What makes psychotherapy work? Using deep learning to quantify the relationship between therapy content and outcomes

Add to your list(s) Download to your calendar using vCal

• Ronan Cummins & Michael Ewbank, Ieso Digital Health
• Friday 18 January 2019, 12:00-13:00
• FW26, Computer Laboratory.

If you have a question about this talk, please contact Andrew Caines.

Compared to physical conditions, the quality of care of mental health disorders remains poor and the rate of improvement in treatment is slow. Understanding the efficacy of psychotherapy is limited by a lack of both large-scale data and quantifiable measures of therapy content. We present 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 treatment, we determine the relationship between the “dose” of different aspects of therapy delivered and clinical outcomes. The approach represents a significant advance in developing a data-driven understanding of the treatment of mental health conditions with implications for monitoring and standardizing clinical practice as well as enhancing the efficacy of psychotherapy.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• FW26, Computer Laboratory
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.