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.

Preconception Care

Despite increased access to prenatal care, the United States continues to rank poorly worldwide in birth outcomes. Intervention studies delivering timely, comprehensive and expanded prenatal care have not been shown to improve persistent disparities in birth outcomes. Thus, prenatal care is too little too late.

The purpose of this project is to develop a relational agent who supports women in improving their personal preconception risks in order to improve their preconception health status and improve their chances of having a healthy pregnancy and healthy baby. The system begins with a Preconception Risk Assessment of 108 health risks, followed by a year of counseling with the agent, in which a woman's preconception risks are incrementally addressed in longitudinal health behavior change counseling.

This work is in collaboration with Dr. Brian Jack at Boston Medical Center, and has been supported by the Agency for Healthcare Research and Quality (AHRQ), the Health Resources and Services Administration (HRSA), and the National Institute on Minority Health and Health Disparities (NIMHD).