"background": "Child undernutrition remains a critical public health challenge in urban informal settlements, where conventional growth monitoring is often inaccessible. Mobile health (mHealth) technologies present a potential solution for improving surveillance and caregiver support in these resource-constrained settings. ", "purpose and objectives": "This case study assessed the implementation and effectiveness of a bespoke mHealth application designed for community health workers to monitor child growth and deliver automated, tailored nutritional guidance to caregivers in Kampala's informal settlements. ", "methodology": "A mixed-methods implementation study was conducted. Community health workers used the application to record anthropometric data (height, weight, mid-upper arm circumference) during household visits. The application calculated z-scores and triggered automated, context-specific SMS advice to caregivers based on the child's growth trajectory. Effectiveness was evaluated using a pre-post design, with child growth status as the primary outcome. A linear mixed-effects model, ij = \0 + \1 ij + u{0j +, where i denotes measurement and j denotes child, was fitted to assess change in height-for-age z-score (HAZ). ", "findings": "The intervention was associated with a statistically significant improvement in mean HAZ after six months (estimated coefficient \₁ = 0. 24, 95% CI: 0. 11 to 0. 37). The prevalence of moderate stunting decreased by 8. 2 percentage points. Qualitative feedback indicated high caregiver satisfaction with the personalised advice, which was perceived as actionable within their financial and food security constraints. ", "conclusion": "The mHealth intervention demonstrated feasibility and a positive association with improved linear growth among children in an informal urban setting. It represents a scalable tool for strengthening community-based nutrition services. ", "recommendations": "Integrate the application into the national community health information system. Secure sustainable funding for data costs for health workers. Expand the
Nalubega et al. (Fri,) studied this question.