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.

This paper presents novel measurement methods, where deep learning was used to detect tableting defects and determine the crushing strength and disintegration time of tablets on images captured by machine vision. Five different classes of defects were used and the accuracy of the real-time defect recognition performed with the deep learning algorithm YOLOv5 was 99.2%. The system can already match the production capability of tablet presses, with still further room left for improvement. The YOLOv5 algorithm was also used to determine the disintegration time and crushing strength of tablets produced at different compression force settings based on their surface texture. With these accurate, low-cost methods, the 100% screening of the produced tablets could be carried out, resulting in the improvement of quality control and effectiveness of pharmaceutical production.

In this decade, one of the major trends in the pharmaceutical industry is the adoption of continuous manufacturing. This requires the development of continuous equivalents of essential pharmaceutical processes such as film coating. The process of film coating is the last step of the processing of solid dosage forms and is critical because it determines the visual appearance of the end product, along with ensuring its stability and possibly even defining the rate of drug release. Several manufacturers advertise continuous solutions for film coating, these include semi-continuous and fully continuous appliances. State-of-the-art continuous coaters can match the throughput of continuous manufacturing lines, because largest appliances have a capacity of 1200-1500 kg/h. The paper also describes the main challenges related to continuous film coating including waste production at the beginning and end of the process and the problem caused by elastic recovery of the tablets when film coating is performed immediately after tablet compression. Lastly, we give an overview of the in-line sensors that can be used to monitor the quality of the film coated tablets, enabling real-time quality control of the process. Near-infrared and Raman spectroscopy can measure the mass gain of the tablets, while terahertz pulsed imaging and optical coherence tomography enable coating thickness measurement of individual tablets and even the characterization of intra-tablet coating thickness variability. UV imaging and machine vision can also measure coating thickness, and they are also excellent for detecting tablets with defective coating.

In this study, a novel quality assurance system was developed utilizing Process analytical technology (PAT) tools and artificial intelligence (AI). Our goal was to monitor the critical quality attributes (CQAs) like drug concentration, morphology and fiber diameter of electrospun amorphous solid dispersion (ASD) formulations with fast at-line techniques. Doxycycline-hyclate (DOX), a tetracycline-type antibiotic was used as a model drug with 2-hydroxypropyl-β-cyclodextrin (HP-β-CD) as the matrix excipient. The water-based formulations were electrospun with high-speed electrospinning (HSES). Raman and NIR sensors and machine vision-based color measurement techniques were employed to accurately determine the drug concentration. Given that morphology can influence the solubility of the drug, a convolutional neural network (CNN)-based AI model was developed to examine this property and detect manufacturing defects. Additionally, the diameter of electrospun fibrous samples was measured using camera images and a trained AI model, enabling rapid analysis of fiber diameter with results similar to that of scanning electron microscopy (SEM). These methods and models demonstrate potential in-line analytical tools, offering rapid, cheap and non-destructive analysis of ASD formulations.

In this work, the performance of two fast chemical imaging techniques, Raman and near-infrared (NIR) imaging is compared by utilizing these methods to predict the rate of drug release from sustained-release tablets. Sustained release is provided by adding hydroxypropyl methylcellulose (HPMC), as its concentration and particle size determine the dissolution rate of the drug. The chemical images were processed using classical least squares; afterwards, a convolutional neural network was applied to extract information regarding the particle size of HPMC. The chemical images were reduced to an average HPMC concentration and a predicted particle size value; these were used as inputs in an artificial neural network with a single hidden layer to predict the dissolution profile of the tablets. Both NIR and Raman imaging yielded accurate predictions. As the instrumentation of NIR imaging allows faster measurements than Raman imaging, this technique is a better candidate for implementing a real-time technique. The introduction of chemical imaging in the routine quality control of pharmaceutical products would profoundly change quality assurance in the pharmaceutical industry.

This study investigates the simultaneous prediction of active pharmaceutical ingredient (API) concentration and mass gain in film-coated tablets using Partial Least Squares (PLS) regression combined with three data fusion (DF) techniques: Low-Level (LLDF), Mid-Level (MLDF), and High-Level (HLDF). Near-Infrared (NIR) and Raman spectroscopy were utilized in both reflection and transmission modes, providing four types of spectral data per tablet. Transmission models proved more effective for API prediction by capturing data from the entire tablet, while reflection models excelled in assessing mass gain by focusing on the surface layer. Among the DF strategies, MLDF with Principal Component Analysis (PCA) offered the most significant improvements in predictive accuracy by filtering out irrelevant information. Variable selection methods further enhanced model performance by reducing the number of latent variables required. Overall, the integration of multiple spectral datasets and DF techniques resulted in models that gave predictions for evaluation samples with lower errors, demonstrating their potential to optimize quality control in pharmaceutical manufacturing.