Relational Agents are computer agents designed to form long-term, social-emotional relationships with their users. We are investigating the use of these agents in task domains in which human-agent relationships actually improve task outcomes, such as in coaching, counseling, psychotherapy and healthcare.

Pre-Surgery Counseling by Relational Agent

Patients are often poorly informed about their options for surgery, such as alternatives for anesthesia, and often arrive at the hospital improperly prepared for their procedure.

In collaboration with the Dept. of Anesthesiology at Massachusetts General Hospital, we have developed a relational agent to counsel patients on their options for anesthesiology, including the risks and befits of each, what to expect before, during, and after surgery, and how to prepare before coming to the hospital. The counseling content is tailored for each patient by an anesthetist, and unresolved questions and issues raised during the session are printed out for follow up with the anesthetist after the agent counseling session. The system is currently undergoing clincial trial with 150 patients, evaluating impact of the agent on patient readiness for surgery and satisfaction, compared to standard care.