Machine vision-based non-destructive dissolution prediction of meloxicam-containing tablets

Machine vision systems have emerged for quality assessment of solid dosage forms in the pharmaceutical industry. These can offer a versatile tool for continuous manufacturing while supporting the framework of process analytical technology, quality-by-design, and real-time release testing. The aim of this work is to develop a digital UV/VIS imaging-based system for predicting the in vitro dissolution of meloxicam-containing tablets. The alteration of the dissolution profiles of the samples required different levels of the critical process parameters, including compression force, particle size and content of the API. These process parameters were predicted non-destructively by multivariate analysis of UV/VIS images taken from the tablets. The dissolution profile prediction was also executed using solely the image data and applying artificial neural networks. The prediction error (RMSE) of the dissolution profile points was less than 5%. The alteration of the API content directly affected the maximum concentrations observed at the end of the dissolution tests. This parameter was predicted with a relative error of less than 10% by PLS models that are based on the color components of UV and VIS images. In conclusion, this paper presents a modern, non-destructive PAT solution for real-time testing of the dissolution of tablets.

Impact of Raman mapping area and intra-tablet homogeneity on the accuracy of sustained-release tablet dissolution prediction

This exploratory study investigated the minimum required Raman mapping area for predicting sustained-release tablet dissolution profiles based on intra-tablet homogeneity. The aim was to minimize scanning time while achieving reliable dissolution profile predictions. To construct the sample set, we controlled the blending time to introduce variability in the homogeneity of the tablets. The dissolution prediction models were established using the partial least squares regression under different Raman mapping area. The accuracies of the prediction results were evaluated according to the difference factor f1 and Intersection-Union two one-sided t-tests (IU TOST) methods, and the implications conveyed by the results were discussed. The results showed that the homogeneity of sustained-release tablet affects the minimum required mapping area, and the tablets with higher homogeneity show higher prediction accuracy when using the same mapping area to model the dissolution profiles of tablets.

Convolutional neural network-based evaluation of chemical maps obtained by fast Raman imaging for prediction of tablet dissolution profiles

In this work, the capabilities of a state-of-the-art fast Raman imaging apparatus are exploited to gain information about the concentration and particle size of hydroxypropyl methylcellulose (HPMC) in sustained release tablets. The extracted information is utilized to predict the in vitro dissolution profile of the tablets. For the first time, convolutional neural networks (CNNs) are used for the processing of the chemical images of HPMC distribution and to directly predict the dissolution profile based on the image. This new method is compared to wavelet analysis, which gives a quantification of the texture of HPMC distribution, carrying information regarding both concentration and particle size. A total of 112 training and 32 validation tablets were used, when a CNN was used to characterize the particle size of HPMC, the dissolution profile of the validation tablets was predicted with an average f₂ similarity value of 62.95. Direct prediction based on the image had an f₂ value of 54.2, this demonstrates that the CNN is capable of recognizing the patterns in the data on its own. The presented methods can facilitate a better understanding of the manufacturing processes, as detailed information becomes available with fast measurements.

Interpretable artificial neural networks for retrospective QbD of pharmaceutical tablet manufacturing based on a pilot-scale developmental dataset

As the pharmaceutical industry increasingly adopts the Pharma 4.0. concept, there is a growing need to effectively predict the product quality based on manufacturing or in-process data. Although artificial neural networks (ANNs) have emerged as powerful tools in data-rich environments, their implementation in pharmaceutical manufacturing is hindered by their black-box nature. In this work, ANNs were developed and interpreted to demonstrate their applicability to increase process understanding by retrospective analysis of developmental or manufacturing data. The in vitro dissolution and hardness of extended-release, directly compressed tablets were predicted from manufacturing and spectroscopic data of pilot-scale development. The ANNs using material attributes and operational parameters provided better results than using NIR or Raman spectra as predictors. ANNs were interpreted by sensitivity analysis, helping to identify the root cause of the batch-to-batch variability, e.g., the variability in particle size, grade, or substitution of the hydroxypropyl methylcellulose excipient. An ANN-based control strategy was also successfully utilized to mitigate the batch-to-batch variability by flexibly operating the tableting process. The presented methodology can be adapted to arbitrary data-rich manufacturing steps from active substance synthesis to formulation to predict the quality from manufacturing or development data and gain process understanding and consistent product quality.

