Optimizing Docto’s Predictive models using Machine Learning Techniques

The proposed research project aims to increase the accuracy of a model used to predict future glucose levels 1 hour ahead of time, with ~90% accuracy. This model should be able to detect, ahead of time, situations where the blood-glucose level is either too high or too low which could lead to complications for the patient. The partner organization will use this model in their application to allow diabetics to see an estimate of their future blood-glucose level. This will allow them to change their current behaviour to avoid high risk situations that could present a risk to their health. Moreover, with the data collected, the partner will also be able to give personalized advice to a patient to regulate his/her blood-glucose level more efficiently.

Faculty Supervisor:

Jared Simpson

Student:

Partner:

Bio-Conscious Technologies Inc

Discipline:

Computer science

Sector:

Health and Related Sciences & Technology

University:

University of Toronto

Program: