Objective Measurement and Analysis of Internalizing Disorders Using Multimodal Machine Learning for Clinical Science and Treatment
Prof.Dr. Jeffrey Cohn
Abstract: To reveal mechanisms in psychopathology and gauge treatment response, reliable, valid, efficient measurement is critical. Self-report and clinical interview, current state of the art in diagnosis and clinical trial end-point measurement, assess severity but are subjective, difficult to standardize within and across settings, impose patient burden, and lack granularity. Multimodal machine learning presents an increasingly powerful alternative to these standard approaches. With emphasis on audio-visual communication in depression and OCD, I present my interdisciplinary teams’ efforts in developing and applying objective, reliable, valid, efficient, and interpretable multimodal measures of disorder, neural activity, and response to treatment in children and adults.
Bio: Dr. Jeffrey Cohn is professor emeritus of Psychology and Intelligent Systems at the University of Pittsburgh, courtesy faculty at the Robotics Institute of Carnegie Mellon University, and chief scientist and co-founder at Deliberate AI. He has led inter-disciplinary efforts to develop advanced methods of automatic analysis and synthesis of facial expression, body movement, and prosody and applied those tools to research in human emotion, nonverbal communication, and computational psychiatry. His research has been supported by the U.S. National Institutes of Health, National Science Foundation, and other agencies in the U.S., Canada, and Australia.
DATE: June 03, Monday @ 13:30
Place: Mithat Çoruh Amfi