The DiffCov Study:
Mitigating the Effects of
COVID-19 Pandemic on Antenatal Attendance in Kisumu County: Leveraging
Technology and Point of Care Diagnostics to deliver Differentiated Care
(DiffCov) and integrated suite of digital tools and artificial
intelligence for antenatal pregnancy risk stratification in sub-Saharan Africa
(DiffCov study)
DiffCov was a targeted intervention
project focused on sustaining and improving maternal health services during the
COVID-19 disruptions in Kisumu County, Kenya.
The DiffCov study piloted
technology-driven, AI-supported differentiated antenatal care in Kisumu County
to counter COVID-19 disruptions. By integrating point-of-care diagnostics and
digital risk stratification tools, it aimed to sustain ANC attendance, improve
pregnancy risk identification, and enhance maternal/newborn outcomes in
resource-limited settings.
Study Overview
Conducted in Kisumu County (with
partnerships involving Bill and Melinda Gates Foundation- Sponsor, local health
departments, organizations like SWAP – Safe Water and AIDS Project – as fund
managers/grant handlers, and collaborators such as CHAMPS/ARC and ILARA
Health), the study piloted innovative approaches to address reduced antenatal
care (ANC) attendance caused by the pandemic. Key challenges during COVID-19
included fear of infection, movement restrictions, resource diversion to COVID
response, economic hardships, and facility disruptions, which led to missed
appointments, delayed care, increased home deliveries, and risks to
maternal/newborn outcomes.
Core Objectives & Innovations
The project aimed to:
●
Mitigate pandemic impacts on ANC
utilization by leveraging technology, point-of-care (POC) diagnostics, and
differentiated care models.
●
Stratify pregnant women into
high-risk and low-risk pregnancies early in ANC using an integrated suite of
digital tools and artificial intelligence (AI) for risk assessment.
●
Strengthen lower-level/primary
health facilities to deliver quality ANC (including POC testing for key
profiles like anemia, infections, etc.) for low-risk cases.
●
Enable decentralized, connected care
— allowing accurate risk identification, better resource allocation, and
improved quality/accuracy of maternal, newborn, and child health (MNCH)
outcomes.
●
Pilot agile, iterative
tools/services to close ANC gaps during COVID-19 and build long-term MNCH
system resilience in resource-limited settings across sub-Saharan Africa.
Outcomes & Significance
The study demonstrated piloting of
innovative, evidence-generating approaches to maintain ANC during crises. It
contributed to accelerating POC diagnostics and AI-driven tools in low-resource
Kenyan settings, with potential scalability for sub-Saharan Africa. It aligned
with broader efforts to enhance MNCH resilience post-COVID.
