Machine learning classifier to facilitate decision making by multidisciplinary tumor boards (Princess Margaret Cancer Centre): Multidisciplinary tumor boards (MDTs) are an opportunity for specialists to meet and discuss the diagnosis and management of cancer patients. At the Princess Margaret Cancer Centre, patients with lung metastases are reviewed at a specialized tumour board, which is a meeting of radiation oncologists, medical oncologists, surgeons, and radiologists to discuss the patient cases. During these meetings, treatment recommendations for patients are made after a careful review of the patients’ clinical history and relevant investigations. The objective of this study is to develop a machine learning classifier which reproduces MDT decision making and can be used as a decision support system to facilitate quality assurance and knowledge sharing in future MDTs. The dataset currently contains primarily numerical and categorical data, but is expected to grow to include imaging data from CT scans or other imaging techniques, and this image data should be incorporated into the classification when available.
Predictive modelling for Emergency Department stay (Sunnybrook Health Sciences Centre): The objective of this project is to enhance patient experience by creating more transparency around certain aspects of an ED visit: How long will it take to see a doctor? Will this ED visit lead to hospital admission? Decision support is looking for an engineering student who will help us leverage machine learning models to answer these types of questions. Our goal is to employ these predictive models to create real-time tools/dashboards which can both inform patients of their expected wait times and outcomes, and also be used by hospital clinicians and decision makers to understand demand and respond to future needs (e.g., bed utilization, staffing needs, added supports for patients etc.).
Please send expression of interest and cv to che@utoronto.ca, or to Prof Dionne Aleman
May also suit MEng students looking to transfer to the MASc program.