Challenges and Opportunities of Implementing Data Fusion in Process Analytical Technology—A Review

Abstract

The release of the FDA’s guidance on Process Analytical Technology has motivated and supported the pharmaceutical industry to deliver consistent quality medicine by acquiring a deeper understanding of the product performance and process interplay. The technical opportunities to reach this high-level control have considerably evolved since 2004 due to the development of advanced analytical sensors and chemometric tools. However, their transfer to the highly regulated pharmaceutical sector has been limited. To this respect, data fusion strategies have been extensively applied in different sectors, such as food or chemical, to provide a more robust performance of the analytical platforms. This survey evaluates the challenges and opportunities of implementing data fusion within the PAT concept by identifying transfer opportunities from other sectors. Special attention is given to the data types available from pharmaceutical manufacturing and their compatibility with data fusion strategies. Furthermore, the integration into Pharma 4.0 is discussed.

Spectroscopic technologies and data fusion: Applications for the dairy industry

“…Savitzky–Golay smoothing, derivatives, detrending and multiplicative scatter correction are all common pre-processing techniques used in chemometrics. Normalization methods include auto scaling, vector normalization, standard normal variate (SNV), min-max normalization or concentration normalization ( 12 ). Normalization methods can be seen as column wise treatments and are useful for ensuring equal weight is given to each variable among the different datasets ( 21 ).…”

“…However, it does require scaling to ensure all data blocks present with equal variance ( 11 ). A high volume of data, often containing similar or correlated information is also a limitation of low level data fusion ( 12 ).…”

“…Mid level data fusion has advantages over low level data fusion in that it can remove unwanted information through dimension reduction techniques. Variable selection techniques are also another way of selecting only relevant data from each dataset thus reducing noise and unwanted information ( 12 ). The variable reduction also reduces the computational time for analysis.…”

Enhancing glucose classification in continuous flow hydrothermal biomass liquefaction streams through generative AI and IR spectroscopy

“…This technique involved stacking the data from different sources on top of each other, resulting in the creation of a new matrix. 40 In order to augment the data, two distinct modes were employed, as described in ref. 41:…”

Prediction of dissolution profiles of sinomenine hydrochloride sustained-release tablets part I: using near-infrared spectra as predictors

“…The concept of process analytical technology (PAT) has become increasingly important in the pharmaceutical industry as a way to achieve faster release testing. 12 Spectroscopic techniques, such as near-infrared (NIR) or Raman spectroscopy, provide a nondestructive and cost-effective means, and have been widely recognized as powerful PAT tools applied in the pharmaceutical industry. 13 More recently, NIR spectroscopy has emerged as one of the most popular measurement methods, which can monitor blend uniformity, 14 tablet strength, 15,16 drug dissolution, 17 powder density 18 and adulteration 19 and has attracted increasing attention.…”