• UCL Twitter account
  • UCL YouTube channel
  • UCL Facebook page
  • UCL SoundCloud channel
  • UCL iTunes store

Information for Staff

Calendar

Select dates to view past and future events

13:00 - 14:00 17 October 2017

Learning Individualized Treatment Effects from Observational Data Seminar - Professor Mihaela van der Schaar

Location

Room GO1, The Farr Institute of Health Informatics (link Map)
222 Euston Road | London | NW1 2DA | United Kingdom

Open to: Academic | Student

Current treatment guidelines have been developed for the “average” patient, but there is ample evidence that different treatments have different effects on different individual. To choose the right treatment for a particular patient requires understanding the effect of each (potential) treatment on that individual. In this talk, Mihaela will present some new theories and associated methods for learning individualized treatment effects (ITE's) from observational data.

Mihaela's work takes a novel approach to learning ITE's, viewing the problem as one of multi-task learning. This work achieves large performance improvements over the previous state-of-the-art and provides guidance for treating individual patients.

Mihaela's research interests and expertise are in machine learning, data science and decisions for a better planet. In particular, she is interested in developing machine learning and decision theory for finance, medicine and personalized education.


Contact

UCL Digital Health
digitalhealth@ucl.ac.uk


Links

More UCL Digital Health events
Speaker bio


image