用机器学习工具评估预测模型,用于使用机器学习工具在湿颗粒制造商业规模制药制造中的平板电脑的封闭和断裂力
Sun Ho Kim1, Su Hyeon Han2, Dong-Wan Seo1
1College of Pharmacy, Dankook University, 119, Dandae-ro, Dongnam-gu, Cheonan-si 31116, Republic of Korea.
Pharmaceuticals (Basel, Switzerland)
|January 25, 2025
概括
机器学习模型可以准确地预测平板电脑完整性的关键质量属性 (CQAs),如破裂力和易碎性. 这种方法在制造规模扩大过程中提高了产品质量,防止了没有损坏平板电脑的问题.
科学领域:
- 制药技术 制药技术 制药技术
- 机器学习在药物制造中的应用
- 通过设计的质量 (QbD)
背景情况:
- 平板电脑的完整性对于药物的疗效和患者安全至关重要.
- 预测关键质量属性 (CQAs),如平板电脑破裂力 (TBF),易碎性和封顶发生,对于强大的制造至关重要.
- 现有的方法可能无法完全捕捉影响平板电脑完整性的过程参数的复杂相互作用.
研究的目的:
- 开发和验证用于预测平板电脑完整性CQAs的机器学习模型.
- 确定影响TBF,易碎性和封装的关键工艺和材料参数.
- 为了在药片制造过程中实现积极的质量控制.
主要方法:
- 采用商业规模的湿颗粒化工艺来制造甲胺HCl片.
- 训练并比较5个机器学习模型用于回归和分类任务.
- 使用特征重要性分析来识别关键输入变量.
主要成果:
- 高斯过程回归实现了TBF (R2=0.959) 和脆性 (R2=0.949) 的高精度.
- 增强树木模型在预测上限发生方面表现出卓越的准确性 (97.80%).
- 压缩力和酸分数被确定为最有影响力的参数.
结论:
- 机器学习模型有效地预测使用大型数据集的平板电脑完整性CQAs.
- 这些预测模型可以在湿颗粒缩放过程中提高产品质量.
- 这些模型的积极应用可以防止制造缺陷,如封装,并确保平板电脑的完整性.
相关概念视频
01:28Factors Influencing Drug Absorption: Pharmaceutical Parameters
113
Solid dosage forms such as tablets and capsules undergo rigorous manufacturing processes to ensure stability and effectiveness. Their dissolution and absorption properties are influenced significantly by the choice of excipients (inactive ingredients that serve various roles in the formulation), and the methodology applied during production. The manufacturing parameters, such as compression force and granulation techniques, significantly affect dissolution rates. Elevated compression forces...
113
01:26Pharmacokinetic Models: Comparison and Selection Criterion
38
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
38
01:21Mechanistic Models: Overview of Compartment Models
62
Mechanistic models, a category encompassing both physiological and compartmental modeling, differ from empirical models' approaches to incorporating known factors about the systems being modeled. Empirical models describe data with minimal assumptions, while mechanistic models aim to provide a robust description of available data by specifying assumptions and integrating known factors about the system. Compartmental analysis is a key example of a mechanistic model in pharmacokinetics and...
62
01:23Factors Affecting Dissolution: Particle Size and Effective Surface Area
691
Dissolution kinetics, an essential aspect of oral drug delivery, is significantly influenced by the drug's particle size. According to the Noyes-Whitney dissolution model, the dissolution rate correlates directly with the drug's surface area. The larger the surface area, the higher the drug's solubility in water, leading to a faster drug dissolution rate. Reducing particle size increases the effective surface area, enhancing the dissolution process. Micronization and nanosizing are...
691
01:20Pharmacokinetic Models: Overview
570
Pharmacokinetic models utilize mathematical analysis to achieve a detailed quantitative understanding of a drug's life cycle within the body. They are instrumental in simulating a drug's pharmacokinetic parameters, predicting drug concentrations over time, optimizing dosage regimens, linking concentrations with pharmacologic activity, and estimating potential toxicity.
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
570
01:12Analysis of Population Pharmacokinetic Data
220
Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
220