Exploring How Lifestyle Factors Influence Digital Biomarkers Using Wearable Devices
Explore how lifestyle impacts glucose levels using wearable devices and data science. Build models linking diet, activity, and sleep with glucose patterns to reduce diabetes risk. Use cutting-edge machine learning to develop personalized health interventions.
AI-generated overview
Project Description
Project Overview
Metabolic health and type 2 diabetes risk are influenced by lifestyle factors such as diet, physical activity, and sleep. This project explores how these behaviors affect blood glucose patterns in real-time through wearable devices. There is limited evidence on whether feedback from these devices improves health in people without diabetes.
The PhD will investigate trends between continuous glucose monitor (CGM) data, lifestyle behaviors, diet, and health outcomes to identify patterns that improve metabolic health in healthy adults or those at risk of diabetes.
What You Will Do
You will use data analysis methods including time series analysis (ARIMAX models) and machine learning techniques (random forests, gradient boosting, LSTM models, deep reinforcement learning) to build predictive models and explore relationships between glucose patterns and lifestyle factors. Developing personalized glucose response models to understand who benefits most and what drives sustained behavior change will be a key focus.
Expected Outcomes
The research will elucidate how wearable technology can support lifestyle changes to reduce diabetes risk and improve health by identifying impactful real-time feedback mechanisms and behavior predictors.
Why This Matters
This work addresses a critical gap in evidence on the effectiveness of wearable devices for metabolic health in non-diabetic populations. It has the potential to enhance personalized health interventions, reduce diabetes incidence, and support healthier lifestyles through data-driven insights.
Entry Requirements
How to Apply
Eligibility
Supervisor Profile
Dr Andrew Kingsnorth is a researcher at Loughborough University's School of Sport, Exercise and Health Sciences, focusing on digital health, physical activity, and sedentary behavior. His work exploits wearable technology and data science to understand and improve metabolic and physical health. He collaborates with multidisciplinary teams to develop personalized lifestyle interventions using wearable data analytics.