# Leveraging community health workers and a responsive digital health system to improve rates and timeliness of child well visits in the first year of life

> **NIH NIH R01** · UNIVERSITY OF SOUTH CAROLINA AT COLUMBIA · 2024 · $574,413

## Abstract

ABSTRACT 
Timely well visits are essential to ensure the wellbeing of children in their first year of life as they provide 
opportunities for delivery of preventive health interventions as well as growth monitoring. Prior studies show high 
rates of gaps and delays in the delivery of preventive health interventions, indicative of gaps in well visits, and 
reflective of broader health system and community-level barriers. For example, in Tanzania, only 68% of children 
receive key recommended preventive health interventions within their first year of life. Utilizing community-based 
health workforce capacity and leveraging rapidly evolving digital health innovations hold great potential to 
mitigate gaps in service delivery, healthcare access, and caregiver knowledge in this context.
Our multidisciplinary study team recently completed a project that demonstrated the feasibility and efficacy of 
mobile phone-based reminders and conditional financial incentives for improving rates and timeliness of routine 
preventive health interventions recommended for children. Our team has also shown that using community 
health workers (CHWs) is an acceptable approach for addressing caregivers’ knowledge gaps. Building on this 
prior work, we propose to develop and evaluate a machine learning approach that allows for the proactive 
identification of children who are most likely to experience missed or delayed child well visits. Early identification 
could allow for these children to be supported by our integrated, community-based, digital intervention to improve 
uptake and timeliness of recommended child well visits. This intervention, called “Huduma Kwa Wakati”, 
facilitates timely well visits through a CHW-led outreach and educational intervention that is supported by a 
combination of low-cost digital strategies (autonomous mobile phone-based child health protocols, reminders, 
clinic operations notifications; conditional incentive offers for adherence to visit schedules). To optimize the 
implementation and efficiency of Huduma Kwa Wakati, we propose the following specific aims:
In Aim 1, we will initially collect retrospective data on the characteristics and child well visits of 800 children in 
their first year of life. Mothers with children ages 12-23 months will be enrolled from 40 geographic clusters in 
the catchment areas of 40 health facilities in four rural districts in Mwanza and Shinyanga regions of Tanzania. 
In Year 4, 800 pregnant women in their last trimester of pregnancy will be enrolled into a parallel two-arm clusterrandomized trial. Women will be enrolled from 80 geographic clusters in the catchment areas of the same 40 
health facilities. 40 clusters will be randomized into the intervention arm; 40 clusters will be randomized into the 
control arm. Women will be followed for up to 15 months, until the child reaches 1 year of age. Child well visit 
dates will be documented using government-issued clinic cards. Concurrently, data on all c...

## Key facts

- **NIH application ID:** 10910017
- **Project number:** 5R01HD110844-03
- **Recipient organization:** UNIVERSITY OF SOUTH CAROLINA AT COLUMBIA
- **Principal Investigator:** Esther Stanslaus Ngadaya
- **Activity code:** R01 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2024
- **Award amount:** $574,413
- **Award type:** 5
- **Project period:** 2022-09-18 → 2027-08-31

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10910017

## Citation

> US National Institutes of Health, RePORTER application 10910017, Leveraging community health workers and a responsive digital health system to improve rates and timeliness of child well visits in the first year of life (5R01HD110844-03). Retrieved via AI Analytics 2026-05-24 from https://api.ai-analytics.org/grant/nih/10910017. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*