Natural Language Processing & Training Providers

David Atkins, Psychiatry and Behavioral Sciences, University of Washington 

Tad Hirsch, School of Art and Art History Design, University of Washington

Zac Imel, University of Utah

Shrikanth ‘Shri’ Narayanan, University of Southern California

Sarah Kopelovich, University of Washington

Projects

Digital Exploration of Psychotherapy- DEPTH

Automated speech recognition can transcribe words from session recordings, and natural language processing (NLP) and machine learning methodologies can use those words and other information from the spoken language of therapy to predict quality metrics.


Informed by psychotherapy experts, engineers and computer scientists have developed a software “pipeline” that takes a motivational interviewing session recording as input and generates a web-based interactive report of quality metrics and key features of the session. Check out a little demo at: http://sri.utah.edu/psychtest/misc/demoinfo.html.

Findings: Quality metrics such as therapist’s empathy and reflective listening can be automatically rated by our software system, CORE-MI; plus, it takes about a quarter of the time as a human and gets faster all the time (and, it doesn’t even get bored or tired).

 

Funded by National Institute of Alcoholism and Alcohol Abuse

Cognitive Behavioral Therapy for psychosis (CBTPro):

Psychosis resulting from schizophrenia spectrum disorders and major mood disorders is one of the most disabling health concerns worldwide. Evidence-based psychotherapeutic interventions are recommended as standard of care by national psychosis treatment guidelines but are rarely accessible. Cognitive Behavioral Therapy for psychosis (CBTp) is the most well-researched psychotherapy for psychotic disorders, yet fewer than 1% of American mental health providers are trained in this intervention. To date, there has been no scalable way to offer high-quality and sustainable training to mental health providers in CBTp-informed care. 

 

BRiTE faculty have partnered with small business Lyssn.io to systematically develop, pilot, and rigorously test CBTpro, a novel Computerized Clinician Support Tool that will use cutting-edge spoken language technology to provide immediate feedback and coaching to mental health staff and trainees who wish to learn CBTp. CBTpro will provide a rapid means of scaling and sustaining CBTp in routine care settings across the US, resulting in more clinicians  across the country providing higher quality CBTp to individuals with psychosis.

 

This work is supported by a National Institute of Mental Health (NIMH) Fast-Track Small Business Technology Transfer grant (R42MH123215-01). For more information about this project, please contact Principal Investigator Sarah Kopelovich, PhD (skopelov@uw.edu).