Understanding Isoniazid Crystals Agglomeration Through Quality by Design and Artificial Neural Network Analysis

Introduction: The aims of this study were to determine and govern critical sources of variability in the process and to investigate the effect of excipients and processing conditions on the critical quality attributes (CQAs) of isoniazid (INZ) crystal agglomerates using a quality-bydesign (QbD) paradigm along with risk-based approach. Methods: The QbD paradigm is thoroughly exercised to determine the CQAs and to, link these CQAs to agglomerate properties and to recognize potentially significant input variables. Considering this, a risk assessment tool was executed with different excipients and processing conditions to define their effect on CQAs of agglomerates. Potential risk factors were recognized using an Ishikawa diagram and then investigated using principal component analysis and an artificial neural network. After that, all agglomerates were optimized using the design of the experiment. Results: The optimized INZ crystal agglomerates were characterized using various tools such as X-ray diffractometry, Fourier transform infrared spectroscopy, scanning electron microscopy, differential scanning calorimetry, gas chromatography, and stability testing. These characterizations confirmed that INZ did not undergo any structural modifications in the agglomerates. Conclusion: The results indicate that the QbD principles and risk assessment tool provide a valuable means to fully understand directly compressible INZ crystal agglomerates, which could be considered an exceptional alternative to the granulation method.