Machine learning modelling of wet granulation scale-up using compressibility, compactibility and manufacturability parameters
Article Sidebar
Main Article Content
Abstract
The purpose of this extensive study is to use a quality by design (QbD) approach and multiple machine learning algorithms in facilitating wet granulation process scale-up. This study investigated the extent of influence of both formulation and process variables. Furthermore, measured responses covered compressibility, compactibility and manufacturability of a powder blend. Finally, the models developed on laboratory scale samples were tested on pilot and commercial scale runs. Tablet detachment and ejection work were calculated from force-displacement measurements. Significant numerical and categorical input variables were identified by using a stepwise regression model and their importance evaluated by using a boosted trees model. Pilot scale runs resulted in the highest tablet tensile strength and compaction work as well as the highest detachment and ejection work. Critical quality attributes (CQAs) that were the most successfully predicted were the compaction, decompaction, and net work, as well as the tablet height. The most important input variable influencing all CQAs was the compaction force. Application of the boosted regression trees model resulted in the lowest Root Mean Square Error (RMSE) values for all of the responses. This work demonstrates reliability of predictions of developed models that can be successfully used as a part of a QbD approach for wet granulation scale-up.
Article Details
Issue
Section
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors grant to the Publisher the following rights to the manuscript, including any supplemental material, and any parts, extracts or elements thereof:
- the right to reproduce and distribute the Manuscript in printed form, including print-on-demand;
- the right to produce prepublications, reprints, and special editions of the Manuscript;
- the right to translate the Manuscript into other languages;
- the right to reproduce the Manuscript using photomechanical or similar means including, but not limited to photocopy, and the right to distribute these reproductions;
- the right to reproduce and distribute the Manuscript electronically or optically on any and all data carriers or storage media – especially in machine readable/digitalized form on data carriers such as hard drive, CD-Rom, DVD, Blu-ray Disc (BD), Mini-Disk, data tape – and the right to reproduce and distribute the Article via these data carriers;
- the right to store the Manuscript in databases, including online databases, and the right of transmission of the Manuscript in all technical systems and modes;
- the right to make the Manuscript available to the public or to closed user groups on individual demand, for use on monitors or other readers (including e-books), and in printable form for the user, either via the internet, other online services, or via internal or external networks.
How to Cite
References
Lawrence XY. Pharmaceutical quality by design: product and process development, understanding, and control. Pharm Res. 2008; 25(4):781-91.
ICH. Pharmaceutical Development Q8 (R2). 2009
Xu X, Khan MA, Burgess DJ. A quality by design (QbD) case study on liposomes containing hydrophilic API: I. Formulation, processing design and risk assessment. Int J Pharm. 2011; 419(1-2):52-9.
Aksu B, Paradkar A, de Matas M, Özer Ö, Güneri T, York P. A quality by design approach using artificial intelligence techniques to control the critical quality attributes of ramipril tablets manufactured by wet granulation. Pharm Dev Technol. 2013; 18(1):236-45.
Mackaplow MB, Rosen LA, Michaels JN. Effect of primary particle size on granule growth and endpoint determination in high-shear wet granulation. Powder Technol. 2000; 108(1):32-45.
FDA. Guidance for Industry–Process Validation: General Principles and Practices. US Department of Health and Human Services, Rockville, MD, USA. 2011;1:1-22.
Leuenberger H. Granulation, new techniques. Pharm Acta Helv. 1982; 57(3):72-82.
Schaefer T, Bak H, Jaegerskou A, Kristensen A, Svensson J, Holm P, et al. Granulation in different types of high speed mixers. I: Effects of process variables and up-scaling. Pharm Ind. 1986; 48(9):1083-9.
Agrawal AM, Pandey P. Scale up of pan coating process using quality by design principles. J Pharm Sci. 2015; 104(11):3589-611.
Aikawa S, Fujita N, Myojo H, Hayashi T, Tanino T. Scale-up studies on high shear wet granulation process from mini-scale to commercial scale. Chem Pharm Bull (Tokyo). 2008; 56(10):1431-5.
Huang J, Kaul G, Cai C, Chatlapalli R, Hernandez-Abad P, Ghosh K, et al. Quality by design case study: an integrated multivariate approach to drug product and process development. Int J Pharm. 2009; 382(1-2):23-32.
Van Buskirk GA, Asotra S, Balducci C, Basu P, DiDonato G, Dorantes A, et al. Best practices for the development, scale-up, and post-approval change control of IR and MR dosage forms in the current quality-by-design paradigm. AAPS PharmSciTech. 2014; 15(3):665-93.
Djuris J, Ibric S, Djuric Z. Quality-by-design in pharmaceutical development. In: Djuris J, ed. Computer-Aided Applications in Pharmaceutical Technology. Amsterdam, Netherlands: Elsevier; 2013:1-16.
Petrović J, Chansanroj K, Meier B, Ibrić S, Betz G. Analysis of fluidized bed granulation process using conventional and novel modeling techniques. Eur J Pharm Sci. 2011; 44(3):227-34.
Ibrić S, Djuriš J, Parojčić J, Djurić Z. Artificial neural networks in evaluation and optimization of modified release solid dosage forms. Pharmaceutics. 2012; 4(4):531-50.
Pandey P, Badawy S. A quality by design approach to scale-up of high-shear wet granulation process. Drug Dev Ind Pharm. 2016; 42(2):175-89.
Chaudhury A, Barrasso D, Pandey P, Wu H, Ramachandran R. Population balance model development, validation, and prediction of CQAs of a high-shear wet granulation process: towards QbD in drug product pharmaceutical manufacturing. J Pharm Innov. 2014; 9(1):53-64.
Barrasso D, Eppinger T, Pereira FE, Aglave R, Debus K, Bermingham SK, et al. A multi-scale, mechanistic model of a wet granulation process using a novel bi-directional PBM–DEM coupling algorithm. Chem Eng Sci. 2015; 123:500-13.
Luo G, Xu B, Sun F, Cui X, Shi X, Qiao Y. Quality by design based high shear wet granulation process development for the microcrystalline cellulose. Acta Pharm Sinica B. 2015; 50(3):355-9.
Badawy SI, Narang AS, LaMarche KR, Subramanian GA, Varia SA. Mechanistic basis for the effects of process parameters on quality attributes in high shear wet granulation. In: Narang A, Badawy S, ed. Handbook of Pharmaceutical Wet Granulation. Amsterdam, Netherlands: Elsevier; 2019:89-118.
Kayrak-Talay D, Dale S, Wassgren C, Litster J. Quality by design for wet granulation in pharmaceutical processing: assessing models for a priori design and scaling. Powder Technol. 2013; 240:7-18.
Sonnergaard JM. Quantification of the compactibility of pharmaceutical powders. Eur J Pharm Biopharm. 2006; 63(3):270-7.
Klevan I, Haware R, Reichenbach M, Bauer-Brandl A. A new tablet press simulator device for extremely accurate measurement of time-resolved forces and displacements based on an electromechanical press. In: Proceedings of Pharmaceutical Sciences World Congress. Amsterdam, Netherlands; 2007.
Armstrong N, Haines-Nutt R. Elastic recovery and surface area changes in compacted powder systems. J Pharm Pharmacol. 1972; 24:Suppl: 135P-6.
Maganti L, Celik M. Compaction studies on pellets I. Uncoated pellets. Int J Pharm. 1993; 95(1-3):29-42.
Tibshirani R. Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Stat Method). 1996; 267-88.
Hoerl AE, Kennard RW. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics. 1970; 12(1):55-67.
Zou H, Hastie T. Regularization and variable selection via the elastic net. J Roy Stat Soc Ser B (Stat Method). 2005; 67(2):301-20.
Quinlan JR. Simplifying decision trees. Int J Man Mach Stud. 1987; 27(3):221-34.
Friedman J. Greedy Function Approximation: A Gradient Boosting Machine. https://pdfs.semanticscholar.org/1679/bedd-da3a183714d380e944fe6bf586c083cd.pdf. Accessed April 11, 2019.
Shapiro SS, Wilk MB. An analysis of variance test for normality (complete samples). Biometrika. 1965; 52(3/4):591-611.
