Product Quality: Prediction by Using Big Data in Pharmaceutical Manufacturing
Dr Md Anawar Hossain
Analysis of big data collected from the different steps of medicine manufacturing processes for long time helps the pharma industry to find alternative ways to determine their product quality.
New innovation in pharmaceutical industry
In the field of pharmaceutical industry, researchers are always doing their best efforts for making new innovation, development of life-saving products, and a high level of product quality. But the pharmaceutical industries are very cautious and also relatively reluctant to adopt changes, new technologies, and approaches that could improve ways of working in the production of medicines, because the area of pharmaceutical production is highly regulated by the regulatory authority, and they need long and heavily documented proof for implementation (Žagar and Mihelič, 2022). Regulatory bodies, such as FDA (Food and Drug Administration, US) and EMA (European Medicines Agency) have recommended the necessity of more data-oriented medicine manufacturing.
Data analysis and product quality
The regulatory bodies encourage the pharmaceutical industry to use new digital technologies and better utilize the data collected to show the quality of their products and improvement of manufacturing efficiency. In the pharmaceutical industries, a lot of processes, machines and equipment are used to manufacture medicines. These machines are equipped with numerous sensors monitoring and controlling critical process and equipment parameters. Therefore, manufacturing of every medicine produces a large amount of data which are sourced from laboratory analysis of incoming raw materials, process parameters, intermediate product characteristics, complex compression process time series outputs available for every second of the manufacturing process and final product quality (Žagar and Mihelič, 2022). These databases are used to confirm the quality of incoming raw materials, intermediate products, and final products. They reported that the excipients, incoming materials and direct compression process have a significant impact on final product quality.
Conclusions
Žagar and Mihelič (2022) collected the data from three main databases: “Laboratory Sample Manager Database”, ‘’Production database’’, and ‘’Process time series database connected with tablet press SQL database’’. They reported that the data is highly valuable because it provides an insight into every 10 seconds of the process trajectory for 1005 actual production batches along with product quality collected over several years. They indicated that advanced analysis models can be developed using this dataset. In addition, this dataset can be used to determine product quality and develop procedures which would lead to the omission of current conventional and time-consuming laboratory testing.
Reference
Žagar, J., Mihelič, J. (2022). Big data collection in pharmaceutical manufacturing and its use for product quality predictions. Sci Data Vol. 9, pp. 99.