Neonatal mortality (defined as death in the first 28 days of life) remains unacceptably high in sub-Sarahan Africa. The concentrated risk of neonatal illness in the first weeks of life and its potential to rapidly deteriorate means that expanding mothers' access to timely information and support during this period is critical to reducing neonatal mortality. This cluster-randomized control trial aims to integrate a 2 way interactive SMS text messaging intervention into existing digital infrastructure supporting Community Health Volunteer (CHV) workflow in Western Kenya (dCHT) to enable remote communication by mothers with CHVs between home visits.

In Kenya, the neonatal mortality rate is 22.6 per 1000 live births, ranking among the countries with the highest number of neonatal deaths (~40,000 per year). Community health volunteers (CHVs) are a large cadre of lay health workers whose role is to promote access to preventative care and treatment in resource-limited settings. In Kenya, CHVs conduct monthly home visits to pregnant and postpartum women to provide education and screen for complications. Several counties in Kenya have adopted a digital community health toolkit (dCHT) that supports CHV workflow by tracking clients, managing tasks, and guiding home visits. Even so, the concentrated risk of neonatal illness in the first weeks of life and its potential to rapidly deteriorate mean that even monthly home visits leave mothers and neonates in need of on-demand support.

Our team developed an interactive SMS text messaging intervention, Mobile WACh Neo (NEO), that connects mothers with healthcare workers remotely in the high-risk period immediately following birth to improve maternal and neonatal health. NEO sends automated, theory-based, actionable daily messages that systematically guide mothers to evaluate neonatal danger signs, and facilitates real-time dialogue with a healthcare worker to triage medical concerns and augment maternal social support.

The overarching goal of this project is to integrate NEO interactive SMS into the existing digital infrastructure supporting CHV workflow in Western Kenya (dCHT) to enable remote communication by mothers with CHVs between home visits. This is a cluster-randomized control trial consisting of 20 facility clusters (10 control, 10 intervention) in Western Kenya.

AIM 1: Employ a human-centered design approach to develop a NEO interactive SMS module in the dCHT, named CHV-NEO.

AIM 2: a) Evaluate CHV-NEO's impact on neonatal mortality, b) clinic visit attendance, and caregiver provision of essential newborn care (cord care, thermal care and initiation of breastfeeding), in a pragmatic cluster-randomized trial.

AIM 3: a) Determine the effect of CHV-NEO on CHV and supervisor workflow, and b) evaluate determinants of CHV-NEO's acceptability, adoption and fidelity of use.

Inclusion Criteria:

• Pregnant
• 26-36 weeks gestation
• Daily access to a mobile phone (own or shared)
• Willing to receive SMS
• Age ≥14 years
• Able to read and respond to text messages in English, Kiswahili or Luo, or have someone in the household who can help
• Receiving antenatal care at study facility
• Plan to be in the area for at least 3 months postpartum

Exclusion Criteria:

• participating in another study
• previously participated in this study

Data from CHV-NEO will be available at end of the project by contacting the study team at the University of Washington (chv-neo@uw.edu) or accessing data on GitHub.

At the end of the project.

After publication of original data, data may be shared upon request with other investigators at academic, non-profit, or Kenyan government institutions in a limited data set. The final dataset will be stripped of identifiers prior to release for sharing. Investigators requesting access to data must sign a data-sharing agreement that provides for a commitment to: (1) using the data only for research purposes and not to identify any individual participant; (2) securing the data using appropriate computer technology; (3) not sharing the data with third parties, and (4) destroying or returning the data after analyses are completed. We reserve the right to limit data provided to outside investigators if we believe there is a possibility of deductive disclosure of subjects with unusual characteristics.