Machine learning modelling of wet granulation scale-up using compressibility, compactibility and manufacturability parameters
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 res...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Association of Chemical Engineers of Serbia
2019-01-01
|
| Series: | Hemijska Industrija |
| Subjects: | |
| Online Access: | http://www.doiserbia.nb.rs/img/doi/0367-598X/2019/0367-598X1903155M.pdf |
| _version_ | 1819118880880066560 |
|---|---|
| author | Millen Nada Kovačević Aleksandar Khera Lalit Đuriš Jelena Ibrić Svetlana |
| author_facet | Millen Nada Kovačević Aleksandar Khera Lalit Đuriš Jelena Ibrić Svetlana |
| author_sort | Millen Nada |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-22T05:55:55Z |
| format | Article |
| id | doaj.art-bff2bc10c4024ce08e1dae448f212cfb |
| institution | Directory Open Access Journal |
| issn | 0367-598X 2217-7426 |
| language | English |
| last_indexed | 2024-12-22T05:55:55Z |
| publishDate | 2019-01-01 |
| publisher | Association of Chemical Engineers of Serbia |
| record_format | Article |
| series | Hemijska Industrija |
| spelling | doaj.art-bff2bc10c4024ce08e1dae448f212cfb2022-12-21T18:36:43ZengAssociation of Chemical Engineers of SerbiaHemijska Industrija0367-598X2217-74262019-01-0173315516810.2298/HEMIND190412017M0367-598X1903155MMachine learning modelling of wet granulation scale-up using compressibility, compactibility and manufacturability parametersMillen Nada0Kovačević Aleksandar1Khera Lalit2Đuriš Jelena3Ibrić Svetlana4Department of Pharmaceutical Technology and Cosmetology, Faculty of Pharmacy, University of Belgrade, Belgrade, SerbiaFaculty of Technical Sciences, University of Novi Sad, Novi Sad, SerbiaInhouse Remote Development, Seven N Consulting Pvt Ltd, Gurgaon, Haryana, IndiaDepartment of Pharmaceutical Technology and Cosmetology, Faculty of Pharmacy, University of Belgrade, Belgrade, SerbiaDepartment of Pharmaceutical Technology and Cosmetology, Faculty of Pharmacy, University of Belgrade, Belgrade, SerbiaThe 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.http://www.doiserbia.nb.rs/img/doi/0367-598X/2019/0367-598X1903155M.pdfquality by designartificial intelligencecompaction workdecompaction workelastic recovery |
| spellingShingle | Millen Nada Kovačević Aleksandar Khera Lalit Đuriš Jelena Ibrić Svetlana Machine learning modelling of wet granulation scale-up using compressibility, compactibility and manufacturability parameters Hemijska Industrija quality by design artificial intelligence compaction work decompaction work elastic recovery |
| title | Machine learning modelling of wet granulation scale-up using compressibility, compactibility and manufacturability parameters |
| title_full | Machine learning modelling of wet granulation scale-up using compressibility, compactibility and manufacturability parameters |
| title_fullStr | Machine learning modelling of wet granulation scale-up using compressibility, compactibility and manufacturability parameters |
| title_full_unstemmed | Machine learning modelling of wet granulation scale-up using compressibility, compactibility and manufacturability parameters |
| title_short | Machine learning modelling of wet granulation scale-up using compressibility, compactibility and manufacturability parameters |
| title_sort | machine learning modelling of wet granulation scale up using compressibility compactibility and manufacturability parameters |
| topic | quality by design artificial intelligence compaction work decompaction work elastic recovery |
| url | http://www.doiserbia.nb.rs/img/doi/0367-598X/2019/0367-598X1903155M.pdf |
| work_keys_str_mv | AT millennada machinelearningmodellingofwetgranulationscaleupusingcompressibilitycompactibilityandmanufacturabilityparameters AT kovacevicaleksandar machinelearningmodellingofwetgranulationscaleupusingcompressibilitycompactibilityandmanufacturabilityparameters AT kheralalit machinelearningmodellingofwetgranulationscaleupusingcompressibilitycompactibilityandmanufacturabilityparameters AT đurisjelena machinelearningmodellingofwetgranulationscaleupusingcompressibilitycompactibilityandmanufacturabilityparameters AT ibricsvetlana machinelearningmodellingofwetgranulationscaleupusingcompressibilitycompactibilityandmanufacturabilityparameters |