A Resnet50-Based Machine Learning Diagnostic Model for Malaria Detection and Diagnosis

Abstract

Malaria remains a major global health challenge, particularly in sub-Saharan Africa, where it accounts for the majority of morbidity and mortality cases. Conventional diagnostic methods, such as microscopic examination of Giemsa-stained blood smears, though considered the gold standard, are time-consuming and prone to human error. This study proposes a deep learning based diagnostic approach using the ResNet50 convolutional neural network architecture for automated malaria detection. The model is trained on labelled microscopic blood smear images to classify infected and uninfected red blood cells. Image pre-processing, data augmentation, and transfer learning techniques were employed to enhance model performance. The results demonstrate that the ResNet50-based model achieves high accuracy, precision, and recall, outperforming traditional diagnostic approaches and earlier machine learning models. The proposed system offers a reliable, fast, and scalable solution for malaria diagnosis, especially in resource-limited settings. This study contributes to the growing body of research on artificial intelligence in healthcare by providing an efficient tool for early malaria detection and control.