BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:What makes psychotherapy work? Using deep learning to quantify the
  relationship between therapy content and outcomes - Ronan Cummins &amp\; 
 Michael Ewbank\, Ieso Digital Health
DTSTART:20190118T120000Z
DTEND:20190118T130000Z
UID:TALK117832@talks.cam.ac.uk
CONTACT:Andrew Caines
DESCRIPTION:Compared to physical conditions\, the quality of care of menta
 l health disorders remains poor and the rate of improvement in treatment i
 s slow. Understanding the efficacy of psychotherapy is limited by a lack o
 f both large-scale data and quantifiable measures of therapy content. We p
 resent an approach using a deep-learning model to automatically categorise
  the content (i.e. natural language) of cognitive behavioural therapy (CBT
 ) sessions. The model was applied to approximately 90\,000 transcripts of 
 internet-enabled message-based CBT. Using this quantifiable measure of tre
 atment\, we determine the relationship between the "dose" of different asp
 ects of therapy delivered and clinical outcomes. The approach represents a
  significant advance in developing a data-driven understanding of the trea
 tment of mental health conditions with implications for monitoring and sta
 ndardizing clinical practice as well as enhancing the efficacy of psychoth
 erapy. 
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR