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.

Published on Jan 24, 2020in International Journal of Pharmaceutics4.213
路 DOI :10.1016/j.ijpharm.2020.119083
Takuya Oishi1
Estimated H-index: 1
(University of Toyama),
Yoshihiro Hayashi7
Estimated H-index: 7
(University of Toyama)
+ 5 AuthorsYoshinori Onuki15
Estimated H-index: 15
(University of Toyama)
Abstract 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.
  • References (44)
  • Citations (0)
馃摉 Papers frequently viewed together
3 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
#1Antonio Matji (Complutense University of Madrid)H-Index: 2
#2Nicoletta Donato (Complutense University of Madrid)H-Index: 1
Last. Juan J. Torrado (Complutense University of Madrid)H-Index: 24
view all 9 authors...
We would like to thank Industrial Farmaceutica Cantabria (Torrejon, Spain) for their support and assistance to perform this work. This study was partially supported by the Complutense University of Madrid and a Science Foundation Ireland grant co-funded under the European Regional Development Fund (SFI/12/RC/2275) provided to Prof. A. M. Healy
#1Yilong Yang (UM: University of Macau)H-Index: 4
#2Zhuyifan Ye (UM: University of Macau)H-Index: 2
Last. Defang Ouyang (UM: University of Macau)H-Index: 12
view all 6 authors...
Abstract Current pharmaceutical formulation development still strongly relies on the traditional trial-and-error methods of pharmaceutical scientists. This approach is laborious, time-consuming and costly. Recently, deep learning has been widely applied in many challenging domains because of its important capability of automatic feature extraction. The aim of the present research is to apply deep learning methods to predict pharmaceutical formulations. In this paper, two types of dosage forms we...
7 CitationsSource
#1Panagiotis Barmpalexis (A.U.Th.: Aristotle University of Thessaloniki)H-Index: 9
#2Anna Karagianni (A.U.Th.: Aristotle University of Thessaloniki)H-Index: 3
Last. Kyriakos Kachrimanis (A.U.Th.: Aristotle University of Thessaloniki)H-Index: 21
view all 4 authors...
Abstract In the present study, the preparation of pharmaceutical mini-tablets was attempted in the framework of Quality by Design (QbD) context, by comparing traditionally used multi-linear regression (MLR), with artificially-intelligence based regression techniques (such as standard artificial neural networks (ANNs), particle swarm optimization (PSO) ANNs and genetic programming (GP)) during Design of Experiment (DoE) implementation. Specifically, the effect of diluent type and particle size fr...
#1Shubhajit Paul (UMN: University of Minnesota)H-Index: 9
#2Changquan Calvin Sun (UMN: University of Minnesota)H-Index: 30
Abstract As an essential formulation component for large-scale tablet manufacturing, the lubricant preserves tooling by reducing die-wall friction. Unfortunately, lubrication also often results in adverse effects on tablet characteristics, such as prolonged disintegration, slowed dissolution, and reduced mechanical strength. Therefore, the choice of lubricant and its optimal concentration in a tablet formulation is a critical decision in tablet formulation development to attain low die-wall fric...
5 CitationsSource
#1Yang Xu (YZU: Yangzhou University)H-Index: 4
#2Xin Wang (YZU: Yangzhou University)H-Index: 4
Last. Zhongli Hu (WHU: Wuhan University)H-Index: 6
view all 7 authors...
Background Hybrid breeding is an effective tool to improve yield in rice, while parental selection remains the key and difficult issue. Genomic selection (GS) provides opportunities to predict the performance of hybrids before phenotypes are measured. However, the application of GS is influenced by several genetic and statistical factors. Here, we used a rice North Carolina II (NC II) population constructed by crossing 115 rice varieties with five male sterile lines as a model to evaluate effect...
6 CitationsSource
#1Yoshihiro Hayashi (University of Toyama)H-Index: 7
#2Takahiro Tsuji (University of Toyama)H-Index: 1
Last. Yoshinori Onuki (University of Toyama)H-Index: 15
view all 9 authors...
Abstract In this study, we evaluated the correlation between the response surfaces for the tablet characteristics of placebo and active pharmaceutical ingredient (API)-containing tablets. The quantities of lactose, cornstarch, and microcrystalline cellulose were chosen as the formulation factors. Ten tablet formulations were prepared. The tensile strength (TS) and disintegration time (DT) of tablets were measured as tablet characteristics. The response surfaces for TS and DT were estimated using...
1 CitationsSource
#1Shigeru YamaguchiH-Index: 1
#2Takahiro Nishimura (Kyoto University)H-Index: 42
Last. Ian Johnston (BU: Boston University)H-Index: 1
view all 6 authors...
In organic chemistry, Comparative Molecular Field Analysis (CoMFA) can be defined as a regression analysis between reaction outcomes and molecular fields, wherein we can extract and visualize important structural information from the coefficients of the constructed regression models. In CoMFA, partial least-squares (PLS) regression, which determines all coefficients in the model, is used for fitting the regression models. However, in organic reactions, steric effects are observed only near the r...
1 CitationsSource
#1Huolong Liu (University of Massachusetts Lowell)H-Index: 4
#2Shaun C. Galbraith (University of Massachusetts Lowell)H-Index: 3
Last. Seongkyu Yoon (University of Massachusetts Lowell)H-Index: 12
view all 9 authors...
Abstract In this study, the influence of key process variables (screw speed, throughput and liquid to solid (L/S) ratio) of a continuous twin screw wet granulation (TSWG) was investigated using a central composite face-centered (CCF) experimental design method. Regression models were developed to predict the process responses (motor torque, granule residence time), granule properties (size distribution, volume average diameter, yield, relative width, flowability) and tablet properties (tensile s...
13 CitationsSource
#1Yifan Wang (RU: Rutgers University)H-Index: 9
#2Tianyi Li (RU: Rutgers University)H-Index: 3
Last. Benjamin J. Glasser (RU: Rutgers University)H-Index: 30
view all 4 authors...
Abstract Purpose Accurate and consistent delivery of materials by well-designed feeders ensures overall process stability. Importantly, feeding performance is strongly dependent on material flow properties. The purpose of this study is to develop a methodology that identifies predictive correlation between material flow properties and feeder performance. Method The proposed methodology includes techniques to characterize material flow properties, methods to quantify feeding performance of a loss...
19 CitationsSource
#1艁ukasz Kubik (Gda艅sk Medical University)H-Index: 9
#2Pawe艂 Wiczling (Gda艅sk Medical University)H-Index: 18
Abstract The aim of this work was to develop mathematical models relating the hydrophobicity and dissociation constant of an analyte with its structure, which would be useful in predicting analyte retention times in reversed-phase liquid chromatography. For that purpose a large and diverse group of 115 drugs was used to build three QSRR models combining retention-related parameters (log k w 鈥攃hromatographic measure of hydrophobicity, S鈥攕lope factor from Snyder-Soczewinski equation, and p K a ) w...
9 CitationsSource
Cited By0