Sergio Gago*, University of California at Irvine, Irvine, United States Nathanial Alan Benjamin, University of California at Irvine, Irvine, United States David J. Reinkensmeyer, University of California at Irvine, Irvine, United States Track: Research Presentation Topic: Mobile & Tablet Health Applications Presentation Type: Rapid-Fire Presentation Submission Type: Single Presentation Building: Sheraton Maui Resort Room: A - Wailuku Date: 2014-11-13 11:50 AM – 12:35 PM Last modified: 2014-09-04

If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL).

Background: The ability of a person to perform the physical activities of daily life can be significantly impaired after a stroke or a spinal cord injury due to a loss of hand function. The impact of loss of function of hand and paralysis often leads to drastic lifestyle changes and psychological effects, including depression and decreased motivation. The quality and effectiveness of the physical training for rehabilitation have a direct impact on the probability of success in recovering motor skills and the functional independence of patients after an injury. The lack of support and motivation in training at home leads to a high rate of therapy abandonment. A therapist who supports people training at home can address this problem. However, the expense of this service can be prohibitive. The development of affordable computer based tools for rehabilitation training of the hand can make incentives and support accessible to all patients in their rehabilitation training tasks.

Objective: Affective communication such as encouragement, confidence and friendship can be easily transmitted by a therapist. However, previous studies have suggested that affective communication for supporting tasks can also be transmitted by a virtual embodied agent. The goal of this study is to evaluate the feasibility and acceptability of a newly developed mobile application consisting of a virtual character – RIVA (Realistic and Interactive Virtual Agent) – to provide feedback and motivate patients through verbal communication and facial expression during home training for rehabilitation. The training device to which RIVA is applied is an electronic glove – the MusicGlove – which is a wearable device with fabric sensors that detects finger grips for hand movement retraining using a serious game.

Methods: RIVA is an animated character-based tablet application that tracks patients’ performance with rehabilitation technologies, analyzing the performance to provide verbal feedback. For the MusicGlove-based training, the animated character interacts with patients, providing support and encouragement in real time. The training task consists in users practicing hand movement by playing along to songs displayed in an interactive musical computer game similar to Guitar Hero. The feedback RIVA provides to patients is both verbal and nonverbal, in the form of facial expressions. The information collected by RIVA is sent to a dedicated server that allows physicians to monitor and respond to patients’ performance in real time. Finally, using a randomized controlled trial design, we will examine the efficacy of RIVA in assisting and encouraging individuals training with a MusicGlove, comparing it to MusicGlove-based training without RIVA.

Results: The research is in progress. A first prototype of RIVA has been developed and integrated to the MusicGlove software using a cloud server and a background service that allow constant communication between both programs during the user’s training.

Conclusions: Virtual agents could couple with rehabilitation devices to improve motivation for home-based therapy.

The goal of the present presentation is to give an overview of the functionality and application of RIVA in clinical and research settings for this purpose. Directions for future development and generic issues will be discussed.