This research uses machine learning to predict trauma demand and optimise hospital scheduling. By forecasting patient volume and dynamically allocating operating rooms, it reduces cancellations, improves efficiency, and lowers costs. The system has the potential to transform healthcare delivery by balancing emergency and elective care more effectively.

This research improves disease mapping by using mixture modeling to capture sharp spatial differences in health risk. Unlike traditional models that assume smooth patterns, this approach better identifies high-risk areas, enabling more accurate resource allocation, improved public health policy, and reduced health inequalities during disease outbreaks.

This research uses agent-based modelling (ABM) to simulate infectious disease spread in regions like Nigeria, enabling policymakers to predict outbreaks, test interventions, and allocate limited resources proactively. The low-cost modelling approach supports governments with constrained budgets and offers a sustainable, data-driven tool for preventing large-scale infections and improving global public health.

This research examines how honeybee queens adjust egg size in response to their environment. Queens in food-rich urban areas lay smaller eggs, while those in rural areas lay eggs 45% larger, producing bees that forage earlier and more often. These findings can guide beekeeping and support pollinator health, crucial for global food supply.