Session Description

This session will explore the development and evaluation of Therabot, the first fully generative AI system designed for psychotherapy. Developed over 6 years by a team of more than 100 people, Therabot is designed to treat anxiety, depression, eating disorders, and their related comorbidities. Dr. Jacobson will discuss the journey of creating this novel therapeutic tool and present the findings from the first-ever randomized controlled trial of a generative AI psychotherapy agent, which was recently published in the New England Journal of Medicine AI. The talk will cover the implications of using generative AI to deliver scalable, personalized mental healthcare

Video

view slides

Speaker

Nicholas C. Jacobson, PhD

Nicholas C. Jacobson, Ph.D., is an Associate Professor in Biomedical Data Science, Psychiatry, and Computer Science at Dartmouth College and the Director of the AI and Mental Health: Innovation in Technology Guided Healthcare (AIM HIGH) Laboratory. Working within the Center for Technology and Behavioral Health, his research focuses on enhancing the assessment and treatment of anxiety and depression through technology. Dr. Jacobson’s work involves creating personalized deep learning models using passive sensor data from smartphones and wearables to predict changes in mental health, and he is the principal investigator of an R01 award from the National Institute of Mental Health. He also developed Therabot, the first fully generative AI for psychotherapy, recently publishing its first trial in the New England Journal of Medicine AI.

Discussant

Roy Perlis, MD, MSc

Roy Perlis, MD, MSc is founding Editor in Chief of JAMA+ AI, the JAMA Network’s artificial intelligence channel; Director of the Center for Quantitative Health and Ronald I. Dozoretz, MD Endowed Chair at Massachusetts General Hospital; and Professor of Psychiatry at Harvard Medical School. His lab works at the intersection of machine learning, genomics, and cellular models of brain disease; they identified the first genes associated with major depressive disorder and treatment resistant depression, and pioneered the application of electronic health records for risk stratification in psychiatry. Dr. Perlis has authored more than 400 articles reporting original research in peer-reviewed journals ranging from Nature Genetics and Nature Neuroscience to JAMA and the New England Journal of Medicine. In 2010 Dr. Perlis was awarded the Depression and Bipolar Support Alliance’s Klerman Award; he now serves as a scientific advisor to the DBSA Professor of Psychiatry, Harvard Medical School

other real world AI events