2 results
African Journal of Health Informatics
Emeka Okafor, Amina Yusuf, Chukwuemeka Nwachukwu
This study investigates the application of supervised machine learning algorithms — including Random Forest, Support Vector Machines, and Gradient Boosting — to the early diagnosis of malaria using clinical and haematological data collected from tertiary hospitals across Sub-Saharan Africa. A dataset of 14,200 patient records was used for training and evaluation. The proposed ensemble model achieved a sensitivity of 94.3% and specificity of 91.7%, outperforming conventional microscopy-based screening in resource-constrained settings. The findings suggest that low-cost, deployable ML pipelines can significantly reduce diagnostic delays and improve patient outcomes in endemic regions.
Nigerian Journal of Technology and Innovation
Ngozi Adeyemi, Babatunde Olawale
Academic credential fraud remains a persistent challenge in Nigeria, with significant consequences for institutional trust and graduate employability. This paper proposes a permissioned blockchain architecture — built on Hyperledger Fabric — to enable tamper-proof issuance and real-time verification of academic certificates. A prototype was deployed in collaboration with three Nigerian universities and evaluated across 2,400 credential verification requests. The system achieved near-instant verification (mean latency: 1.2 s) with zero false positives, compared to a mean turnaround of 11 business days for conventional verification channels. Policy implications for national adoption are discussed.
© 2026 Laravel. All rights reserved.
Open Access · Peer Reviewed · ISSN Platform
