This study aimed to produce a computerized identification system for diagnosing malaria disease using Convolutional Neural Network (CNN) models. This endeavor is aligns with the goals of the Sustainable Development that are associated with health and well-being. Inspired by recent research highlighting the potential of CNN in medical image analysis, our proposed CNN design successfully categorized photos of malaria disease into two distinct groups. This significant achievement has made notable contributions towards the progress of economical and easily accessible healthcare. The model underwent thorough training for 20 epochs with a dataset of 43,390 photos. As a result of this extensive training, the model achieved a notable accuracy rate of 94%. This technological improvement aligns with promoting innovation and infrastructure for sustainable development. The implications of the study's findings are significant for global health, as they demonstrate the CNN model's ability to analyze complex patterns effectively. This ability has the potential to assist in the timely identification and management of medical conditions, consequently making a valuable contribution towards the goals of poverty elimination and the reduction of inequalities. Moreover, by addressing health disparities, these advancements can have a positive impact on societal well-being. This study highlights the significance of technology in promoting the progress of healthcare, thereby contributing to the broader objectives of sustainable development.