Bridging Guidance and Regulation: Interpreting the Draft Annex 22 on Artificial Intelligence in GMP Manufacturing
Clinical Snapshot
PICO Framework
| P — Population | Pharmaceutical manufacturing facilities implementing AI systems under GMP regulations |
| I — Intervention | EMA Draft Annex 22 regulatory framework for AI implementation |
| C — Comparator | Current continued process verification (CPV) practices and existing regulatory guidance |
| O — Outcomes | Regulatory compliance, AI governance frameworks, operational implementation challenges, and harmonization with CPV principles |
Bottom Line
This regulatory review provides essential guidance for pharmaceutical manufacturers preparing for AI implementation under emerging European regulations. The authors successfully bridge the gap between draft EMA Annex 22 requirements and practical implementation through continued process verification frameworks. Key contributions include structured approaches to AI validation, lifecycle management, and human oversight requirements. While based on draft guidance that may evolve, the framework offers valuable preparation for regulatory compliance. Australian manufacturers should monitor TGA alignment with these European standards, as similar requirements are likely to emerge locally. The work is particularly valuable for quality assurance professionals and regulatory affairs teams planning AI integration in manufacturing processes. However, implementation will require significant investment in validation infrastructure and regulatory expertise, making this more immediately applicable to larger pharmaceutical operations.
Key Findings
Effect Size: Not applicable - regulatory guidance interpretation
Primary Outcome: Structured framework for AI implementation in GMP manufacturing aligned with EMA Draft Annex 22
Nnt Or Sensitivity: Provides operational roadmap for regulatory compliance with risk-based AI validation approach
Clinical Application
High feasibility for large pharmaceutical companies with regulatory expertise; may require significant investment in validation infrastructure Relevant for Australian pharmaceutical manufacturers as TGA often aligns with EMA guidance; principles applicable to local GMP requirements and quality systems Pharmaceutical manufacturers implementing AI systems in GMP-regulated environments, particularly in Europe
Abstract
This paper builds upon Stassen et al. (2025), "Recommendations for Artificial Intelligence Application in Continued Process Verification," to provide a detailed interpretation of the European Medicines Agency (EMA) Draft Annex 22-Artificial Intelligence (July 2025 draft) within the context of GMP-regulated pharmaceutical manufacturing. The draft annex introduces a structured, risk-based framework for artificial intelligence (AI) adoption, defining expectations for intended use, validation, life cycle management, explainability, and human-in-the-loop (HITL) oversight. This manuscript examines the alignment between Annex 22 provisions and continued process verification (CPV) recommendations, identifies convergence, operational challenges, and areas for future development, and proposes a roadmap for compliant AI implementation. Conceptual frameworks and workflow illustrations depict the harmonization of CPV principles, life cycle management, and emerging regulatory expectations. This review supports harmonized AI governance and readiness for Annex 22 compliance across the pharmaceutical sector.
References
- 1.Stassen, M., Schmucki, M., Valero, F., & Manzano, T. (2026). Bridging guidance and regulation: Interpreting the draft annex 22 on artificial intelligence in GMP manufacturing. PDA Journal of Pharmaceutical Science and Technology. https://doi.org/10.5731/pdajpst.2025-000076.1
Related Research
Journal of pharmacokinetics and pharmacodynamics
Diffusion models for virtual populations and pharmacometric simulations
1 Aug 2026
Journal of chemical information and modeling
Reinforcement Learning-Driven Multiproperty Optimization in Molecular Design Using Multicontext Transcriptome Data
29 July 2026
Journal of computer-aided molecular design
Artificial intelligence in impurity prediction: current landscape, challenges, and future directions
23 July 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service