Online Program

A Feasibility Study to introduce an Embodied Conversational Agent (ECA) on a tablet computer into a group medical visit

Monday, November 2, 2015 : 2:45 p.m. - 3:00 p.m.

Kelly Mccue, MPH, BUMC, Boston University School of Public Health, Boston, MA
Amenah Shamekhi, PhD(c), Northeastern University, Boston, MA
Timothy Bickmore, PhD, College of Computer and Information Science, Northeastern University, Boston, MA
Denise Crooks, MPH, Family Medicine, Boston Medical Center, Boston, MA
Katherine Gergen Barnett, MD, Boston Medical Center, Boston, MA
Niina Haas, Bright Outcome, Buffalo Grove, IL
Gwynneth Johnson, Department of Family Medicine, Boston Medical Center, Boston, MA
Paula Gardiner, MD, MPH, Department of Family Medicine, Boston University Medical Center, Boston, MA
Purpose: The purpose of this pilot study is to evaluate the feasibility of introducing a tablet computer with an Embodied Conversational Agent (ECA) into an integrative medical group visit (IMGV) for patients with chronic pain and depression.


Methods: This prospective observational cohort study enrolled 20 participants who were attending an integrative medicine group visit. Patients attended a 9-session integrative medical group visit and received a tablet computer with an Embodied Conversational Agent (ECA). Participants were encouraged to interact with the ECA between groups at home. Participants completed questionnaires at baseline and 9 weeks. We recorded socio-demographics and feasibility outcomes including ECA helpfulness, satisfaction with the ECA, areas of interest for the ECA to discuss (nutrition and stress) and what could be improved about the ECA.


Results: All participants receive their primary care in inner city outpatient clinics; the average age of participants was 47; 13 participants identified as African American and 3 as Latino; 16 participants with an annual income under $30,000; 12 participants were on disability. Of the participants who completed surveys, 100% reported they used the ECA’s suggestions to reduce stress; 89% used the ECA’s suggestions to eat healthier; 67% said they were extremely confident they could continue to use the ECA’s recommendations post-study. Sixty seven percent said it was easy to talk with the ECA; 78% said they trusted the ECA very much; 44% said they would prefer the ECA over speaking with a clinician; and 89% said they would definitely recommend the ECA to a friend. Emerging themes included participants’ feeling like the ECA was a friend and someone to talk and relate to, ability to use the ECA whenever they wanted (accessibility), ability to dive deeper into curriculum at their own pace and review material with the ECA when needed.

Conclusions: It is feasible to introduce an ECA into a 9-week IMGV program for an underserved patient population with chronic pain and depression.

Learning Areas:

Chronic disease management and prevention
Diversity and culture

Learning Objectives:
Describe implementing an Embodied Conversational Agent into a group medical visit.

Keyword(s): Technology, Chronic Disease Management and Care

Presenting author's disclosure statement:

Qualified on the content I am responsible for because: I developed the content within the Embodied Conversational Agent.
Any relevant financial relationships? No

I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.