Project WAITLEARN: Using machine learning to predict patient waiting times using reconstructed minute-by-minute state - MDPH 396 Undergraduate Research Project Application Form

Supervisor's Name: John Kildea

Supervisor's Email: john.kildea [at]

Supervisor's Phone: 5144758943

Supervisor's Website:

Supervisor's department: Medical Physics

Course number: MDPH 396 (Medical Physics)

Term: Winter 2018

Project start date: Monday, January 8th, 2018

Project end date: Monday, April 16th, 2018

Project title: Project WAITLEARN (MDPH 396): Using machine learning to predict patient waiting times using reconstructed minute-by-minute state

Project description (50-100 words suggested): Waiting for appointments is a painful aspect of healthcare. Ideally, the duration of waiting times should be reduced to make the experience less painful. However, in reality, reducing waiting times is difficult to achieve. One way of possibly reducing the pain of waiting, without reducing the actual wait, is to provide patients with realistic estimates of how long they should expect to wait. Waiting time estimates can help patients to better plan around their visits to the hospital and can give them the confidence to move around (eg go to the bathroom or cafeteria) without the fear of missing their call to see the clinician.
To predict patient waiting times using machine learning it is important that the learning algorithm learns using the data that are available at the moment the prediction is being made. Although this sounds straightforward in theory, it is quite complex in reality. Hindsight allows us to easily see how long each patient waited but it doesn’t easily allow us to reconstruct the state of the clinic on a minute-by-minute basis. The goal of this project will be to work with reconstructed clinic data to determine if such data improve waiting time estimates compared to simple highsight summary data.

Prerequisite: (ideally Machine Learning experience) 1 term completed at McGill + CGPA of 3.0 or higher; or permission of instructor. Grading scheme (The final report must be worth at least 50% of final grade): 50% final report, 50% milestones and progress

Other project information: Student is expected to work on project onsite at the Cedars Cancer Centre for the equivalent of one afternoon or morning per week.

Project status: This project is open to applicant.

How students can apply / Next steps: Please contact me by email (john.kildea [at] for further steps/information

Ethics, safety, and training: Supervisors are responsible for the ethics and safety compliance of undergraduate students. This project involves NEITHER animal subjects, nor human subjects, nor biohazardous substances, nor radioactive materials, nor handling chemicals, nor using lasers.