Designing Rosie the Chatbot with and for Pregnant and New Mothers of Color:  a Community-Engaged Study Leveraging Artificial Intelligence and Prevention Science to Improve Maternal and Child Health Outcomes

Abstract Maternal and child health is widely recognized as a marker for a healthy society. According to the Centers for Disease Control and Prevention, the US maternal mortality rates have remained high, with over 1200 maternal deaths occurring in 2021. Recognizing that systemic racism is embedded at all levels of the public health and medical fields, intervention is needed at all levels of the socio-ecological model. Developing health communication tools for pregnant women and new parents is one leverage point in the numerous changes that must occur across public health and medical fields to achieve maternal and child equity. The current study employed focus groups to inform development of an interactive question-and-answer chatbot called Rosie. Participants ( n = 30) were all pregnant and new mothers of color residing in the United States. Data were collected in virtual focus groups ( N = 6) and transcribed verbatim. Template analysis of focus group transcripts produced three themes in women’s health information needs and preferences: (1) Pregnancy and New Parenthood Challenges, (2) Sources of Information and Support, and (3) Chatbot Design. Chatbots as a purveyor of health education information were perceived as a promising approach among our pregnant and new mothers of color participants, who had an array of needs that could be addressed by an intervention such as a chatbot. This technology has broad applicability in the health sphere and may serve as an important supplement to both clinical care and existing early childhood intervention services.