to predict and mitigate the spread of pandemic diseases in urban populations, to design and validate radiation therapy treatment plans, to improve hospital surgical scheduling, and to optimize organ transplant matches and multi-person chains. Dr. Aleman has held grants from NSERC, CFI, ORF, and NSF for her research. She is a two-term past President of the Canadian Operational Research Society (CORS). Within the Institute for Operations Research and Management Science (INFORMS), she currently serves on the Committee for Teaching and Learning, and has previously served as Chair of the Health Applications Society (HAS), President of the Public Sector OR Section (PSOR), President of the Junior Faculty Interest Group (JFIG), Chair of INFORM-ED, and TutORials co-chair. Dr. Aleman is also a Topical Editor for the Wiley Encyclopedia of Operations Research and Management Science, Associate Editor for IIE Transactions on Healthcare Systems Engineering, Associate Editor for OMEGA, Associate Editor for the International Journal of Biomedical Data Mining, and Editorial Board Member of Operations Research in Health Care.
András Tilcsik holds the Canada Research Chair in Strategy, Organizations, and Society at the Rotman School of Management. His research focuses on organizations, occupations, and work, and he is particularly interested in the causes and consequences of inequality in labor markets and the workplace.