Machine learning modeling for ultrasonic quality attribute assessment of pharmaceutical tablets for continuous manufacturing and real-time release testing.

In in-process quality monitoring for Continuous Manufacturing (CM) and Critical Quality Attributes (CQA) assessment for Real-time Release (RTR) testing, ultrasonic characterization is a critical technology for its direct, non-invasive, rapid, and cost-effective nature. In quality evaluation with ultrasound, relating a pharmaceutical tablet's ultrasonic response to its defect state and quality parameters is essential. However, ultrasonic CQA characterization requires a robust mathematical model, which cannot be obtained with traditional first principles-based modeling approaches. Machine Learning (ML) using experimental data is emerging as a critical analytical tool for overcoming such modeling challenges. In this work, a novel Deep Neural Network-based ML-driven Non-Destructive Evaluation (ML-NDE) modeling framework is developed, and its effectiveness for extracting and predicting three CQAs, namely defect states, compression force levels, and amounts of disintegrant, is demonstrated. Using a robotic tablet handling experimental rig, each attribute's distinct waveform dataset was acquired and utilized for training, validating, and testing the respective ML models. This study details an advanced algorithmic quality assessment framework for pharmaceutical CM in which automated RTR testing is expected to be critical in developing cost-effective in-process real-time monitoring systems. The presented ML-NDE approach has demonstrated its effectiveness through evaluations with separate (unused) test datasets.

[Current status, trends, and challenges of continuous manufacturing technology for oral traditional Chinese medicine solid preparations].

In recent years, continuous manufacturing technology has attracted considerable attention in the pharmaceutical industry. This technology is highly sought after for its significant advantages in cost reduction, increased efficiency, and improved productivity, making it a growing trend in the future of the pharmaceutical industry. Compared to traditional batch production methods, continuous manufacturing technology features real-time control and environmentally friendly intelligence, enabling pharmaceutical companies to produce drugs more efficiently. However, the adoption of continuous manufacturing technology has been slow in the field of traditional Chinese medicine(TCM) pharmaceuticals. On the one hand, there is insufficient research on continuous manufacturing equipment and technology that align with the characteristics of TCM preparations. On the other hand, the scarcity of talent with diverse expertise hampers its development. Therefore, in order to promote the modernization and upgrading of the TCM pharmaceutical industry, this article combined the current development status of the TCM industry to outline the development status and regulatory requirements of continuous manufacturing technology. At the same time, it analyzed the problems with existing TCM manufacturing models and explored the prospects and challenges of applying continuous manufacturing technology in the field of TCM pharmaceuticals. The analysis focused on continuous manufacturing control strategies, technical tools, and pharmaceutical equipment, aiming to provide targeted recommendations to drive the development of the TCM pharmaceutical industry.

Machine learning framework for extracting micro-viscoelastic and micro-structural properties of compressed oral solid dosage forms.

A compressed pharmaceutical oral solid dosage (OSD) form is a strongly micro-viscoelastic material composite arranged as a network of agglomerated particles due to its constituent powders and their bonding and fractural mechanical properties. An OSD product's Critical Quality Attributes, such as disintegration, drug release (dissolution) profile, and structural strength ("hardness"), are influenced by its micro-scale properties. Ultrasonic evaluation is direct, non-destructive, rapid, and cost-effective. However, for practical process control applications, the simultaneous extraction of the micro-viscoelastic and scattering properties from a tablet's ultrasonic response requires a unique solution to a challenging inverse mathematical wave propagation problem. While the spatial progression of a pulse traveling in a composite medium with known micro-scale properties is a straightforward computational task when its dispersion relation is known, extracting such properties from the experimentally acquired waveforms is often non-trivial. In this work, a novel Machine Learning (ML)-based micro-property extraction technique directly from waveforms, based on Multi-Output Regression models and Neural Networks, is introduced and demonstrated. Synthetic waveforms with a given set of micro-properties of virtual tablets are computationally generated to train, validate, and test the developed ML models for their effectiveness in the inverse problem of recovering specified micro-scale properties. The effectiveness of these ML models is then tested and demonstrated for a set of physical OSD tablets. The micro-viscoelastic and micro-structural properties of physical tablets with known properties have been extracted through experimentally acquired waveforms to exhibit their consistency with the generated ML-based attenuation results.

Pharmaceutical Application of Process Understanding and Optimization Techniques: A Review on the Continuous Twin-Screw Wet Granulation.

Twin-screw wet granulation (TSWG) is a method of continuous pharmaceutical manufacturing and a potential alternative method to batch granulation processes. It has attracted more and more interest nowadays due to its high efficiency, robustness, and applications. To improve both the product quality and process efficiency, the process understanding is critical. This article reviews the recent work in process understanding and optimization for TSWG. Various aspects of the progress in TSWG like process model construction, process monitoring method development, and the strategy of process control for TSWG have been thoroughly analyzed and discussed. The process modeling technique including the empirical model, the mechanistic model, and the hybrid model in the TSWG process are presented to increase the knowledge of the granulation process, and the influence of process parameters involved in granulation process on granule properties by experimental study are highlighted. The study analyzed several process monitoring tools and the associated technologies used to monitor granule attributes. In addition, control strategies based on process analytical technology (PAT) are presented as a reference to enhance product quality and ensure the applicability and capability of continuous manufacturing (CM) processes. Furthermore, this article aims to review the current research progress in an effort to make recommendations for further research in process understanding and development of TSWG.

Non-destructive detection of disintegrant levels in compressed oral solid dosage forms.

