This chapter highlights the importance of explainable artificial intelligence (AI) and responsible application of AI and machine learning (ML) in advancing public health. It introduces core interpretability methods such as Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), with demonstrations in R that show how these tools make complex models more transparent and understandable to clinicians, policymakers, and patients. The chapter also examines key ethical challenges, including bias, privacy, and reproducibility, emphasizing why accountability and fairness are critical in applied health research. By integrating technical interpretability techniques with governance strategies, the chapter provides readers with practical skills and conceptual frameworks to ensure AI systems remain trustworthy, transparent, and aligned with public health goals.