PhD defence: Helene Bei Thomsen
Machine Learning Methods for Continuous Glucose Monitoring Data and their Potential in Cardiovascular Risk Assessment
Info about event
Time
Location
Verdensrummet, aud. A201-170, Aarhus University Hospital
On Thursday 22 October at 10:00, Helene Bei Thomsen defends her PhD dissertation entitled “Machine Learning Methods for Continuous Glucose Monitoring Data and their Potential in Cardiovascular Risk Assessment”.
Continuous glucose monitors provide a detailed picture of how glucose levels change throughout the day. But can these measurements also be used to assess the risk of cardiovascular disease in people with diabetes? This is investigated in a new PhD project at Aarhus University, Health.
Diabetes is characterized by elevated blood glucose levels and is associated with an increased risk of cardiovascular disease. Current cardiovascular risk models may be improved by incorporating more detailed information about glucose patterns than is provided by HbA1c—the average blood glucose levels over the past 3 months— which is commonly used in prediction models today. Continuous glucose monitoring (CGM) captures how glucose levels change throughout the day, while recent advances in machine learning offer new ways to identify patterns in these complex data.
The dissertation comprises three studies examining how CGM data and machine-learning methods may contribute to cardiovascular risk assessment and glucose prediction in people with diabetes. The first study reviewed the existing evidence on associations between CGM-derived measures and cardiovascular disease. The second investigated whether a foundation model—a machine-learning model trained on large amounts of CGM data—could extract clinically meaningful patterns and whether these patterns could identify people who might benefit from further examination for heart failure. The third study examined whether the racial composition of training data affected the performance of machine-learning models used to predict future glucose levels in Non-Hispanic Black and White individuals with type 1 diabetes.
The summary is written by the PhD student.
The defence is public and takes place in Verdensrummet aud. A201-170, Aarhus University Hospital. Please see the press release for more information.
Contact
PhD student Helene Bei Thomsen
Email: hbt@ph.au.dk
Phone +45 21139392