BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning Engines for Healthcare:  Using Machine Learning to Transf
 orm Clinical Practice and Discovery - Prof Mihaela van der Schaar from 	De
 partment of Applied Maths and Theoretical Physics\, University of Cambridg
 e
DTSTART:20190218T130000Z
DTEND:20190218T140000Z
UID:TALK114082@talks.cam.ac.uk
CONTACT:72001
DESCRIPTION:The overarching goal of professor Mihaela van der Schaar’s r
 esearch is to develop cutting-edge machine learning\, AI and operations re
 search theory\, methods\, algorithms and systems to understand the basis o
 f health and disease\; develop methodology to catalyze clinical research\;
  support clinical decisions through individualized medicine\; inform clini
 cal pathways\, better utilize resources & reduce costs\; and inform public
  health.\n\nTo do this\, professor van der Schaar  is creating what she ca
 lls Learning Engines for Healthcare (LEH’s). An LEH is an integrated eco
 system that uses machine learning\, AI and operations research to provide 
 clinical insights and healthcare intelligence to all the stakeholders (pat
 ients\, clinicians\, hospitals\, administrators). In contrast to an Electr
 onic Health Record\, which provides a static\, passive\, isolated display 
 of information\, an LEH provides dynamic\, active\, holistic & individuali
 zed display of information including alerts.  \n\nIn this talk professor v
 an der Schaar will focus on 3 steps in the development of LEH’s:\n1.    
 Building a comprehensive model that accommodates irregularly sampled\, tem
 porally correlated\, informatively censored and non-stationary processes i
 n order to understand and predict the longitudinal trajectories of disease
 s.\n2.    Establishing the theoretical limits of causal inference and usin
 g what has been established to create a new approach that makes it possibl
 e to better estimate individualized treatment effects.\n3.     Using Machi
 ne Learning itself to automate the design and construction of entire pipel
 ines of Machine Learning algorithms for risk prediction\, screening\, diag
 nosis and prognosis. \n\n
LOCATION:CRUK CI Lecture Theatre (Room 001)
END:VEVENT
END:VCALENDAR