Predicting Pharmaceutical Particle Size Distributions Using Kernel Mean Embedding
In the pharmaceutical industry, the transition to continuous manufacturing of solid dosage forms is adopted by more and more companies. For these continuous processes, high-quality process models are needed. In pharmaceutical wet granulation, a unit operation in the ConsiGma<inline-formula> &l...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Pharmaceutics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4923/12/3/271 |
| _version_ | 1811263396196122624 |
|---|---|
| author | Daan Van Hauwermeiren Michiel Stock Thomas De Beer Ingmar Nopens |
| author_facet | Daan Van Hauwermeiren Michiel Stock Thomas De Beer Ingmar Nopens |
| author_sort | Daan Van Hauwermeiren |
| collection | DOAJ |
| description | In the pharmaceutical industry, the transition to continuous manufacturing of solid dosage forms is adopted by more and more companies. For these continuous processes, high-quality process models are needed. In pharmaceutical wet granulation, a unit operation in the ConsiGma<inline-formula> <math display="inline"> <semantics> <msup> <mrow></mrow> <mi>TM</mi> </msup> </semantics> </math> </inline-formula>-25 continuous powder-to-tablet system (GEA Pharma systems, Collette, Wommelgem, Belgium), the product under study presents itself as a collection of particles that differ in shape and size. The measurement of this collection results in a particle size distribution. However, the theoretical basis to describe the physical phenomena leading to changes in this particle size distribution is lacking. It is essential to understand how the particle size distribution changes as a function of the unit operation’s process settings, as it has a profound effect on the behavior of the fluid bed dryer. Therefore, we suggest a data-driven modeling framework that links the machine settings of the wet granulation unit operation and the output distribution of granules. We do this without making any assumptions on the nature of the distributions under study. A simulation of the granule size distribution could act as a soft sensor when in-line measurements are challenging to perform. The method of this work is a two-step procedure: first, the measured distributions are transformed into a high-dimensional feature space, where the relation between the machine settings and the distributions can be learnt. Second, the inverse transformation is performed, allowing an interpretation of the results in the original measurement space. Further, a comparison is made with previous work, which employs a more mechanistic framework for describing the granules. A reliable prediction of the granule size is vital in the assurance of quality in the production line, and is needed in the assessment of upstream (feeding) and downstream (drying, milling, and tableting) issues. Now that a validated data-driven framework for predicting pharmaceutical particle size distributions is available, it can be applied in settings such as model-based experimental design and, due to its fast computation, there is potential in real-time model predictive control. |
| first_indexed | 2024-04-12T19:43:17Z |
| format | Article |
| id | doaj.art-934e6b2a7f2742199fcc8f8312821b0b |
| institution | Directory Open Access Journal |
| issn | 1999-4923 |
| language | English |
| last_indexed | 2024-04-12T19:43:17Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Pharmaceutics |
| spelling | doaj.art-934e6b2a7f2742199fcc8f8312821b0b2022-12-22T03:19:01ZengMDPI AGPharmaceutics1999-49232020-03-0112327110.3390/pharmaceutics12030271pharmaceutics12030271Predicting Pharmaceutical Particle Size Distributions Using Kernel Mean EmbeddingDaan Van Hauwermeiren0Michiel Stock1Thomas De Beer2Ingmar Nopens3BIOMATH—Department of data analysis and mathematical modelling, Ghent University, Coupure Links 653, 9000 Gent, BelgiumKERMIT—Department of data analysis and mathematical modelling, Ghent University, Coupure Links 653, 9000 Gent, BelgiumLaboratory of Pharmaceutical Process Analytical Technology—Department of pharmaceutical analysis, Ghent University, Ottergemsesteenweg 460, 9000 Gent, BelgiumBIOMATH—Department of data analysis and mathematical modelling, Ghent University, Coupure Links 653, 9000 Gent, BelgiumIn the pharmaceutical industry, the transition to continuous manufacturing of solid dosage forms is adopted by more and more companies. For these continuous processes, high-quality process models are needed. In pharmaceutical wet granulation, a unit operation in the ConsiGma<inline-formula> <math display="inline"> <semantics> <msup> <mrow></mrow> <mi>TM</mi> </msup> </semantics> </math> </inline-formula>-25 continuous powder-to-tablet system (GEA Pharma systems, Collette, Wommelgem, Belgium), the product under study presents itself as a collection of particles that differ in shape and size. The measurement of this collection results in a particle size distribution. However, the theoretical basis to describe the physical phenomena leading to changes in this particle size distribution is lacking. It is essential to understand how the particle size distribution changes as a function of the unit operation’s process settings, as it has a profound effect on the behavior of the fluid bed dryer. Therefore, we suggest a data-driven modeling framework that links the machine settings of the wet granulation unit operation and the output distribution of granules. We do this without making any assumptions on the nature of the distributions under study. A simulation of the granule size distribution could act as a soft sensor when in-line measurements are challenging to perform. The method of this work is a two-step procedure: first, the measured distributions are transformed into a high-dimensional feature space, where the relation between the machine settings and the distributions can be learnt. Second, the inverse transformation is performed, allowing an interpretation of the results in the original measurement space. Further, a comparison is made with previous work, which employs a more mechanistic framework for describing the granules. A reliable prediction of the granule size is vital in the assurance of quality in the production line, and is needed in the assessment of upstream (feeding) and downstream (drying, milling, and tableting) issues. Now that a validated data-driven framework for predicting pharmaceutical particle size distributions is available, it can be applied in settings such as model-based experimental design and, due to its fast computation, there is potential in real-time model predictive control.https://www.mdpi.com/1999-4923/12/3/271granulationwet granulationcontinuous manufacturingprocess modelingparticle size distributionskernel methodskernel mean embeddingpredictive modelingdata-drivenmachine learning |
| spellingShingle | Daan Van Hauwermeiren Michiel Stock Thomas De Beer Ingmar Nopens Predicting Pharmaceutical Particle Size Distributions Using Kernel Mean Embedding Pharmaceutics granulation wet granulation continuous manufacturing process modeling particle size distributions kernel methods kernel mean embedding predictive modeling data-driven machine learning |
| title | Predicting Pharmaceutical Particle Size Distributions Using Kernel Mean Embedding |
| title_full | Predicting Pharmaceutical Particle Size Distributions Using Kernel Mean Embedding |
| title_fullStr | Predicting Pharmaceutical Particle Size Distributions Using Kernel Mean Embedding |
| title_full_unstemmed | Predicting Pharmaceutical Particle Size Distributions Using Kernel Mean Embedding |
| title_short | Predicting Pharmaceutical Particle Size Distributions Using Kernel Mean Embedding |
| title_sort | predicting pharmaceutical particle size distributions using kernel mean embedding |
| topic | granulation wet granulation continuous manufacturing process modeling particle size distributions kernel methods kernel mean embedding predictive modeling data-driven machine learning |
| url | https://www.mdpi.com/1999-4923/12/3/271 |
| work_keys_str_mv | AT daanvanhauwermeiren predictingpharmaceuticalparticlesizedistributionsusingkernelmeanembedding AT michielstock predictingpharmaceuticalparticlesizedistributionsusingkernelmeanembedding AT thomasdebeer predictingpharmaceuticalparticlesizedistributionsusingkernelmeanembedding AT ingmarnopens predictingpharmaceuticalparticlesizedistributionsusingkernelmeanembedding |