Initial disease focus
Malaria intelligence for targeted, timely prevention.
Malaria remains one of the most significant public health challenges in sub-Saharan Africa. Epinova’s initial malaria work focuses on Nigeria, where the scale and geographic diversity of transmission make precise, data-driven targeting especially valuable.
Disease burden context
According to the World Health Organization, the WHO African Region carries the large majority of the world’s malaria cases and deaths, and Nigeria accounts for the largest share of any single country. Children under five are among the most affected. Current figures are published annually in the WHO World Malaria Report.
Environmental and geographic risk
Transmission by Anopheles mosquitoes is shaped by rainfall, temperature, humidity, standing water and land use. In a country as large as Nigeria, these conditions - and the timing of the transmission season - vary substantially between the Sahelian north and the humid south.
- Lagged rainfall and temperature effects
- Seasonality differences across ecological zones
- Urban and peri-urban transmission patterns
Predictive intelligence
Epinova is developing models that combine routine surveillance with climate and environmental data to estimate how malaria risk is likely to evolve over coming weeks and across the season, at the sub-national level where programmes plan.
Population vulnerability
Risk is not evenly experienced. Vulnerability analysis considers age structure, pregnancy, distance to care, prior intervention coverage and socio-economic factors to identify communities where malaria is likely to cause the most harm.
Intervention planning
Insecticide-treated nets, indoor residual spraying, seasonal malaria chemoprevention, case management and - increasingly - vaccination all depend on reaching the right communities at the right time. Epinova aims to connect risk intelligence directly to these operational decisions.
Predictive intelligence
How a forecast could look
Illustrative only - fictional areas and simulated values.
+1%projected change to peak within 6 weeks (simulated)
Interval widens with horizon: uncertainty grows the further ahead the model looks.
What is driving this forecast
- Rainfall (lagged 4–6 weeks)34%
- Recent case trend27%
- Temperature18%
- Net coverage gap13%
- Other factors8%
Illustrative forecast - simulated values, fictional areas. Not a real prediction.
Community risk explorer
From risk to prioritized communities
- <35
- 35–54
- 55–74
- 75+
Rank #3 of 14
Amber Ridge
- Children under 514.2%
- Travel time to facility97 min
- Net coverage65%
- Test positivity40.9%
Suggested public health investigation
Assess outreach options for remote settlements; consider community case management.
Field planning preview
- Population
- 260,583
- Field teams
- 6
- Nets to close gap
- 50,700
Community priority ranking
Illustrative explorer - fictional areas, simulated indicators and illustrative weighting.
Public health applications
Where intelligence meets action
Seasonal campaign timing
Inform the timing of chemoprevention and spraying rounds.
Net distribution targeting
Prioritize wards for mass and continuous distribution.
Commodity pre-positioning
Anticipate test and treatment demand by area.
Programme evaluation
Track coverage and trends across intervention areas.
Related platform modules
The modules involved
Sources
References
- World Malaria Report (latest edition) World Health Organization · accessed 2026-10
- Malaria fact sheet World Health Organization · accessed 2026-10
We avoid quoting point statistics that quickly become outdated. Please consult the latest edition of each source for current figures.
Bring malaria intelligence into your planning.
Talk to us about data, geographies and the decisions you need to support.


