Conclusion

Although the biopharma industry is highly regulated, there are many opportunities to develop better and more robust processes. This is also encouraged by health authorities with the various guidelines that have been adopted in the past, such as PAT, QbD, Continuous Manufacturing and Real-time Release. All the elements for technical implementation are in place and there is acceptance by the authorities. There is a perception that real-time monitoring is difficult to implement and requires a lot of change. It is possible to integrate real-time monitoring gradually and it should be considered from a soft sensor perspective. This concept has been successfully implemented in other industries. It required relatively simple model training and the use of established statistical tools such as multivariate statistics or neural networks. Such approaches have been practiced for decades and are known as chemometrics when multiple analytical methods were required to measure a particular analytical attribute. A soft sensor could also be described with predictive chemometrics. A fully controlled and automated process would also help reduce drug shortages, improve process economics, and reduce the environmental footprint.