About Me
I am a lecturer of Health Informatics at Wollo University since September 2022. I completed my Master of Public Health (MPH) in Health Informatics at the University of Gondar. My research focuses on applying data science, spatial epidemiology, and machine learning to understand major public health challenges. I primarily work with large public data repositories, using statistical and computational methods to generate evidence on disease patterns, health service utilization, and population-level health outcomes. Through this work, I aim to uncover spatial and temporal trends that inform targeted, data-driven public health decision-making.
I have a strong research experience in maternal, child, and reproductive health. My work in this area explores determinants of maternal continuum of care, family planning outcomes, neonatal and child mortality, and
women’s health disparities. These topics remain central to my research identity, and I continue to apply modern analytical
approaches including predictive modeling, causal inference, and spatial analysis to generate actionable insights that support improved health outcomes for women and children.
Alongside my work in maternal and child health, I am increasingly focused on infectious diseases, respiratory illnesses, and environmental exposures. I am particularly interested in using GIS and
geospatial methods to map disease distribution, evaluate exposure to air pollution, and identify high-risk communities. I also apply machine learning models to predict disease outcomes and study
interactions between environmental, biological, and social determinants of health. These research directions reflect my commitment to improving population health using advanced analytic tools.
As I prepare for my future PhD studies, I am passionate about advancing the application of machine learning and AI in public health, with special emphasis on spatial epidemiology, health equity,
and infectious disease modeling. I am committed to developing analytical solutions that support evidence-based interventions, reduce health disparities, and strengthen health systems.
I also prioritize ethical and responsible use of AI to ensure fairness, transparency, and real-world impact.
I am particularly interested in explainable AI and its role in healthcare. Understanding how AI models make decisions is essential for building trust in clinical and population-health applications.
I aim to contribute to methods that enhance model interpretability, such as SHAP, feature interaction analysis, and transparent machine learning frameworks. By combining explainable AI with GIS
and epidemiological modeling, my goal is to deliver insights that are both scientifically rigorous and actionable for policymakers, clinicians, and public health practitioners.