Regulatory Perspectives for AI/ML Implementation in Pharmaceutical GMP Environments
Open accessAbstract
Integrating artificial intelligence (AI) and machine learning (ML) into pharmaceutical manufacturing processes holds great promise for enhancing efficiency, product quality, and regulatory compliance. However, implementing good manufacturing practices (GMP) in regulated environments introduces complex challenges related to validation, data integrity, risk management, and regulatory oversight. This review article comprehensively analyzes current regulatory frameworks and guidance for AI/ML in pharmaceutical Good Manufacturing Practice (GMP) settings, identifies gaps and uncertainties, and proposes considerations for future policy development. Emphasis is placed on understanding regulatory expectations across various agencies, including the US FDA, EMA, and MHRA. This article examines verified case studies and pilot programs that demonstrate the successful application of AI/ML under regulatory scrutiny, as well as recent developments in regulatory frameworks and implementation strategies. Ultimately, this article emphasizes the importance of a risk-based life cycle approach and the need for advancements in regulatory science to accommodate the dynamic nature of AI/ML technologies.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In 2014, the FDA established the 'Emerging Technology Program' to evaluate innovative technologies, such as AI and ML.
“In 2014, the FDA established the ‘Emerging Technology Program’ to evaluate innovative technologies, such as AI and ML [159].”
From Genetic Insights into the Economic Toll of Cell Line Misidentification: A Comprehensive Review (2026) · cites this paper as [159]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · see citing works
Flagged first, then by citations
Research works printed but not linked: 17
- [2]Ajmal C.S. Yerram S. Abishek V. Muhammed Nizam V.P. Aglave G. Patnam J.D. Raghuvanshi R.S. Srivastava S. Innovative Approaches in Regulatory Affairs: Leveraging Artificial Intelligence and Machine Learning for Efficient Compliance and Decision-Making AAPS J. 2025 27 22 10.1208/s12248-024-01006-5 39776314 · DOI
- [4]Collier R. Singh A. Chopra S. Harnessing the AI/ML in Drug and Biological Products Discovery and Development: The Regulatory Perspective Pharmaceuticals 2025 18 47 10.3390/ph18010047 39861110 PMC11769376 · DOI
- [6]Liu Q. Huang R. Hsieh J. Zhu H. Tiwari M. Liu G. Jean D. ElZarrad M.K. Fakhouri T. Berman S. Landscape Analysis of the Application of Artificial Intelligence and Machine Learning in Regulatory Submissions for Drug Development from 2016 to 2021 Clin. Pharmacol. Ther. 2023 113 771 774 10.1002/cpt.2668 35707940 · DOI
- [24]Pantanowitz L. Hanna M. Pantanowitz J. Lennerz J. Henricks W.H. Shen P. Quinn B. Bennet S. Rashidi H.H. Regulatory Aspects of Artificial Intelligence and Machine Learning Arch. Pathol. Lab. Med. 2024 148 1185 1194 10.1016/j.modpat.2024.100609 39260776 · DOI
- [26]Yaeger K.A. Martini M. Rasooly J. Samir A.E. Louissaint A. A Systematic Review of Artificial Intelligence-Based Image Analysis in Clinical Cytopathology Cytopathology 2019 30 489 497 10.1111/cyt.12755 · DOI
- [30]Leligkou H.C. Gerogiannis V.C. Deep Transformers for Computing and Predicting ALCOA+ Data Integrity Compliance in the Pharmaceutical Industry Appl. Sci. 2023 13 7616 10.3390/app13137616 · DOI
- [34]Hedberg T.D. Manas B. Camelio J.A. Using graphs to link data across the product lifecycle for enabling smart manufacturing digital threads J. Comput. Inf. Sci. Eng. 2020 20 031011 10.1115/1.4044921 PMC7437158 32831801 · DOI
