type of treatment they will provide to patients. With technological improvements and the availability of a significant volume of data, it is increasingly difficult for care providers to properly evaluate and analyze the options available to them. The current health condition of the patient–reflected in the monitored observations which are recorded in EMR–may depend on […]

Anticoagulation with Warfarin is indicated and required for post-operative cardiovascular patients. However, it is a high-risk medication with a narrow therapeutic range where sub-optimal dosing can lead to complications and even death. While multiple risk factors have been associated to Warfarin sensitivity, the prediction of optimal Warfarin dosing strategies remains ineffective and requires trial and […]

Personalized and precise treatments are the keys to improve prognosis of cancer patients and are also the main strategy of Sunnybrook Hospital. This project aims to stratify patients with colorectal cancer liver metastases (CRM) based on their disease subtype and risk using magnetic resonance imaging, which is routinely used in the diagnosis, staging and operative […]

This proposed study will significantly enhance our current understanding of how specific intra-operative factors can impact patient outcomes. Our proposed work will provide a proof of concept that machine learning can objectively predict a specific, high-impact post-operative complication, allowing us to move forward with scaling this work to a wide variety of surgical settings. Moreover, […]

Healthcare facilities collect and produce vast amounts of clinical-relevant data. Various AI-related methods (like computer-aided detection for mammography and the learning and visualization of clinical pathways) are applied to healthcare these days, and visualization techniques are also used to support clinicians due to the complexities of clinical data. This self-contained survey focuses on the assessment […]

Hospitals strive to perform cutting edge medical treatment, treat all patients fairly, and reduce operating costs, while also enabling caregivers to spend more time interacting with patients. Artificial intelligence and machine learning promise these things. However, medical data provides unique challenges for machine learning. Currently, if a hospital wants to include an algorithm for automated […]

While neural networks can classify images with very high accuracy, it was shown in 2013 (original paper by Szegedy et al) that it is also possible to make very small perturbation to an image so that the network misclassifies it (e.g. so that a panda is classified as an airplane). Many variations of this effect […]

Using genomics in clinical care has the potential to treat patients more efficiently. There have been a number of recent discoveries of genomic assays that can guide treatment. However, most genomic data is generated in a research setting and useful health data only in a clinical setting. Translating potential genomic research into a clinical setting […]