Allen M. Kruskal–Wallis Test. In: Allen M, ed. The SAGE Encyclopedia of Communication Research Methods. Thousand Oaks, California, USA: Sage Publications, 2017.
Caruana R, Niculescu-Mizil A. An empirical comparison of supervised learning algorithms. Proceedings of the 23rd international conference on Machine learning. Pittsburgh, Pennsylvania, USA, 2006.
Antikainen O, Yliruusi J. Determining the compression behaviour of pharmaceutical powders from the force–distance compression profile. Int J Pharm. 2003; 252(1-2):253-61.
Šantl M, Ilić I, Vrečer F, Baumgartner S. A compressibility and compactibility study of real tableting mixtures: the impact of wet and dry granulation versus a direct tableting mixture. Int J Pharm. 2011; 414(1-2):131-9.
Osamura T, Takeuchi Y, Onodera R, Kitamura M, Takahashi Y, Tahara K, et al. Formulation design of granules prepared by wet granulation method using a multi-functional single-punch tablet press to avoid tableting failures. Asian J Pharm Sci. 2018; 13(2):113-9.
Haware RV, Tho I, Bauer-Brandl A. Evaluation of a rapid approximation method for the elastic recovery of tablets. Powder Technol. 2010; 202(1-3):71-7.
York P, Baily E. Dimensional changes of compacts after compression. J Pharm Pharmacol. 1977; 29(1):70-4
Muller F. Viscoelastic models. In: Alderborn G, Nystrom C. ed. Pharmaceutical Powder Compaction Technology. New York, NY: Marcel Dekker; 1996: 99-132.
Osamura T, Takeuchi Y, Onodera R, Kitamura M, Takahashi Y, Tahara K, et al. Characterization of tableting properties measured with a multi-functional compaction instrument for several pharmaceutical excipients and actual tablet formulations. Int J Pharm. 2016; 510(1):195-202.
Uzondu B, Leung LY, Mao C, Yang C-Y. A mechanistic study on tablet ejection force and its sensitivity to lubrication for pharmaceutical powders. Int J Pharm. 2018; 543(1):234-44.
Adolfsson Å, Nyström C. Tablet strength, porosity, elasticity and solid state structure of tablets compressed at high loads. Int J Pharm. 1996; 132(1-2):95-106.
Paul S, Sun CC. Gaining insight into tablet capping tendency from compaction simulation. Int J Pharm. 2017; 524(1-2):111-20.
Gamlen M. Comparison of tablet ejection and detachment stresses using a dynamic powder compaction analyzer, 2016.
Chai T, Draxler RR. Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature. Geosci Model Dev. 2014; 7(3):1247-50.
Thompson B. Stepwise regression and stepwise discriminant analysis need not apply here: A guidelines editorial. Thousand Oaks, California, USA: Sage Publications; 1995.
Tso GK, Yau KK. Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks. Energy. 2007; 32(9):1761-8.
Shi L, Feng Y, Sun CC. Origin of profound changes in powder properties during wetting and nucleation stages of high-shear wet granulation of microcrystalline cellulose. Powder Technol. 2011; 208(3):663-8.
Patel S, Dahiya S, Calvin Sun C, Bansal AK. Understanding size enlargement and hardening of granules on tabletability of unlubricated granules prepared by dry granulation. J Pharm Sci. 2011; 100(2):758-66.
Schmidt P, Herzog R. Calcium phosphates in pharmaceutical tableting. Pharm World Sci. 1993; 15(3):116-22.
Zhang Y, Wrzesinski A, Moses M, Bertrand H. Comparison of Superdisintegrants in Orally Disintegrating Tablets. Pharm Technol. 2010; 34(7):54-65.
Rojas JJ, Aristizabal J, Henao M. Screening of several excipients for direct compression of tablets: A new perspective based on functional properties. Rev. Ciênc. Farm. Básica Apl. 2013; 34(1):17-23.
predictorImportance. MathWorks. https://au.mathworks.com/help/stats/compactregressionensemble.predictor¬importan-ce.html. Accessed April 11, 2019.
Stolley DL, May EE. Spatiotemporal Analysis of Mycobacterium-Dependent Macrophage Response. Proceedings of 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Honolulu, HI, 2018, pp. 2390-3.