Usability and Usefulness of SMS-Based Artificial Intelligence Intervention (Mwana) on Breastfeeding Outcomes in
1Independent Researcher, 10685-B Hazelhurst Dr. #40992, Houston, TX, 77043, United States.
Background:
Nigeria has one of the highest child mortality rates globally, with 111 deaths per 1000 live births. Exclusive breastfeeding (EBF) improves infant survival by providing essential nutrients and antibodies that protect against infections and diseases. Despite its benefits, EBF rates in Nigeria remain low at 29%, largely due to limited health care support and breastfeeding guidance. With the proliferation of mobile phones in Nigeria, mobile health (mHealth) interventions are being explored as scalable solutions. SMS text messaging interventions have demonstrated success in delivering behavioral interventions; yet, few use artificial intelligence (AI) for personalized breastfeeding support.
Objective:
This study evaluates the effectiveness of Mwana, an AI-powered SMS-based app, in improving breastfeeding outcomes for postpartum mothers in Lagos, Nigeria.
Methods:
Mwana was developed using TextIt for SMS integration and Meta's Wit.ai for natural language processing (NLP). The chatbot provides breastfeeding support via SMS, offering personalized tips, addressing common challenges, and connecting users to human agents when necessary. The intervention was piloted with 216 postpartum mothers recruited through local health care networks, focusing on usability, usefulness, and engagement. The study used a mixed methods approach, using structured surveys and observation to assess participant experiences at multiple intervals over a 6-month period. Primary outcomes measured were app usability, usefulness, and breastfeeding adherence.
Results:
The intervention was well-received, with high scores for both usefulness (mean 4.01, SD 1.41) and usability (mean 3.92, SD 1.35) on a 5-point scale. The majority of respondents, 57% (118/206), rated the chatbot's usefulness at the highest score of 5. Qualitative feedback statements identified areas for improvement, including enhancing AI comprehension, response times, and human-like interaction.
Conclusions:
The study highlights the potential of Mwana to improve breastfeeding outcomes in resource-limited settings, contributing to the growing body of evidence supporting mHealth interventions in maternal and child health. By leveraging personalized messaging, SMS-based delivery, and language localization, Mwana offers a scalable, accessible solution. However, challenges remain regarding AI comprehension, and further research is necessary to evaluate Mwana's effectiveness among populations not actively engaged with health care services. Future iterations will expand AI training datasets, refine NLP capabilities, and scale to broader populations.
