University of Cambridge > Talks.cam > Department of Psychiatry & CPFT Thursday Lunchtime Seminar Series > Peeking Inside Black Boxes: New Insights Into Depression Recovery with Deep Brain Stimulation Using Explainable AI

Peeking Inside Black Boxes: New Insights Into Depression Recovery with Deep Brain Stimulation Using Explainable AI

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

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

Abstract: Simultaneous advances in neurotechnology and data science have created new opportunities to measure, modulate and understand the neural activity underlying complex psychiatric disorders such as treatment resistant depression (TRD). Despite promising open label studies of deep brain stimulation (DBS) as a therapy for TRD , one of the barriers to scaling this treatment is the lack of objective information supporting clinical decision making during patient-specific trajectories toward stable recovery. In a recent study we have collected longitudinal intracortical local field potential (LFP) data from TRD patients undergoing subcallosal cingulate cortex (SCC) DBS . I will describe our development of a novel “explainable AI” (XAI) technique for generating causal post-hoc explanations of machine learning systems. Using a data-driven approach that employs these XAI techniques, we identify unexpected changes in SCC LFP dynamics that correspond to individual recovery trajectories, behavioral changes reflected in facial expressions, and white matter structural integrity. In addition to providing evidence about neural dynamics underlying TRD and recovery with chronic SCC DBS , our results also demonstrate potential biomarkers that could be used to support psychiatric decision making during SCC DBS therapy.

Biography: Christopher J. Rozell is the Julian T. Hightower Chaired Professor of Electrical and Computer Engineering at the Georgia Institute of Technology. He received a B.S.E. degree in Computer Engineering and a B.F.A. degree in Music in 2000 from the University of Michigan, received M.S. and Ph.D. degrees in Electrical Engineering in 2002 and 2007 from Rice University, and was a postdoctoral scholar at the Redwood Center for Theoretical Neuroscience at the University of California, Berkeley. Dr. Rozell’s research interests is in computational neuroengineering to advance the understanding of brain function, the engineering of effective interventions for neurologic disorders, and the development of more intelligent engineered systems. Beyond his technical contributions, Dr. Rozell’s scholarly activity also includes research and creative work that advances public engagement on the societal implications of emerging areas such as AI and neurotechnology. His work has been recognized with the Scholar Award in Studying Complex Systems from the James S. McDonnell Foundation (one of six international recipients), the National Science Foundation CAREER Award, the Sigma Xi Young Faculty Research Award, and the Class of 1940 W. Howard Ector Outstanding Teacher Award. Dr. Rozell is proud to be a first-generation scholar who is committed to diversity, equity and inclusion in our educational institutions and scientific communities. He is a co-founder and member of the Board of Directors of Neuromatch, Inc., a global nonprofit increasing access to scientific knowledge through inclusive conferences and summer schools. For more information on Dr Rozell, please visit: https://siplab.gatech.edu/rozell.html

This talk is part of the Department of Psychiatry & CPFT Thursday Lunchtime Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity