Machine Learning for Automated Quality Evaluation in Pharmaceutical Manufacturing of Emulsions

Abstract

In pharmaceutical industries, the quality assessment of emulsions is typically based on subjective examination of these samples under the microscope by trained analysts. The major drawbacks of such manual quality assessment include inter-observer variability, intra-observer variability, lack of speed and poor accuracy. In order to address these challenges, an automated approach, based on machine vision and machine learning, is investigated in this study. Micrographs, obtained during an emulsification process, are classified into four quality-based categories named TAMU (target, acceptable, marginal and unacceptable). A machine learning approach using principal component–based discriminant analysis is employed in this study for the classification. This approach is compared with manual classification results obtained for the same set of micrographs using attribute agreement analysis, which is a methodology of assessing the accuracy and precision of an evaluation system. The automated approach is demonstrated to be repeatable, 40% more accurate compared to the least performing analyst and 10% more accurate than the best performing analyst. The results show that the automated classification is superior to manual classification of micrographs with respect to speed (180 times faster), greater accuracy and repeatability. The automated approach, implemented as a soft sensor, integrated with real-time image acquisition can be applied for in situ process monitoring of emulsions. The real-time approach can be used to predict the instantaneous product quality as well as optimum process time required to achieve the desirable droplet characteristics, which will avoid over-processing and wastage of resources in pharmaceutical industries.