Patient monitoring in the hospital is transitioning from stand-alone bedside solutions to mobile telemetry systems enabling ubiquitous and home-based patient care. This has important implications for enabling patient care in transition between hospital acuity levels and allow hospitals to generate cost savings by shifting care to home. In this talk I will focus on the role of machine learning and AI in interpreting data captured by wearable sensors to assess patient activity and health-related parameters such as vital signs and atrial fibrillation.

Alberto Bonomi received a M.Sc. degree in Biomedical Engineering from Politecnico di Milano, Milan (Italy), in 2006, and the Ph.D. degree from Maastricht University, Maastricht (The Netherlands), in 2010. His research interests are related to machine learning and data analytics applied to the field of wearables sensors and physiological data interpretation. The aim is develop systems and services to improve people health by broadening the efficacy of preventive treatments, the quality of medical diagnostic, and the care of patients. In particular, he worked on physical activity recognition and context assessment, energy expenditure and cardio-respiratory fitness estimation, environmental sensors data analysis, arrhythmia detection, and deterioration prediction due to lungs edema in heart failure. Alberto is currently senior scientist at Philips Research and product manager at the Cardiology Informatics Philips business unit.