Assess undergraduate students' understanding of technical principles and societal implications of machine learning model interpretability in clinical diagnostics. Scope includes key concepts (intrinsic vs. post-hoc interpretability), common methods (feature importance, SHAP, LIME), evaluation trade-offs with accuracy and robustness, and ethical, legal, and policy issues such as trust, bias, informed consent, accountability, and implications for clinical workflow and patient safety; students should analyze brief clinical scenarios and discuss method selection and mitigation strategies.