Usability and Usefulness of SMS-Based Artificial Intelligence Intervention (Mwana) on Breastfeeding Outcomes in Lagos, Nigeria: Pilot App Development Study
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".