- [35]Salih A. Raisi-Estabragh Z. Boscolo Galazzo I. Radeva P. Petersen S.E. Menegaz G. Lekadir K. A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME arXiv 2023 2305.02012 10.1002/aisy.202400304 · DOI · Paper page
- [37]Ribeiro M.T. Singh S. Guestrin C. “Why Should I Trust You?”: Explaining the Predictions of Any Classifier Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining San Francisco, CA, USA 13–17 August 2016 1135 1144 10.1145/2939672.2939778 · DOI · Paper page
- [38]Rahman M.S. Rahman M.K. Kaykobad M. Rahman M.S. Interpreting artificial intelligence models: A systematic review on the application of LIME and SHAP in Alzheimer’s disease detection Brain Inform. 2024 11 4 10.1186/s40708-024-00222-1 38578524 PMC10997568 · DOI
- [41]Mirbabaie M. Stieglitz S. Frick N.R.J. Artificial intelligence in disease diagnostics: A critical review and classification on the current state-of-research guiding future research directions Health Technol. 2021 11 693 731 10.1007/s12553-021-00555-5 · DOI
- [45]ISPE GAMP 5 Second Edition: A Risk-Based Approach to Compliant GxP Computerized Systems International Society for Pharmaceutical Engineering Bucharest, Romania 2022
- [53]MilliporeSigma MilliporeSigma Launches First Ever AI Solution to Integrate Drug Discovery and Synthesis 2023 Available online: https://www.sigmaaldrich.com/US/en/collections/press/first-ever-ai-solution-to-integrate-drug-discovery-and-synthesis (accessed on 6 June 2025)
- [58]Institute of Electrical and Electronics Engineers (IEEE) IEEE Standards for Artificial Intelligence 2024 Available online: https://standards.ieee.org/initiatives/artificial-intelligence-systems/ (accessed on 6 June 2025)
- [60]Ahmed Z. Mohamed K. Zeeshan S. Dong X. Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine Database 2020 2020 baaa010 10.1093/database/baaa010 32185396 PMC7078068 · DOI · Paper page
- [61]Voronova V. Spinetti S. Kauffmann P. Heidmann J. Masson J. Stankovic A. Popovic L.J. Vukovic V. Objectivization of virus titration method in GMP-regulated environment using artificial intelligence-based classification system Eur. J. Pharm. Biopharm. 2022 181 113 121 10.1016/j.ejpb.2022.11.004 36435311 · DOI
- [62]Shah P. Kendall F. Khozin S. Goosen R. Hu J. Laramie J. Ringel M. Schork N. Artificial intelligence and machine learning in clinical development: A translational perspective NPJ Digit. Med. 2019 2 69 10.1038/s41746-019-0148-3 31372505 PMC6659652 · DOI
Cited by
Sorted by citations
Niazi, S. K. (2025) · Pharmaceuticals · doi:10.3390/ph18091271 · Cited by 61 · see citing works
Self-citationGenetic Insights into the Economic Toll of Cell Line Misidentification: A Comprehensive Review
Weiskirchen, R. (2026) · Medical Sciences · doi:10.3390/medsci14010025 · Cited by 4 · see citing works
- Authors
- Niazi, S. K.
- Affiliations
- University of Illinois Chicago (US)
- Corresponding author
- Niazi, Sarfaraz K.
- ORCID
- Niazi, Sarfaraz K.
- Venue
- Pharmaceuticals
- Publisher
- MDPI AG
- Published
- 2025-06-16
- Volume
- 18
- Issue
- 6
- Pages
- 901
- ISSN
- 1424-8247 (ISSN-L)
- PMC
- PMC12195787
- OpenAlex
- W4411384680
- Cited by
- 90
- References
- 1
- Citations by year
- 2026: 66 · 2025: 24
- FWCI
- 11.52
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Pharmaceuticals (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Health Sciences › Health Professions › Health Information Management › Healthcare Regulation
- Social Sciences › Law › Digitalization, Law, and Regulation
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- artificial intelligence, machine learning, pharmaceutical manufacturing, good manufacturing practices, regulatory compliance, data integrity, risk management, regulatory science, FDA guidance, EMA guidance, MHRA guidance, regulatory policy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
