Accepted for/Published in: JMIR Formative Research
Date Submitted: Aug 6, 2024
Date Accepted: Apr 30, 2025
Usability and Usefulness of SMS-Based AI Intervention (Mwana) on Breastfeeding Outcomes in Lagos, Nigeria: A Pilot Study
ABSTRACT
Background:
Nigeria has one of the highest child mortality rates in the world. Exclusive breastfeeding is a proven intervention to improve child survival, but many mothers face difficulties with breastfeeding due to insufficient support from the healthcare system. The widespread use of mobile phones has been recognized as a potential way to deliver scalable health interventions. However, there has been limited application of artificial intelligence (AI) technology delivered via SMS to support breastfeeding practices.
Objective:
The objective of this study was to evaluate the effectiveness of an SMS-based artificial intelligence application in improving breastfeeding outcomes for mothers in Lagos, Nigeria.
Methods:
Mothers were recruited through partnerships with healthcare facilities in Lagos. Participants received breastfeeding support and guidance through an AI-powered SMS application over the course of their breastfeeding journey. Data on usability and usefulness was collected.
Results:
A total of 216 mothers participated in the study. The intervention was well-received, with high ratings for both usefulness (mean score of 4.01) and usability (mean score of 3.92). Cultural compatibility was ensured through translations into Hausa and Swahili, while widespread mobile technology contributed to its effectiveness as a breastfeeding tool in resource-limited environments.
Conclusions:
The findings suggest that SMS-based artificial intelligence applications can be an effective tool to improve breastfeeding outcomes in Nigeria. Our qualitative analysis suggests that while the design and concept of the app are promising, the AI model requires extensive further training to be fully effective. Future research should refine the AI model for this mobile health intervention and expand to additional populations to ensure effectiveness and sustainability in diverse settings.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.