• Suraj Ramesh Jamadar
• Vivek Suresh Ingle

Abstract : Quality risk management (QRM) is the cornerstone of pharmaceutical manufacturing oversight, guiding decisions that protect patients from harm arising from variability in materials, processes, equipment, and human performance. For nearly two decades, QRM in the industry has been anchored in the International Council for Harmonisation's ICH Q9 guideline, operationalised through structured, largely manual tools such as Failure Mode and Effects Analysis (FMEA), Hazard Analysis and Critical Control Points (HACCP), and Fault Tree Analysis (FTA). While this traditional model has brought discipline and harmonisation to risk decision-making, it is inherently periodic, retrospective, and dependent on subjective expert scoring. The emergence of artificial intelligence (AI), machine learning (ML), the Internet of Things (IoT), and digital twin technology is now enabling a parallel model often described as dynamic or continuous QRM, in which risk is monitored, scored, and mitigated in near real time as manufacturing data are generated. This review synthesises the peer-reviewed and regulatory literature to compare traditional and AI-based dynamic QRM approaches across the dimensions of methodology, data usage, timeliness, objectivity, scalability, regulatory acceptance, and implementation cost. The review finds that AI-based dynamic QRM offers substantial gains in early-warning capability, predictive accuracy, and consistency, but introduces new categories of risk related to data integrity, model transparency, validation burden, and cybersecurity that traditional QRM does not encounter to the same degree. The evidence suggests that the two paradigms are not mutually exclusive: current regulatory thinking from the U.S. Food and Drug Administration (FDA), the European Medicines Agency (EMA), and the International Society for Pharmaceutical Engineering (ISPE) points toward a hybrid model in which AI-enabled analytics augment, rather than replace, the ICH Q9(R1) risk management framework, with human oversight retained as a decisive control point. The review concludes with recommendations for regulatory science, workforce development, and validation strategy needed to responsibly scale dynamic QRM across the pharmaceutical manufacturing sector.

"Comparative Evaluation of Traditional Quality Risk Management and AI-Based Dynamic Quality Risk Management in Pharmaceutical Manufacturing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 9, page no.d238-d252, September-2026, Available :http://www.jetir.org/papers/JETIR2609327.pdf

"Comparative Evaluation of Traditional Quality Risk Management and AI-Based Dynamic Quality Risk Management in Pharmaceutical Manufacturing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 9, page no. ppd238-d252, September-2026, Available at : http://www.jetir.org/papers/JETIR2609327.pdf