Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{209453,
        author = {Kulshreshth Sharma and Gurmeet Chhabra and Lalit Dhakar and Ankita Bhadoriya and Nimita Manocha},
        title = {Automation-Assisted Pharmaceutical Annual Product Quality Review: An Integrated Framework for Digital Data Systems, AI-Driven Trend Analysis, and Human Oversight in GMP Compliance},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {5},
        pages = {2784-2793},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=209453},
        abstract = {Since 1978, the regulatory authorities have mandated pharmaceutical companies to significantly evaluate the quality of their drug product at least once a year, according to the ICH Q7 guideline and the Good Manufacturing Practice (GMP) guideline of the European Union. The approach to performing this Annual Product Quality Review is largely manual, however, with the data being distributed across laboratory, quality, enterprise and manufacturing. The aim of this review is to gather the literature from the period 2020-2026 and show the necessity of a new model that is not independent that will be able to digitalize APQR. It introduces a hybrid data integration architecture model, a 5-layer hierarchical model for automated analytical functions, a layer for anomaly detection by machine learning algorithms at the top, an AI-aided report generation model based on the validated data obtained from the sources and a 3-tier model for human oversight based on the interpretive complexity of the data and the impact of Good Manufacturing Practice (GMP) on the function. The oversight model conforms to the existing validation models including risk-based Computer Software Assurance and Good Automated Manufacturing Practice, as well as the validation requirements for electronic records in 21 CFR Part 11 and European Union Annex 11. Although there are many published reports and manuals, there is no peer-reviewed literature that assesses the artificial-intelligence tools that are actually being used specifically in the APQR realm of work, especially those using NLP to analyze the story of the deviations and corrective actions. Most critically, aside from the time saving, no study could be found that proved that using automation to aid APQR for the purpose of finding quality trends is effective. The five research priorities that are suggested to address this gap are benchmark datasets, comparative outcome studies, validated evaluation methods, model lifecycle governance and better collaboration between industry and regulators.},
        keywords = {Annual Product Quality Review; APQR digitalization; automation-assisted quality review; pharmaceutical artificial intelligence; human oversight boundary; Computer Software Assurance; GAMP 5; data integration architecture},
        month = {October},
        }