Improving Maternal and Child Health Through Data Driven Segmentation

With less than five years left until 2030, there is a need to accelerate improvements in maternal and child health globally. Population wide one size fits all approaches to health are failing to address the diverse needs of women and their children especially in settings with weak health and social systems. Currently, implementers are lacking the possibility to identify the populations most at risk of poor reproductive, maternal, neonatal and child health outcomes and understand their complex and intersecting health needs from social determinants of health perspective. There is a need for novel strategies that can ensure that those most vulnerable are reached by the health system.

The proposed session engages participants in an interactive dialogue and learning experience around the socio-economic, cultural and environmental vulnerability to poor health across the life course of women. It will demonstrate how a mixed method segmentation approach can be used as a cost-efficient strategy tool for policy making and intervention design.

After an introductory overview by the moderator, session guides will support participants in moving through a process of empathy building through qualitative data to AI assisted decision making with quantitative data using segmented population data. Government representatives from Senegal and Ethiopia will provide short concrete policy examples on how such segmentation approaches have influenced policy. Participants will be able to experience the benefit of using mixed method data in policy problem framing and strategy design, allowing for a more precise approach to reaching vulnerable populations with the right interventions. The session will end with the moderator summarizing key takeaways and policy insights that can be used for transformative action.