Data Challenge: Applying Machine Learning Algorithms to Antimicrobial Resistance Data

The Pfizer ATLAS dataset will be filtered to focus on pathogens and antibiotics prevalent in Kenya. Standard preprocessing methods will be applied, and models evaluated using appropriate performance metrics (e.g., accuracy, RMSE, silhouette scores). Expected findings include enhanced prediction of resistance, insights into evolving trends, and identification of resistance hotspots across regions and pathogens. These insights will support more informed decision-making in Kenya’s AMR response. This research will highlight the potential of machine learning to transform AMR data into practical public health tools, strengthening evidence-based policy and resource allocation in Kenya.