Quality issues related to compressed oral solid dosage (OSD) forms, such as tablets, arise during the design, development, and production stages, despite established processes and robust production tools. One of the primary quality concerns is the disintegration properties and drug release profile of immediate-release OSD products, which depend on their micro-texture and micro-viscoelastic properties at the grain level. These properties are influenced by the composition of the formulation, particularly the disintegrant level in the tablet matrix and the porosity of the matrix. In this study, a novel, rapid, non-destructive ultrasonic characterization technique was proposed to correlate the sensitivity of propagating elastic wave speeds, physical/mechanical properties, and the dispersion profile of the OSD material with the disintegrant level (% w/w) in the formulation and the compression force applied during tableting. The proposed characterization framework involves transmitting pressure (longitudinal) and shear (transverse) waves through the OSDs to calculate the speed of sound, which in turn provides information on the apparent Young's and shear moduli. In addition, the attenuation profile of the propagating wave is obtained through dispersion analysis. To investigate the impact of disintegrants and compression force on ultrasonic wave propagation in OSDs, we incorporated seven levels of a frequently used disintegrant. In each formulation, OSDs are compacted in five compaction forces. The sensitivity of wave speeds, physical/mechanical properties, and attenuation profile was observed with each disintegrant and compression force level. The utilization of ultrasonic techniques may present a viable solution for rapid, non-destructive, non-invasive, and cost-effective testing methods required in continuous manufacturing (CM) and real-time release testing (RTRT), and its practical utility in pharmaceutical manufacturing is also discussed.

Early detection and assessment of invisible cracks in compressed oral solid dosage forms.

In the pharmaceutical manufacturing industry, real-time in situ quality monitoring for detecting defects at an early stage is a desirable ability, especially in high-rate production, to minimize downstream quality-related issues, financial losses, and timeline risks. In this study, we focus on the early detection of crack formation in compressed oral solid dosage (OSD) forms at its onset before complete delamination and/or capping in downstream processing. The detection of internal tablet cracks related to local micro-stress/strain states, internal granularity (texture), and micro-structure failures is rather unlikely by traditional testing methods, such as the USP reference standards for friability, fracturing, or hardness testing. In addition, these tests do not permit the objective and quantitative evaluation of the influence of formulation and process parameters, which are critical for the development of high-quality drug products manufactured at high rates on a large scale. Internal cracks (potentially resulting in 'capping' and/or 'lamination') under high-strain compaction of highly visco-elastic powder materials are a common failure mode. In the current study, two approaches are introduced and utilized for non-destructively detecting and evaluating hidden cracks in pharmaceutical compacts based on (i) varying axial load-displacement measurements and (ii) ultrasonic reflection ray tracing. The reflection ray tracing technique is a non-destructive, inexpensive, rapid, and material-sparing approach, which makes it advantageous for real-time quality monitoring and defect characterization applications. The varying axial load-displacement technique is more suitable for analytical studies, especially in the design and development phases of compressed OSD products. In this study, as a model application, utilizing these two approaches, it is demonstrated how internal and external cracks can be detected, localized, characterized, and analyzed as a function of disintegrant ratio and main compression force. Various uses of these two techniques in practice, such as in Continuous Manufacturing (CM) and Real-Time Release Testing (RTRT), are also discussed.

Current status, trends, and challenges of continuous manufacturing technology for oral traditional Chinese medicine solid preparations / 中国中药杂志

In recent years, continuous manufacturing technology has attracted considerable attention in the pharmaceutical industry. This technology is highly sought after for its significant advantages in cost reduction, increased efficiency, and improved productivity, making it a growing trend in the future of the pharmaceutical industry. Compared to traditional batch production methods, continuous manufacturing technology features real-time control and environmentally friendly intelligence, enabling pharmaceutical companies to produce drugs more efficiently. However, the adoption of continuous manufacturing technology has been slow in the field of traditional Chinese medicine(TCM) pharmaceuticals. On the one hand, there is insufficient research on continuous manufacturing equipment and technology that align with the characteristics of TCM preparations. On the other hand, the scarcity of talent with diverse expertise hampers its development. Therefore, in order to promote the modernization and upgrading of the TCM pharmaceutical industry, this article combined the current development status of the TCM industry to outline the development status and regulatory requirements of continuous manufacturing technology. At the same time, it analyzed the problems with existing TCM manufacturing models and explored the prospects and challenges of applying continuous manufacturing technology in the field of TCM pharmaceuticals. The analysis focused on continuous manufacturing control strategies, technical tools, and pharmaceutical equipment, aiming to provide targeted recommendations to drive the development of the TCM pharmaceutical industry.

Residence time distribution as a traceability method for lot changes in a pharmaceutical continuous manufacturing system.

Residence time distribution (RTD) models were developed to track raw material lots and investigate batch transitions in a continuous manufacturing system. Two raw materials with similar physical properties (granular metformin and lactose) were identified via Principal Component Analysis (PCA) from a library of bulk material properties and used to simulate the switching of lots during production. In-line near-infrared (NIR) spectra were collected with the powder flowing through a chute in a continuous manufacturing system to monitor metformin and lactose concentration in step-change experiments with Partial Least Squares (PLS) models. RTD provided an understanding of raw material propagation through the continuous manufacturing system. Transition times between raw material changes were identified using the results of two multivariate approaches PLS and PCA. The methodology was implemented to discriminate the transition zone in a raw material change, contributing to design control strategies for acceptance and diverting mechanisms.