Creation of novel large dataset comprising several granulation methods and the prediction of tablet properties from critical material attributes and critical process parameters using regularized linear regression models including interaction terms

Oishi Takuya; Hayashi Yoshihiro; Noguchi Miho; Yano Fumiaki; Kumada Shungo; Takayama Kozo; Okada Kotaro; Onuki Yoshinori

首页> 外文期刊>International Journal of Pharmaceutics >Creation of novel large dataset comprising several granulation methods and the prediction of tablet properties from critical material attributes and critical process parameters using regularized linear regression models including interaction terms

【24h】

Creation of novel large dataset comprising several granulation methods and the prediction of tablet properties from critical material attributes and critical process parameters using regularized linear regression models including interaction terms

机译：创建包括几种造粒方法的新型大型数据集和使用包括交互条款的正则线性回归模型的关键材料属性和关键过程参数的平板性质的预测

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Our aim was to understand better the causal relationships between material attributes (MAs), process parameters (PPs), and critical quality attributes (CQAs) using an originally created large dataset and regularized linear regression models. In this study, we focused on the following three points: (1) creation of a dataset comprising several tablet production methods, (2) the influence of interaction terms of MAs and/or PPs, and (3) comparison of regularized linear regression models with partial least squares (PLS) regression. First, we prepared 44 kinds of tablets using direct compression and five kinds of granulation methods. We then measured 12 MAs and two model CQAs (tensile strength and disintegration time of tablet). Principal component analysis showed that the constructed dataset comprised a wide variety of particles. We applied regularized linear regression models, such as ridge regression, LASSO and Elastic Net (ENET), and PLS to our dataset to predict CQAs from the MAs and PPs. As a result of external validation, the prediction performance of the models was sufficiently high, although ENET was slightly better than the other methods. Moreover, in almost all cases, the models with interaction terms showed higher predictive ability than those without interaction terms, indicating that the interaction terms of MAs and/or PPs have a strong influence on CQAs. ENET also allowed the selection of critical factors that strongly affect CQAs. The results of this study will help to understand systematically knowledge obtained in pharmaceutical development.

机译：我们的目标是使用最初创建的大型数据集和正则线性回归模型了解更好的材料属性（MAS），过程参数（PPS）和关键质量属性（CQAS）之间的因果关系。在这项研究中，我们专注于以下三点：（1）创建一个数据集，包括多种片剂生产方法，（2）MAS和/或PPS的相互作用条款的影响，以及（3）正规化线性回归模型的比较偏最小二乘（PLS）回归。首先，我们使用直接压缩和五种造粒方法制备了44种片剂。然后，我们测量了12个MAS和两种模型CQAs（平板电脑的拉伸强度和崩解时间）。主成分分析表明，构造的数据集包括各种各样的颗粒。我们应用了正规化的线性回归模型，例如岭回归，套索和弹性网（ENET），以及PLS到我们的数据集，以预测来自MAS和PPS的CQA。由于外部验证，模型的预测性能足够高，尽管ENET略好于其他方法。此外，在几乎所有情况下，具有相互作用术语的模型比没有相互作用术语的那些模型表明MAS和/或PPS的相互作用项对CQAs产生了强烈影响。 ENET还允许选择强烈影响CQA的关键因素。本研究的结果将有助于了解药物发育中获得的系统知识。

著录项

来源
《International Journal of Pharmaceutics》 |2020年第2020期|共10页
作者
Oishi Takuya; Hayashi Yoshihiro; Noguchi Miho; Yano Fumiaki; Kumada Shungo; Takayama Kozo; Okada Kotaro; Onuki Yoshinori;
展开▼
作者单位

Univ Toyama Grad Sch Med &

Pharmaceut Sci Res Dept Pharmaceut Technol 2630 Sugitani Toyama;

Univ Toyama Grad Sch Med &

Pharmaceut Sci Res Dept Pharmaceut Technol 2630 Sugitani Toyama;

Univ Toyama Grad Sch Med &

Pharmaceut Sci Res Dept Pharmaceut Technol 2630 Sugitani Toyama;

Nichi Iko Pharmaceut Co Ltd Dev &

Planning Div Formulat Dev Dept 205-1 Shimoumezawa Namerikawa;

Nichi Iko Pharmaceut Co Ltd Dev &

Planning Div Formulat Dev Dept 205-1 Shimoumezawa Namerikawa;

Josai Univ Fac Pharm &

Pharmaceut Sci 1-1 Keyakidai Sakado Saitama 3500295 Japan;

Univ Toyama Grad Sch Med &

Pharmaceut Sci Res Dept Pharmaceut Technol 2630 Sugitani Toyama;

Univ Toyama Grad Sch Med &

Pharmaceut Sci Res Dept Pharmaceut Technol 2630 Sugitani Toyama;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类药学;
关键词
Tablet; Granulation; Elastic Net; LASSO; Partial least squares; Quality by design;

机译：平板电脑;造粒;弹性网;套索;部分最小二乘;质量设计;

相似文献

外文文献
专利

1. Creation of novel large dataset comprising several granulation methods and the prediction of tablet properties from critical material attributes and critical process parameters using regularized linear regression models including interaction terms [J] . Oishi Takuya, Hayashi Yoshihiro, Noguchi Miho, International Journal of Pharmaceutics . 2020,第期

机译：创建包括几种造粒方法的新型大型数据集和使用包括交互条款的正则线性回归模型的关键材料属性和关键过程参数的平板性质的预测
2. Predicting the critical quality attributes of ibuprofen tablets via modelling of process parameters for roller compaction and tabletting [J] . Matji Antonio, Donato Nicoletta, Gagol Adrianna, International Journal of Pharmaceutics . 2019,第期

机译：通过辊压缩和压片的工艺参数建模预测布洛芬片剂的临界质量属性
3. Statistical modeling methods to analyze the impacts of multiunit process variability on critical quality attributes of Chinese herbal medicine tablets [J] . Fei Sun, Bing Xu, Yi Zhang, Drug Design, Development and Therapy . 2016,第5期

机译：统计建模方法分析多单元过程变异性对中草药片关键质量属性的影响
4. THE METHODS OF PREDICTION OF THE PROPERTIES FOR SUBSTANCES ON THE COEXISTENCE CURVE INCLUDING VICINITY OF THE CRITICAL POINT [C] . Vitaly P. Zhelezny NATO Advanced Research Workshop on Nonlinear Dielectric Phenomena in Complex Liquids . 2004

机译：在包括临界点附近的共存曲线上预测物质的性质的预测方法
5. Understanding the Effect of Granulation and Mill Process Parameters on Granule Critical Quality Attributes [D] . Kotamarthy, Lalith Venkat Gopal. 2018

机译：了解制粒和研磨工艺参数对颗粒关键质量属性的影响
6. Statistical modeling methods to analyze the impacts of multiunit process variability on critical quality attributes of Chinese herbal medicine tablets [O] . Fei Sun, Bing Xu, Yi Zhang, 2016

机译：统计建模方法分析多单元过程变异性对中草药片关键质量属性的影响
7. Statistical modeling methods to analyze the impacts of multiunit process variability on critical quality attributes of Chinese herbal medicine tablets [O] . Fei Sun, Bing Xu, Yi Zhang, 2016

机译：统计建模方法分析多单工艺变异对中药药片危重质量属性的影响

Creation of novel large dataset comprising several granulation methods and the prediction of tablet properties from critical material attributes and critical process parameters using regularized linear regression models including interaction terms

摘要

著录项

相似文献

相关主题

期刊订阅