Using wearable and health data to model and classify individual health risk
Principal Investigator:
Dr Mark Farrell
Approved Research ID:
42107
Approval date:
March 26th 2019
Lay summary
An increase in the amount of individual-level health data, including that from wearable devices provides the opportunity to classify risk and predict the occurrence of adverse health events, therefore allowing preventative interventions to be taken. This study will use health and accelerometer data to both classify risks and predict adverse health outcomes, through the use of advanced machine learning algorithms. These models have several applications across the private and public sector, with this study focusing primarily on individual understanding of risk , adverse-health event avoidance and hospital readmission prevention.