Malarial fever is an infectious disease affecting millions worldwide. Accurate identification of malaria, especially distinguishing it from non-malarial infections, is challenging. Traditional diagnosis requires careful laboratory analysis. This study employs Convolutional Neural Networks (CNN) to detect malaria parasites in microscopy images with 97.76% accuracy. Datasets from Kaggle were used for training and testing. Model performance was evaluated using Accuracy and Loss metrics, demonstrating the effectiveness of CNN in identifying malarial parasites and their stages in blood samples. © 2024 Elsevier B.V., All rights reserved.