Abstract

Malaria remains a significant public health concern, particularly in sub-Saharan Africa, where it accounts for a high number of preventable deaths, especially among children. While vector control remains a key preventive measure, accurate and timely diagnosis is essential for effective treatment and disease management. This study proposes a machine learning-based model for the automated detection of malaria parasites using microscopic blood smear images. The system incorporates feature extraction, dimensionality reduction, and classification techniques, employing algorithms such as Naive Bayes, Support Vector Machine (SVM), and Convolutional Neural Networks (CNN). Experimental evaluation showed that the CNN model outperformed the other classifiers, achieving an accuracy of 95.0%, a precision of 94.7%, a recall of 95.3%, and an F1-score of 95.0%. The proposed solution offers a cost-effective, scalable, and reliable diagnostic aid that can support healthcare practitioners, particularly in low-resource environments, by improving diagnostic efficiency and reducing malaria-related mortality.

Statistics