Current Treatments
Type 1 diabetes is treated with life-long insulin-replacement therapy using daily injections or subcutaneous insulin infusion via a portable pump. With the currently available treatments, less than 20% of patients achieve glucose targets, and the life expectancy of patients with type 1 diabetes is less than that of the general population by as much as 13 years.
What are closed-loop systems?
Over the last 30 years, several biological and mechanical approaches have been developed to help patients reach glucose targets. Biological approaches, notably islets transplants, are hampered by the need for immune-suppression, availability of organs, and the limited survival of transplants.
The artificial pancreas is a medical device that automatically regulates glucose levels for patients with type 1 diabetes. The artificial pancreas is composed of a glucose sensor, a portable infusion pump, and an advanced mathematical dosing algorithm that controls hormonal delivery based on the sensor readings.
What are learning algorithms?
Learning algorithms can involve models or machine learning approaches that frequently analyze the amount of insulin taken with the corresponding blood sugar levels to recommend adjustments in insulin parameters with the aim of improving blood sugar control for people using multiple daily injections.
Our Focus
The development of the artificial pancreas for insulin pump users, as well as learning algorithms integrated into mHealth applications for multiple daily injection users, is the current focus of the McGill Diabetes Technologies Lab. We develop and test novel algorithms that lie at the heart of these devices. Our research is highly experimental and interdisciplinary, as it involves the collaboration of engineers and clinicians to develop our algorithms and test them in clinical trials. Find out more about our ongoing work here.