A Korean-developed AI diagnostic system is moving from hospital trials into Benin's national malaria response. Noul, a startup specializing in digital microscopy, said Monday that its miLab MAL platform won a public procurement contract from Benin's health ministry, starting with an initial order of 20 units for hospitals treating severe malaria cases.
The system has been integrated into Benin's National Malaria Control Program (PNLP) as a point-of-care tool. The decision follows a 2025 clinical evaluation that tested the platform on 211 children suspected of severe malaria at university hospitals in the country's north and south.
Clinical results that drove the decision
Compared with manual microscopy, miLab MAL recorded sensitivity of 98.82 percent and specificity of 100 percent. The system also cut diagnostic time to under 20 minutes. Manual microscopy averaged 75 minutes per test.
Benin is among the West African countries with a high malaria burden. The World Health Organization estimated about 5.1 million cases and 9,900 deaths in the country during 2024. Africa accounts for roughly 95 percent of the global malaria burden.
"Based on the study's final report, Benin's PNLP officially recommended miLab MAL as a point-of-care device for malaria control programs in African countries," Noul said.
How the system works
Noul's platform automates the full diagnostic workflow. It handles blood-smear preparation, digital imaging, and AI analysis in sequence. The company said this standardization matters in settings with limited medical infrastructure and few trained technicians.
David Lim, Noul's CEO, said the adoption showed the technology could address frontline diagnostic gaps. The company plans to expand partnerships with medical institutions and public health programs in other high-burden regions across Africa.
Why this matters for IT and development professionals
This deployment is a real-world case of AI for Healthcare moving from pilot studies into a national health system's standard operations. For developers and IT leads working on diagnostic tools, the integration path is instructive: clinical validation data fed directly into a government procurement decision, with clear metrics on speed and accuracy.
The system's architecture - combining automated sample preparation, digital imaging, and AI classification into a single point-of-care unit - also shows how hardware-software integration can solve labor-constrained deployment environments. For teams building AI for IT & Development in regulated sectors, Benin's evaluation process offers a template for what public health buyers require before adopting autonomous diagnostic systems at scale.
Your membership also unlocks:
