Machine Learning Methods for Early Disease Detection




Roberts, Samuel

Journal Title

Journal ISSN

Volume Title



The use of machine learning and artificial intelligence has immense potential in healthcare management. One such application is the early detection of diseases and prediction of possible health outcomes. Although the full potential of these technologies for early detection of malaria has not been explored, the possibilities are enormous. Malaria is a severe infectious disease that affects millions of people worldwide, resulting in hundreds of thousands of deaths annually. Ineffective diagnosis and management of the disease can lead to misdiagnosis, unnecessary use of antimalarial drugs, and potentially fatal outcomes such as kidney failure or coma if left untreated. In this study, we analyzed telemetry data such as daily activity, heartbeat rate, periodic temperature, blood pressure, and electrocardiogram from pre-infection and post-malaria infection stages. Our objective was to develop a deep neural network capable of accurately classifying the preinfection stage of the Plasmodium parasite and the early liver stage using raw ECG data sampled into heartbeat observations. Our model achieved high and stable accuracy, demonstrating the potential for machine learning in the early detection of malaria.


This item is available only to currently enrolled UTSA students, faculty or staff. To download, navigate to Log In in the top right-hand corner of this screen, then select Log in with my UTSA ID.


Early disease detection, Machine learning methods, Health outcomes, Antimalarial drugs