Semi-mechanistic reduced order model of pharmaceutical tablet dissolution for enabling Industry 4.0 manufacturing systems

We propose a generalization of the Weibull dissolution model, referred to as generalized Weibull dissolution model, that seamlessly captures all three fractional dissolution rates experimentally observed in pharmaceutical solid tablets, namely decreasing, increasing, and non-monotonic rates. This is in contrast to traditional reduced order models, which capture at most two fractional dissolution rates and, thus, are not suitable for a wide range of product formulations hindering, for example, the adoption of knowledge management in the context of Industry 4.0. We extend the generalized Weibull dissolution model further to capture the relationship between critical process parameters (CPPs), critical materials attributes (CMAs), and dissolution profile to, in turn, facilitate real-time release testing (RTRT) and quality-by-control (QbC) strategies. Specifically, we endow the model with multivariate rational polynomials that interpolate the mechanistic limiting behavior of tablet dissolution as CPPs and CMAs approach certain values of physical significance (such as the upper and lower bounds of tablet porosity or lubrication conditions), thus the semi-mechanistic nature of the reduced order model. Restricting attention to direct compaction and using various case studies from the literature, we demonstrate the versatility and the capability of the semi-mechanistic ROM to estimate changes in dissolution due to process disturbances in tablet weight, porosity, lubrication conditions (i.e., the total amount of shear strain imparted during blending), and moisture content in the powder blend. In all of the cases considered in this work, the estimations of the model are in remarkable agreement with experimental data.

Raman mapping-based non-destructive dissolution prediction of sustained-release tablets

In this paper, the applicability of Raman chemical imaging for the non-destructive prediction of the in vitro dissolution profile of sustained-release tablets is demonstrated for the first time. Raman chemical maps contain a plethora of information about the spatial distribution and the particle size of the components, compression force and even polymorphism. With proper data analysis techniques, this can be converted into simple numerical information which can be used as input in a machine learning model. In our work, sustained-release tablets using hydroxypropyl methylcellulose (HPMC) as matrix polymer are prepared, the concentration and particle size of this component varied between samples. Chemical maps of HPMC are converted into histograms with two different methods, an approach based on discretizing concentration values and a wavelet analysis technique. These histograms are then subjected to Principal Component Analysis, the score value of the first two principal components was found to represent HPMC content and particle size. These values are used as input in Artificial Neural Networks which are trained to predict the dissolution profile of the tablets. As a result, accurate predictions were obtained for the test tablets (the average f₂ similarity value is higher than 59 with both methods). The presented methodology lays the foundations of the analysis of far more extensive datasets acquired with the emerging fast Raman imaging technology.

Dissolution assessment of allopurinol immediate release tablets by near infrared spectroscopy

The purpose of this study was to develop a NIR spectroscopic method for assessment of drug dissolution from allopurinol immediate release tablets. Thirty three different batches of allopurinol immediate release tablets containing constant amount of the active ingredient, but varying in excipients content and physical properties were introduced in a PLS calibration model. Correlating allopurinol dissolution reference values measured by the routinely used UV/Vis method, with the data extracted from the NIR spectra, values of correlation coefficient, bias, slope, residual prediction determination and root mean square error of prediction (0.9632, 0.328%, 1.001, 3.58, 3.75%) were evaluated. The obtained values implied that the NIR diffuse reflectance spectroscopy could serve as a faster and simpler alternative to the conventional dissolution procedure, even for the tablets with a very fast dissolution rate (>85% in 15minutes). Apart from the possibility of prediction of the allopurinol dissolution rate, the other multivariate technique, PCA, provided additional data on the non-chemical characteristics of the product, which could not be obtained from the reference dissolution values. Analysis on an independent set of samples confirmed that a difference between the UV/Vis reference method and the proposed NIR method was not significant. According to the presented results, the proposed NIR method may be suitable for practical application in routine analysis and for continuously monitoring the product's chemical and physical properties responsible for expected quality.