MALARIA intelligence platform powered by AI developed in Nigeria, with hopes to move malaria surveillance from retrospective reporting to real-time prediction. The platform integrates epidemiological, climate, environmental and geospatial data to identify transmission risks before outbreaks emerge.
AI Platform to Predict Malaria Risk and Improve Public Health Decisions
Previously, surveillance relied on routine case reporting after infections occur. With the integration of multiple datasets, approximate 435,000 localised clusters across Nigeria are analysed and generates predictive risk maps rather than reporting existing cases. This can help to identify areas where environmental conditions suggest outbreaks are likely before case numbers increase.
The new intelligence system highlights areas where disease may be under-reported or healthcare access is limited. From this, public health decisions can be stratified such as mosquito net distribution, vaccine deployment, surveillance team placement, awareness campaigns, and resource allocation. Rather than one-off interventions, the platform can support continuous monitoring and assess lasting impact.
Technology Could Expand Beyond Malaria Surveillance
With Nigeria as the first implementation site, there is planned expansion into the Democratic Republic of the Conge. Technology could be adapted for use in other disease areas such as Ebola, Lassa fever, and emerging outbreaks of infection. The challenges remain in fragmentated datasets, computing requirements, internet and infrastructure limitations, and integration into existing health systems.
The authors emphasize the success of the platform as dependent on usability by frontline healthcare workers and embedding AI into routine public health decision-making rather than creating standalone technology.
Rather than replacing clinicians or epidemiologists, the platform functions as a clinical decision-support and public health intelligence tool, using AI to identify emerging malaria risks earlier and enable more targeted, data-driven interventions. This represents a shift from reactive surveillance to predictive disease intelligence, with potential applications across multiple infectious diseases.
Reference
Muzaki S. Building a malaria intelligence system for real-time prediction and data-driven intervention planning. J Med Internet Res. 2026;28:e105472.
Featured Image: Andrey Popov on Adobe Stock
- Author:
