Seminars & Events

Tuesday, April 16, 2024, 15:00-16:00
The Health AI and Data Science (HAD) Program presents
Developing and Deploying Transparent and Reproducible Predictive Algorithms in Healthcare (Part 1 of 2)
Speaker: Doug Manuel and Wenshan Li
Dr. Doug Manuel holds the position of Senior Scientist at the Ottawa Hospital Research Institute and is a distinguished professor at uOttawa’s Department of Family Medicine and School of Epidemiology and Public Health, holding a Tier 1 Clinical Research Chair in Precision Medicine for Disease Prevention. Dr. Manuel holds an additional appointment as a senior investigator at Bruyère Research Institute.

Dr. Manuel’s research combines expertise in public health, healthcare systems, and primary care, focusing on understanding factors contributing to differences in population health outcomes across societies. This research involves developing and using advanced predictive algorithms and microsimulation models to assess the potential impact of health interventions and policy strategies. Dr. Manuel collaborates on Project Big Life, a website with disease risk calculators, helping millions globally to understand their health and contribute to evidence-based public health decisions.

Wenshan Li is a post-doctoral fellow at the Ottawa Hospital Research Institute, with a PhD in epidemiology. She is experienced in conducting health services research using large and/or complex data, and involved in several projects on predictive model development.
Location: Virtual via MS Teams. Meeting ID: 226 357 291 422 | Passcode: HyCFcM

Please contact Emma Brown at if you would like the meeting link.

NOTE: If you would like to be added to the HAD - Health AI and Data Science team on MS Teams (including the HAD JC seminar mailing list), please join the team using code: owfh55e. If you are external to TOH/OHRI and would like to be added, please email Emma Brown at

This is a two-part seminar series. Part 2 of the seminar will be held in May by Juan Li and Kitty Chen from the Ottawa Hospital Research Institute.

Learning Objectives

By the end of the sessions, participants will:

  • Be able to apply open science principles in developing predictive algorithms to enhance reproducible science and improve patient care quality
  • Understand the approaches used by other participants, thereby improving researcher and IS collaboration for algorithm development and deployment

Part 1 – Foundations for reproducible predictive algorithms in healthcare

Objectives: review and discuss the essentials of reproducible and transparent AI, understanding its imperatives, best practices, and challenges in the healthcare context.

  • Review and discuss open science from the perspective of predictive algorithms in health care.
  • Examine case studies comparing open-source and proprietary workflows in algorithm development, discussing their implications for healthcare IT and patient care.

Part 2 – Practical application of open and reproducible predictive algorithms

Objectives: Engage in hands-on development and deployment of predictive algorithms using open-source tools, with a focus on real-world healthcare applications.

  • Review a hands-on example of algorithm development and deployment using an open-source workflow (R Tidymodels and Plumber).
  • Walk-through of algorithm development and deployment at the Project Big Life platform.

Please note that OHRI seminars are open to all members of OHRI and partner institutions. Members of the general public are asked to contact the communications office ( for more information about the research presented at OHRI seminars.