A Framework for Cognitive Monitoring Using Computer Interactions

In this paper we describe a software architecture and methodology for monitoring cognitive performance using data from natural computer interactions in a home setting. Elders are the fastest growing demographic of new computer users, and those over the age of 75 are at risk for medically related cognitive decline and confusion. The early detection of cognitive problems allows for more effective clinical intervention. To address these issues, we have developed a suite of cognitive computer games to specifically assess various aspects of cognition. The feedback from game performance and other metrics for conventional applications allows us to detect within subject trends over time, providing a method for the early detection of cognitive decline. In addition, the real-time information on cognitive state is used to adapt the user interface to the needs of the individual user.