Data for Health in Africa Meeting
&
5th DS-I Africa Consortium Meeting
23 - 29 August 2025
CEDI Centre, University of Ghana, Accra

Ms Maria Magdalene Namaganda - Travel Awardee

Makerere University Data Science Research Training to Strengthen Evidence-Based Health Innovation, Intervention and Policy (MakDARTA) (PhD trainee)

I am a predoctoral fellow in bioinformatics and data science under Makerere University Data Science Research Training Program (MakDARTA), Uganda. My academic background includes a Master of Science in Bioinformatics and a Bachelor's degree in Biomedical Laboratory Technology, both from Makerere University. My current PhD work focuses on applying machine learning to predict HIV virological failure using routine clinical data, a project that aims to inform timely, data-driven decision-making in national ART programs. As part of my scientific leadership training, I've had the privilege to engage in international research environments, including H3Africa, as a TDR-WHO Clinical Research Leadership Fellow at the University of Oxford and a visiting graduate scholar at the University of California, San Francisco. These experiences have shaped my approach to interdisciplinary collaboration and deepened my commitment to equitable health innovation in Africa. I'm passionate about capacity building and routinely support training activities in computational biology, data literacy, and research reproducibility. I have presented my work at various global and local platforms, including the University of Oxford and have contributed to publications in data analytics, HIV drug resistance, hepatitis B epidemiology, and genomics of infectious diseases. As a trainee under DS-I Africa Training and Education programs, I am especially interested in strengthening African research collaborations and creating space for early-career African scientists to lead within the continent's data science ecosystem. My long-term goal is to integrate predictive analytics into health system workflows, advancing person-centered care in low-resource settings.