BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:CANCELLED - Identifying and evaluating personalised treatment reco
 mmendations - Prof Richard Emsley\, University of Manchester
DTSTART:20170223T143000Z
DTEND:20170223T153000Z
UID:TALK69774@talks.cam.ac.uk
CONTACT:Alison Quenault
DESCRIPTION:Stratified or personalised medicine is an attempt to move beyo
 nd a `one size fits all' approach based on comparing group-level average o
 utcomes to improve patient-level outcomes by identifying personalised trea
 tment recommendations (PTR). A PTR maps a set of predictive markers to a d
 ecision of whether or not to treat an individual patient. A PTR can be est
 imated from a weighted sum of predictive markers and the treatment effect 
 using either regression models\, inverse probability weighting (IPW)\, aug
 mented IPW\, or classification methods.\n\nOnce estimated\, PTRs can be ev
 aluated by testing if the expected outcome under the PTR improves on the e
 xpected outcome under an alternative policy - such as one where either eve
 ry patient receives the treatment or every patient receives the control co
 ndition. Evaluating a PTR differs from the evaluation of prognostic or dia
 gnostic models because the object of inference (whether a subject benefite
 d from treatment) remains unobserved.\n\nIn this talk\, we will describe t
 he statistical methods for estimating a PTR. Monte-Carlo simulations are u
 sed to compare the statistical properties of the estimation methods under 
 a range of data generating scenarios. These methods will be demonstrated w
 ith application to data from a randomised controlled trial in Chronic Fati
 gue Syndrome\, using our new user-written Stata command -ptr-.
LOCATION:Large  Seminar Room\, 1st Floor\, Institute of Public Health\, Un
 iversity Forvie Site\, Robinson Way\, Cambridge
END:VEVENT
END:VCALENDAR