Abaris — Aware Home Research Institute at Georgia Tech

What is Abaris?

Abaris is a fully functioning prototype capture and access application to support therapists who perform Discrete Trial Training therapy, a current best practice intervention for children with autism.

Formative work on Discrete Trial Training

We have studied extensively the domain of discrete trial training through participant observation and interviews.

Discrete Trial Training has the following characteristics:

One-on-one, repetitive trials
Very data-intensive
Involves a lot of handwritten, paper-based records
Team meetings by therapists working with same child to discuss progress

The high amount of manual data collection and recording can lead to inaccuracies in the data, which can affect a team's analysis, and draws the attention of the therapist away from the child.

The Abaris project attempts to address some of these deficiencies in order to increase the accuracy of data collection and reduce the amount of time the therapist spends doing manual calculations. Additionally, since Discrete Trial Training is almost always carried out by a team of therapists for one particular child, Abaris attempts to facilitate the communication among teams to ensure that each member is performing the therapy consistently.

Example of some of the paper forms used by therapists in DTT. The left shows the data collection sheet with manual calculations, and the right shows the hand-made graphs made by therapists to show trends in the child's development.

The Abaris System

We have developed a prototype using an Anoto digital pen and Nexidia voice indexing technology that allows for easy indexing of trials into a video session. The paper based form is very familiar to the paper ones the therapists previously used. The capture side of the interface allows for easier capture and less paperwork on a session by session basis. Abaris then provides an access interface for therapists and lead therapists to go back and review how the child is doing, look for inaccuracies, and easily show problem areas to other therapists for evaluation.

The above shows a therapist using a digital pen and voice recognition during a therapy session to index into a video of the session.

Abaris capture interface. The left images shows the Anoto digital pen and a printed form. The right image shows the simple computer program used by the therapist to sync their information with the database and access side.

Abaris access interface, data view mode. Therapists can view graphs of the child's progress, and use the mouse on various data points to get more information about a particular session.

Abaris access interface, session viewer mode. If the therapist wants more information on a session, he or she can bring up the video and data sheet for a particular session or compare multiple sessons. A time line across the bottom shows the different trials throughout the session with the timestamp guesses made by voice recognition and the digital pen.

Deployment

We have deployed Abaris in a pilot study for four months with one particular therapy team in one child's home.

Abaris was used in:

52 therapy sessions
- 3869 trials
- 45.1 hours of recorded video
6 team meetings

Therapists found the capture interface to be seamless in their therapy sessions, and self-reported times indicate a decrease in the amount of time spent in paperwork. The therapists found the access system very useful in facilitating discussions. In an average meeting, Abaris was used 6 times to view videos and took up 20.4% of the meeting time. The ability for everyone to view data and videos via a projecter helped others to contribute to data analysis and compare techniques across therapists.

We conducted an in-depth analysis of the collaborative aspects of Abaris and found an increased reliance on more objective measures during meetings, such as videos and data sheets, and also saw a significant increase in the level of collaboration amongst caregivers.

What is our future direction?

We are working with the Experimental Education Unit at the University of Washington toward a new system for more general use in school settings.
We would like to integrate the use of biometric sensors with videos of therapy session to see if various biological factors influence the child's performance in therapy.
We would like to evaluate how Abaris impacts the therapy itself, or use it as a took to help behavior analyists evalute techniques in DTT.

Publications

Kientz, J.A., G.R. Hayes, G.D. Abowd, and R.E. Grinter. From the War Room to the Living Room: Decision Support for Home-based Therapy Teams. To appear in the proceedings of CSCW 2006. Banff, Alberta, Canada. 2006. (Nominated for Best Paper Award)
Kientz, J.A. and G.D. Abowd. Collective Remembering in Evidence-Based Care. Workshop on Collective Remembering at CHI 2006 (April 22-27, Montreal, Canada), 2006.
Kientz, J.A., Boring, S., Abowd, G.D., Hayes, G.R. Abaris: Evaluating Automated Capture Applied to Structured Autism Interventions. In the Proceedings of UBICOMP 2005: The 7th International Conference on Ubiquitous Computing. September 11-14, Tokyo, Japan, 2005. ( PDF)
Boring, S., Kientz, J. A., Abowd, G. D., Hayes, G. R. Abaris: Capture and Access for Structured One-on-One Educational Settings. In the Extended Abstracts of UBICOMP 2005: The 7th International Conference on Ubiquitous Computing, to appear. September 11-14, Tokyo, Japan, 2005. ( PDF)
Hayes, G.R., Kientz, J.A., Truong, K.N., White, D.R., Abowd, G.D., Pering, T. Designing Capture Applications to Support the Education of Children with Autism. In the Proceedings of Ubicomp 2004, September, Nottingham, England, 2004. ( PDF)