June 4, 2022
The Health Care Operational Research Special Interest Group (HCOR SIG) of the Canadian Operational Research Society (CORS) is pleased to announce the details for this year’s Canadian Healthcare Optimization Workshop (CHOW). This will be a hybrid event, held on Saturday, June 4, 2022 (the day before the start of the CORS/INFORMS International Conference in Vancouver, BC).
Registration has closed for in-person attendees, but for those wanting to participate online, the Zoom info is as follows:
Meeting ID: 618 9736 7076
The theme of this year’s CHOW is “Research meets Practice,” which will feature paired presentations of OR/MS researchers and their health care collaborators. The former will speak to the modeling approaches and results, while the latter will speak to the importance and impact of the work. Our distinguished set of speakers will also discuss the origins of their work, next steps, and challenges in bridging academia and practice. There will be plenty of time for Q&A for both speakers.
Join us for this exciting new format highlighting experts in both mathematical modeling and healthcare delivery. Details of the talks and bios of workshop speakers can be found below. Details for the event (e.g., location, zoom link) will be updated when available.
Schedule at a Glance
All times are in Pacific Daylight Time (PDT)
|8:50-9am||Steven Shechter||Introduction to Workshop|
|9-10am||Nadia Lahrichi and Marie-Andrée Fortin||Designing Decision Support Systems to Improve Cancer Treatment Logistics|
|10-11am||Tinglong Dai and Risa Wolf||Designing AI-augmented Healthcare Delivery Systems for Physician Buy-in and Patient Acceptance|
|11am-12noon||Pengyi Shi and Jason Huber||Reducing Substance Use Disorders-related Recidivism with Community-based Programs: Data-driven Analytics for Fairness and Societal Benefits|
|1-2pm||Timothy Chan and Sheldon Cheskes||Pi in the Sky: Drone-delivered Defibrillators for Out-of-hospital Cardiac Arrest|
|2-3pm||Carri Chan and Hayley Gershengorn||Optimal Scheduling with Customer Deterioration and Improvement: The Use of High-flow Nasal Cannula and Mechanical Ventilators During COVID-19|
Designing Decision Support Systems to Improve Cancer Treatment Logistics
In this talk, we present how simulation and optimization models can help improve the efficiency of cancer treatment centers. Patient flow in these centers is complex and involves multiple steps and resources. While dealing with limited resources and a number of constraints, decision makers need to ensure that patients are treated within deadlines. We provide data-driven models to achieve these goals for scheduling patients’ treatments, scheduling physicians, assessing delays or the surges in demand for radiotherapy treatment. Managerial insights are shared.
Designing AI-augmented Healthcare Delivery Systems for Physician Buy-in and Patient Acceptance
The role of artificial intelligence (AI) in augmenting healthcare is expected to grow substantially in future decades. Current research in medical AI focuses on developing, validating, and implementing point-level AI applications in an ad-hoc manner. To harness the full power of AI to improve the patient experience and outcomes at a societal scale, however, requires a gestalt shift—with systematic understanding of AI in the context of healthcare—and so results in its widespread adoption. This translates to four pillars of incorporating AI into healthcare workflow, including physician buy-in, patient acceptance, provider investment, and payer support (the “4Ps”). To achieve these 4Ps, it is imperative to design AI-augmented healthcare delivery systems in view of (1) how physicians integrate AI into their clinical practice and (2) how patients perceive the role of AI in healthcare delivery. This will in turn boost provider investment and payer support. In this joint talk, we discuss several ongoing projects aimed at understanding and overcoming barriers to the appropriate use of AI in clinical practice.
Reducing Substance Use Disorders-related Recidivism with Community-based Programs: Data-driven Analytics for Fairness and Societal Benefits
Recidivism, when a convicted criminal commits a new offense, is one of the most challenging and important issues facing the modern criminal justice system. Notably, many repeat offenders suffer from substance use disorders (SUD), which is a chronic disease that needs continuous support from the community. Rather than receiving aid and treatment from their local communities, SUD sufferers are often criminalized and incarcerated for minor offenses. The large number of individuals with SUD involved in the criminal justice system presents a unique opportunity, as well as challenges, in addressing the concerns of public safety and public health. In this talk, we first discuss the complex process flow of individuals with SUD through the criminal justice and social services support systems. We then discuss using data-driven analytics to aid community-based programs in optimally allocating their limited resources to different intervention and support services to maximize the benefit to society while reducing racial disparity in incarceration and recidivism.
Pi in the Sky: Drone-delivered Defibrillators for Out-of-hospital Cardiac Arrest
This talk presents several research projects related to optimizing drone delivery of defibrillators to out-of-hospital cardiac arrest (OHCA) victims. The first project combines optimization and queuing to design a hypothetical drone network to reduce response time to OHCAs in a large region surrounding Toronto, Ontario. The second project develops machine learning-based dispatch rules so drones are prioritized to cases where they are most likely to beat an ambulance. The third project describes feasibility studies of actual drone flights to deliver defibrillators.
Optimal Scheduling with Customer Deterioration and Improvement: The Use of High-flow Nasal Cannula and Mechanical Ventilators During COVID-19
In healthcare settings, scarce capacity is often reserved for the most urgent customers. However, there has been a growing interest in the use of proactive service when a less urgent patient may become urgent while waiting. In this work, we consider the optimal allocation of resources to patients whose health state can improve or deteriorate while waiting. We apply the insights from our stylized queueing model to consider the use of an alternative therapy for patients in respiratory distress – High-flow Nasal Cannula. Using simulation, we find that the use of high-flow nasal cannula coupled with early mechanical ventilation when supply is sufficient results in fewer deaths and greater ventilator availability. Using data from the 2020 COVID-19 peak, we estimate that our proposed strategy resulted in 10,000–40,000 fewer deaths than if high-flow nasal cannula were not available.