Psychological Monitoring and Rehabilitation Enhancement in Post-Stroke Depression

Fillia Makedon The HERACLEIA Human Centered Computing Laboratory Computer Science and Engineering The University of Texas at Arlington, U.S.A.  http://heracleia.uta.edu/

Abstract
Depression is a severe disorder that affects approximately 16% of the adult population and (30-40%) of stroke survivors. Although depression can heavily impact physical and emotional recovery, brain neural recovery, speech therapy, and even holding a conversation, it is often a hidden condition in the case of stroke survivors.

In this presentation, we will describe computational methods and tools to address the challenges associated with post stroke depression and rehabilitation monitoring. In particular, we will describe a system that uses game-like adaptive interfaces to elicit human responses that help assess the severity of depression along time and in the context of different environmental conditions. The interactive system we are developing is called DPLAY and it can recognize, quantify, and monitor the severity of depression symptoms effectively.  DPLAY uses a humanoid robot interface and other devices to provide incentives and collect multimodal data.  It is used both as a diagnostic and as a rehabilitation tool.

We will give highlights of different computational methods that are also applicable to other conditions related to mental health, such as autism, cerebral palsy and depression. We describe adaptive dialogue systems, recognition of human expressions of depression and related emotions by the integration of audio and visual data. We also describe how we use multifaceted programmable computer games to engage the patient and the use of probabilistic database methods to tag, store and search the collected heterogeneous spatiotemporal behavioral data to improve patient-centered health and wellness services for stroke survivors.

Brief Bio
Fillia Makedon is Name Professor and Department Head of Computer Science and Engineering at the University of Texas at Arlington (UTA). She received her Ph.D. in Computer Science from Northwestern University in 1982. Between 1991-2006, she was professor of computer science at Dartmouth College where she founded and directed the Dartmouth Experimental Visualization Laboratory (DEVLAB). In 2005-2006, she was Program Director at the National Science Foundation. Prior to Dartmouth, Prof. Makedon was Assistant and Associate Professor at the Univ. of Texas at Dallas (UTD), where she directed the Computer LEArning Research Center (CLEAR). She has supervised over 20 Ph.D. theses and numerous Masters Degree theses. Makedon has received several NSF research awards in the areas of trust management, data mining, parallel computing, visualization, and knowledge management.  She has been senior investigator and co-PI of NIH, DOJ and Foundation grants. She received the Dartmouth Senior Research Professor Award, three Fulbright awards, and is author of over 300 peer-reviewed research publications. She is faculty affiliate of the Dartmouth ISTS security institute and currently directs the HERACLEIA Human Centered Laboratory, that develops pervasive technologies for human monitoring and privacy and security algorithms. She is member of several journal editorial boards and chair of the PETRA conference (www.petrae.org) and senior editor of EJETA.ORG, an electronic journal on emerging tools and applications in computing