Use of machine learning in prediction of granule particle size distribution and tablet tensile strength in commercial pharmaceutical manufacturing.

In the manufacturing of pharmaceutical Oral Solid Dosage (OSD) forms, Particle Size Distribution (PSD) and Tensile Strength (TS) are common in-process tests that are controlled in order to achieve the quality targets of the end-product. The Quality by Design (QbD) concept elaborates process understanding and sufficient controls. However, for older pharmaceutical products upscaled to commercial phase with Quality by Testing (QbT) approach, the knowhow of the product-specific critical parameters is often limited. In this study, two predictive machine learning (ML) models were used for a commercial tablet product, for which historical data of raw materials, production, in-process controls and condition monitoring were available. With the aforementioned data, the aim was to predict the PSD and the TS that indicate the product quality. The feature importance was used to evaluate the parameter importance for the PSD and the TS. Partial dependence, in turn, was used to estimate the parameter impact on the predicted TS. The study illustrates the capability of the ML models to bring additional value for commercial products through the enhanced product-related knowhow.

Solid-state properties and relationship between anhydrate and monohydrate of baclofen.

Baclofen, a widely used antispastic agent, has been found to exist in two crystalline forms, the anhydrate and monohydrate. The aim of this study was (1) to identify and characterize these two solid phases of baclofen, and (2) to examine the processing-induced phase transformations associated with wet granulation of baclofen. Using multiple techniques (powder X-ray diffraction, thermal analysis, vibrational spectroscopy and water vapor sorption analysis), a structural relationship has been established between the anhydrate and monohydrate of baclofen. Thermal and variable-temperature powder X-ray diffraction data indicate that the monohydrate, which presumably belongs to the channel hydrate class, dehydrates at 60 degrees C with the formation of the anhydrate. Furthermore, the anhydrate to monohydrate transformation followed by optical microscopy was found to occur via a solvent-mediated route. During wet massing experiments, the critical moisture value for the hydrate formation under the conditions of the present study was identified using qualitative powder X-ray diffraction and Raman spectroscopy. Finally, the interconversion pathway between the two crystalline forms of baclofen was presented. The knowledge of this pathway provides better understanding and control of the solid state of baclofen during processing and storage.