Integration of quality by design with artificial intelligence/machine learning technologies in pharmaceutical manufacturing: A comprehensive review

作者
Sumit Ghosal,NIRANJAN PANDA,Bikash Ranjan Jena,Madhusudan Maity,Sankhadip Bose,Rabinarayan Parhi
出处
期刊:ADMET and DMPK [International Association of Physical Chemists (IAPC)]
卷期号:14
标识
DOI:10.5599/admet.3565
摘要

Background and purpose: Quality by design (QbD) has revolutionized pharmaceutical development by shifting from a conventional quality-by-testing approach to a science-based approach that incorporates quality into products and processes from inception. The integration of artificial intelligence (AI), machine learning (ML), automation, and digital technologies with QbD offers new opportunities to enhance process understanding, optimize critical quality attributes (CQAs) and support the Pharma 4.0 industry framework. Experimental approach: A systematic review of studies published between 2016 and 2025 was conducted to evaluate the application of supervised learning algorithms, deep neural networks, reinforcement learning, and digital twin technologies within QbD. Regulatory frameworks, including International Council for Harmonisation (ICH) quality guideline Q8 through Q14, the U.S. Food and Drug Administration’s Emerging Technology Program and the European Medicines Agency quality initiative, together with representative industrial case studies, were also examined. Key results: This review demonstrates that AI-driven QbD improves process understanding, CQA optimization, batch-to-batch consistency, process robustness, and real-time quality control. Further, advanced computational models enable predictive process monitoring, intelligent decision-making, and in silico experimentation, reducing manufacturing costs, development time and experimental burden. However, challenges related to data quality, model interpretability, validation, and regulatory harmonisation remain a critical barrier to widespread implementation. Conclusion: The convergence of AI, ML and QbD provides a robust framework for intelligent pharmaceutical manufacturing (PM). AI-enabled QbD supports the development of high-quality products through predictive, data-driven, and in silico approaches while accelerating development and improving manufacturing efficiency. These technologies offer a practical roadmap toward Pharma 4.0 and the future of digital PM.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Maestro_S的应助被一呆采纳,获得10
1秒前
tx发布了新的文献求助100
2秒前
Ililam完成签到,获得积分10
3秒前
重要的大白菜真实的钥匙完成签到,获得积分10
3秒前
3秒前
zero完成签到,获得积分10
4秒前
LordRedScience完成签到,获得积分10
5秒前
贪玩的秋柔的应助被wyf采纳,获得10
5秒前
我说今晚月光那么美完成签到,获得积分10
5秒前
sjn完成签到,获得积分10
6秒前
sunwen发布了新的文献求助10
7秒前
水煮电吹风的应助被魔法大王采纳,获得10
7秒前
健康的依白完成签到,获得积分10
7秒前
隐形曼青的应助被收手吧大哥采纳,获得10
8秒前
陈婕完成签到,获得积分10
8秒前
8秒前
8秒前
9秒前
11秒前
无极微光的应助被是我呀吼采纳,获得20
12秒前
明理乾发布了新的文献求助10
12秒前
12秒前
FG发布了新的文献求助10
13秒前
史迪仔完成签到 ,获得积分10
13秒前
xiaobai发布了新的文献求助10
14秒前
西红柿完成签到,获得积分10
14秒前
大模型的应助被开朗紫采纳,获得10
14秒前
研友_ndvWy8完成签到,获得积分10
15秒前
16秒前
17秒前
18秒前
莓莓发布了新的文献求助10
19秒前
FG完成签到,获得积分10
19秒前
爆米花的应助被简单山水采纳,获得10
19秒前
上官若男的应助被雾潋采纳,获得10
20秒前
Kiss完成签到,获得积分10
22秒前
cdercder的应助被fzt采纳,获得10
22秒前
22秒前
GBY完成签到,获得积分10
23秒前
LIUJIAWEI发布了新的文献求助10
24秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181658
求助须知:如何正确求助?哪些是违规求助? 9571454
关于积分的说明 21818081
捐赠科研通 7777987
什么是DOI,文献DOI怎么找? 3433508
关于科研通互助平台的介绍 2557696
邀请新用户注册赠送积分活动 2479568