Investigation of Preprocessing and Validation Methodologies for PAT: Case Study of the Granulation and Coating Steps for the Manufacturing of Ethenzamide Tablets

Shibayama, Shojiro; Funatsu, Kimito

doi:10.1208/s12249-020-01911-w

Cited by 3 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Especially when the number of samples is less than 30, LOOCV is generally considered to be the most recommended evaluation method. In case the division of the dataset may have an impact on the performance of the model, the repeatability measure named y-scrambling can be used to further verify the stability of the model 45,46 . By randomly dividing the dataset into training set and test set for multiple times to evaluate the stability of the model, the problem of random fluctuations caused by dataset division can be avoided.…”

Section: Workflow Of Materials Machine Learningmentioning

confidence: 99%

Small data machine learning in materials science

et al. 2023

npj Comput Mater

193

View full text Add to dashboard Cite

This review discussed the dilemma of small data faced by materials machine learning. First, we analyzed the limitations brought by small data. Then, the workflow of materials machine learning has been introduced. Next, the methods of dealing with small data were introduced, including data extraction from publications, materials database construction, high-throughput computations and experiments from the data source level; modeling algorithms for small data and imbalanced learning from the algorithm level; active learning and transfer learning from the machine learning strategy level. Finally, the future directions for small data machine learning in materials science were proposed.

show abstract

Section: Workflow Of Materials Machine Learningmentioning

confidence: 99%

Small data machine learning in materials science

et al. 2023

npj Comput Mater

193

View full text Add to dashboard Cite

show abstract

“…Shibayama and Funatsu [66] studied the application of NIRS in vinyl amide granulation and coating steps to investigate which factors should be considered and solved in PAT model construction and management, and how to build a prediction model. The researchers built a model for the granulation step and verified the prediction ability of the model according to the external data set.…”

Section: Pat Implementation In Pharmaceutical Granulation Techniquesmentioning

confidence: 99%

Granulation process analysis technologies and potential applications in traditional Chinese medicine

Cui

Hou

Feng

et al. 2022

Acupuncture and Herbal Medicine

View full text Add to dashboard Cite

Pharmaceutical production is changing from batch production to continuous production, during which granulation is one of the most important unit operations. The quality of mass-produced products is traditionally guaranteed by conducting off-line testing, which cannot meet the demand of continuous production for real-time monitoring of critical process parameters and critical quality attributes (CQAs) of the pharmaceutical granulation technology. Since the U.S. Food and Drug Administration proposed process analytical technology (PAT) in 2004, many PAT tools have been developed to monitor the granulation process and provide information regarding the granulation operation conditions and endpoint determination. In this article, we review the recent research and application of two PAT modes in the granulation process, namely, single CQA and multi-CQA PAT, with the aim to provide references for comprehensively improving the technological level of the pharmaceutical granulation process. Furthermore, the potential applications in traditional Chinese Medicine are discussed.

show abstract