Advancing Medicine through Data Science, Machine Learning and Artificial Intelligence

In this talk, I will describe some of the research of my group on developing and applying new machine learning methods for personalized healthcare, with special focus on clinical decision support for chronic conditions (including cancer, cardio-vascular disease, etc.) and for in-hospital care. Among other things, I will discuss our development of data-driven methods for risk scoring and early warning systems, for screening and diagnosis, for prognosis and treatment. Our novel machine learning techniques take into account the unique characteristics of medical data and embody a deep understanding of the medical domain, achieved through continuous interaction with medical researchers and clinicians. As a result, our work achieves enormous improvements over current technology and over existing state-of-the-art machine learning methods. Moreover, our methods are designed to be easily interpretable by clinicians and to extract from data the necessary knowledge and representations to enable data-driven medical epistemology and to allow easy adoption in hospitals and clinical practice. You can find more information about our past research at: http://medianetlab.ee.ucla.edu/MedAdvance

• Speaker: Mihaela van der Schaar, University of Oxford and Alan Turing Institute
• Wednesday 22 February 2017, 14:00–15:00
• Venue: MR15 Centre for Mathematical Sciences.
• Series: CCIMI Seminars; organiser: Rachel Furner.