Sage Journals: Discover world-class research

Abstract

There has been great progress in both Process Analytical Technology (PAT) analytics and process validation within pharmaceutical manufacturing. Advanced analytical techniques and monitoring instrumentation have resulted in increases in the amount and type of data generated. Artificial intelligence (AI) tools are now dramatically improving our capability to both govern and employ these data. One example of AI’s power is its capability to advance the third stage of process validation lifecycle in drug manufacturing: continued process verification (CPV). Governing and standards bodies are working to ensure the safety, efficacy, and quality of products employing AI and AI-driven PAT tools within the lifecycle framework of Good Automated Manufacturing Practice (GAMP 5). Despite this work, and published case studies, sponsors remain in need of generic, platform guidance to direct the practical validation of specific AI-enabled systems in a particular GxP application.

Get full access to this article

View all access options for this article.

References

ICH Harmonised Tripartite Guideline. Pharmaceutical development Q8(R2). Available from: https://database.ich.org/sites/default/files/Q8_R2_Guideline.pdf [Last accessed: October 15, 24].

Redica Systems. What is quality intelligence? How is data governance a key enabler? January 16, 2024. Available from: https://redica.com/what-is-quality-intelligence-how-is-data-governance-a-key-enabler/ [Last accessed: October 15, 24].

Davidson

. Advancing the transition to computer software assurance: Responding to the FDA draft guidance for production and quality system software. FDLI Update Available from: https://www.fdli.org/2023/05/advancing-the-transition-to-computer-software-assurance/ [Last accessed: November 30, 24]

21 CFR 820.70 - production and process controls. Available from: https://www.govinfo.gov/app/details/CFR-2012-title21-vol8/CFR-2012-title21-vol8-sec820-70 [Last accessed: October 15, 24].

EudraLex. The rules governing medicinal products in the European Union. Volume 4. Good manufacturing practice medicinal products for human and veterinary use. Annex 11: Computerised systems. Available from: https://health.ec.europa.eu/system/files/2016-11/annex11_01-2011_en_0.pdf [Last accessed: October 15, 24].

FDA. Pharmaceutical quality for the 21st century. Available from: https://www.fda.gov/media/77391/download [Last accessed: October 15, 24].

U.S. Food and Drug Administration (FDA). Guidance for industry: Process validation: General principles and practices. Available from: https://www.fda.gov/files/drugs/published/Process-Validationeneral-Principles-and-Practices.pdf [Last accessed: November 30, 24].

GAMP 5 guide. 2nd ed Available from: https://ispe.org/publications/guidance-documents/gamp-5-guide-2nd-edition [Last accessed: October 15, 24].

The EU artificial intelligence act. Available from: https://artificialintelligenceact.eu/ [Last accessed: October 15, 24].

10.

ISO. Information technology — artificial intelligence artificial intelligence concepts and terminology. ISO Standard 22989:2022. Available from: https://www.iso.org/standard/74296.html [Last accessed: October 15, 24].

11.

U.S. Food and Drug Administration (FDA). Discussion paper. Available from: https://www.fda.gov/media/165743/download [Last accessed: October 15, 24].

12.

FDA-PQRI AI workshop program. Available from: https://pqri.org/wp-content/uploads/2023/09/FDA-PQRI-AI-Workshop-Program-FINAL.pdf [Last accessed: October 15, 24].

13.

Islam

. Best practices for machine learning model monitoring. MarkTechPost. Available from: https://www.marktechpost.com/2023/01/22/best-practices-for-machine-learning-model-monitoring/ [Last accessed: November 30, 24].

14.

ISO/IEC DIS 42001:2022. Information technology - Artificial intelligence - Management system. 2022: Available from: https://webstore.ansi.org/standards/iso/isoiecdis420012022 [Last accessed: October 15, 24].

15.

Blumenthal

, Heitmann

, Münch

, et al. ChatGPT, BARD, and other large language models meet regulated pharma. Pharm Eng, 2023; 43(4):58–64.

16.

Jiang

, Huang

, Zhang

, et al. Smart miniature mass spectrometer enabled by machine learning. Anal Chem, 2023; 95(14):5976–5984; doi: 10.1021/acs.analchem.2c05714

17.

Rathore

, Winkle

. Quality by design for biopharmaceuticals. Nat Biotechnol, 2009; 27(1):26–34; doi: 10.1038/nbt0109-26

18.

Whitford

, Manzano

. AI applications for multivariate control in drug manufacturing. In: A Handbook of Artificial Intelligence in Drug Delivery. ( Philip

; eds). Cambridge: Academic Press; 2023; p. 55–88 doi: 10.1016/C2020-0-03058-6

19.

Konnaiyan

. Artificial Intelligence (AI) Based Continued Process Verification (CPV). ISPE iSpeak Blog. 2023. Available from: https://ispe.org/pharmaceutical-engineering/ispeak/artificial-intelligence-ai-based-continued-process-verification [Last accessed: October 15, 24].

20.

Venkata

, Prakash

, In

. Pharmaceutical manufacturing: Optimizing production processes and ensuring quality control. Journal of AI-Assisted Scientific Discovery [Internet], 2024; 4(1):338–379. https://scienceacadpress.com/index.php/jaasd/article/view/141

21.

Goodfellow

, Bengio

, Courville

. Deep Learning. MIT Press: Cambridge; 2016.

22.

Manzano T Whitford

. AI-Enabled digital twins in biopharmaceutical manufacturing. BioProcess Int, 2023; 21(7–8):22–27.

23.

Whitford

, Manzano

. Growing value of artificial intelligence in biopharmaceutical operations. BioProcess Int, 2022; 20(5):28–30.

24.

Wang

. Kernel principal component analysis and its applications in face recognition and active shape models. arXiv Preprint arXiv:1207.3538, 2012 doi: 10.48550/arXiv.1207.3538

25.

Manzano

, Fernández

, Ruiz

, et al. AI algorithm qualification. PDA J Pharm Sci Technol, 2020; 74(4):328–335; doi: 10.5731/pdajpst.2019.011338

26.

Liu

. C. PAC(S) of trust: A glimpse into healthcare security. Kiasura blog, 3021. Available from: https://www.kaisura.com/post/blog-4 [Last accessed: October 15, 24].

27.

U.S. Cybersecurity and Infrastructure Security Agency (CISA). Secure by Design. 2023. Available from: https://www.cisa.gov/sites/default/files/2023-10/Shifting-the-Balance-of-Cybersecurity-Risk-Principles-and-Approaches-for-Secure-by-Design-Software.pdf [Last accessed: October 15, 24].

28.

U.S. Food and Drug Administration (FDA). General principles of software validation. Available from: https://www.fda.gov/regulatory-information/search-fda-guidance-documents/general-principles-software-validation [Last accessed: October 15, 24].

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.02 MB

Artificial Intelligence Empowering Process Analytical Technology and Continued Process Verification in Biotechnology

Abstract

Get full access to this article

References

Supplementary Material