Sudden cardiac arrest is a leading cause of death in Canada, often resulting in death within minutes if not treated. Quick recognition is crucial, but many incidents occur when no one is around to help. Our research aims to change this by using common consumer wearable devices, like smartwatches, to detect and predict cardiac arrest. Currently, smartwatches are unable to do this in a reliable way because these algorithms are not trained and tested on real cardiac arrest cases. We have collected this type of data from patients in hospices, undergoing medically assisted dying, and dying in the intensive care unit and trained highly accurate algorithms to detect cardiac arrest. In this project I will build an end to end cardiac arrest detection and alerting system which can use this algorithm to detect cardiac arrest, and complete the necessary steps to integrate it into the 9-1-1 system, building a foundation for real world community testing.
Our goal is to harness everyday wearable technology to improve the detection of cardiac arrest, enhancing survival rates and improving patient outcomes.
Research Location: Centre for Advancing Health Outcomes
Administrative-based case-finding algorithms to evaluate health inequities: a methodological framework and an application in progressive pulmonary fibrosis
The ability to study disease at the population level is required to understand the causes for delays in diagnosing a disease. Administrative data are collected when patients have an encounter with the healthcare system and are commonly used to identify individuals with disease. However, there is no way to specifically identify patients whose disease is getting worse over time and would benefit the most from treatment. My proposed research program will create a framework to develop algorithms that identify patients with worsening disease using administrative data. My research will start with people who have progressive pulmonary fibrosis (lung scarring conditions) and then extend to other common lung diseases. Using these algorithms to identify people with progressive lung diseases, I will then study health inequities that prevent people from receiving treatment. I will use these findings to inform health system and policy changes by working with patients, researchers, clinicians, and policymakers.