Ethical Considerations and Translational Applications of AI in Pharmacy (Theory)

AI Lifecycle, Validation & Model Auditing Overview of AI system lifecycle: data collection, preprocessing, modeling, validation, deployment, and monitoring Importance of data quality in healthcare datasets Training vs testing vs validation datasets Cross-validation (conceptual understanding) Model drift and performance degradation, data leakage in modeling Documentation practices: Documentation and reproducibility Basics of model auditing

Regulatory Framework & Explainable AI Overview of AI in regulatory submissions Explainable AI (XAI) concept Transparency and interpretability Overview of regulatory guidance on AI (EU AI Act, FDA/ CDSCO frameworks) Accountability in automated decision systems Risk-based classification of AI systems

AI in in Pharmacy Automation & Supply Chain Overview of AI in automated dispensing systems Inventory prediction models Case studies on regression-based demand forecasting, different forecasting methods Medication adherence monitoring systems AI in supply chain risk prediction Predictive analytics in pharmaceutical logistics Advantages, limitations, legal & privacy considerations of AI in pharmacy automation.

AI in in Public Health & Real-World Data Analytics Overview of real-world data sources (EHR, claims, surveillance systems) Conceptual knowledge of AI in outbreak prediction, Population-level risk modeling Regression models in epidemiology AI in vaccination forecasting Case studies: AI applications in epidemiological trend analysis (e.g. COVID-19 vaccination hesitancy, diabetes prevalence forecasting, antibiotic resistance trends etc.)

• Guided Project - Translational AI in Pharmacy Students implement a supervised ML model (regression, logistic regression, or others) using real-world pharmacy data from domains like formulation, pharmacokinetics (PK), ADR detection, quality control (QC), automation, or public health. They validate the model, analyze regulatory implications, identify ethical risks (e.g., bias, privacy), and present a structured AI implementation plan for peer/faculty review. Suggested topics (not exhaustive): ADR prediction system, stability forecasting, demand prediction, QC failure model, disease risk prediction, medication adherence Recommended Readings:
• Germanakos, P. Human-Centered AI: An Illustrated Scientific Quest.
• Matheny, M., et al. Artificial Intelligence in Health Care: The Hope, the Hype, the Promise, the Peril. National Academy of Medicine.
• Mittal, M. and Bhushan, B. Generative AI in Healthcare: Concepts, Methodologies, Tools, and Applications.
• Steyerberg, E. W. Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating. Springer.
• Steyerberg, E. W. Practical Predictive Analytics and Decisioning Systems for Medicine. Academic Pres Course Code Course Title Course Type