Projects

Precision Intensive Care Powered by Machine Learning

Intensive care units are an ideal arena for health data science research thanks to their detailed patient monitoring that generates a large volume of rich clinical data. We strive to develop and rigorously validate ICU patient outcome prediction models that take into account individual patients’ unique states and characteristics. 

 

Development of Novel Case-specific Machine Learning Methodologies

Traditional machine learning tends to treat individual cases in a data set equally in terms of training or evaluation. Hence, we aim to improve various aspects of machine learning via novel case-specific methodologies that characterize and utilize unique individual cases. 

Digital Public Health Surveillance

Digital platforms such as social media and search engines effectively capture people’s online activities. In this research area, we have utilized digital platforms to investigate various surveillance opportunities. In particular, we are using large-scale Twitter data and machine learning to monitor physical activity, sedentary behaviour, and sleep disorder at the population level. 

 

Using AI to Protect Children from Unhealthy Food and Brand Marketing

Children are constantly exposed to unhealthy food/brand marketing on digital media. Evidence confirms that unhealthy food marketing adversely affects children’s diet quality and diet-related health. We are developing an AI-based system that automatically monitors marketing instances on various types of digital media.

 

Leveraging Machine Learning to Enable Precision Coronary Artery Disease Patient Care

Coronary artery disease is the leading cause of death globally. The application of machine learning to the high quality clinical data from APPROACH offers enormous potential to develop a clinically meaningful artificial intelligence decision support tool to inform revascularization decisions. 

 

mHealth and Aging

With aging comes increased burden of chronic disease. A successful transition to a sustainable health care system would require older adults and their caregivers to carry out routine care at home or in the community. This much needed patient/caregiver empowerment, as well as seamless integration with health care providers when needed, can be facilitated by data technologies.