Exploring the implementation of an SMS-based digital health tool on maternal and infant health in informal settlements

Document Type

Article (peer-reviewed)

Publication Date



Background: The rapid urbanization of Kenya has led to an increase in the growth of informal settlements. There are challenges with access to maternal, newborn, and child health (MNCH) services and higher maternal mortality rates in settlements. The Kuboresha Afya Mitaani (KAM) study aimed to improve access to MNCH services. We evaluate one component of the KAM study, PROMPTS (Promoting Mothers through Pregnancy and Postpartum), an innovative digital health intervention aimed at improving MNCH outcomes. PROMPTS is a two-way AI-enabled SMS-based platform that sends messages to pregnant and postnatal mothers based on pregnancy stage, and connects mothers with a clinical help desk to respond and refer urgent cases in minutes. Methods: PROMPTS was rolled out in informal settlements in Mathare and Kawangware in Nairobi County. The study adopted a pre-post intervention design, comparing baseline and endline population outcomes (1,416 participants, Baseline = 678, Endline = 738). To further explore PROMPTS's effect, outcomes were compared between endline participants enrolled and not enrolled in PROMPTS (738 participants). Outcomes related to antenatal (ANC) and postnatal (PNC) service uptake and knowledge were assessed using univariate and multivariate linear and logistic regression. Results: Between baseline and enldine, mothers were 1.85 times more likely to report their babies and 1.88 times more likely to report themselves being checked by a provider post-delivery. There were improvements in moms and babies receiving care on time. 45% of the 738 endline participants were enrolled in the PROMPTS program, with 87% of these participants sending at least one message to the system. Enrolled mothers were 2.28 times more likely to report completing four or more ANC visits relative to unenrolled mothers. Similarly, enrolled mothers were 4.20 times more likely to report their babies and 1.52 times more likely to report themselves being checked by a provider post-delivery compared to unenrolled mothers. Conclusions: This research demonstrates that a digital health tool can be used to improve care-seeking and knowledge levels among pregnant and postnatal women in informal settlements. Additional research is needed to refine and target solutions amongst those that were less likely to enroll in PROMPTS and to further drive improved MNCH outcomes amongst this population.