MIT and Takeda Develop AI-based Estimator to Improve Pharmaceutical Manufacturing

MIT and Takeda have teamed up to develop a physics-enhanced autocorrelation-based estimator (PEACE), which uses physics and machine learning to categorize rough particle surfaces in pharmaceutical pills and powders. The aim is to increase efficiency, accuracy, and reduce the number of failed batches of products. This development is part of the MIT-Takeda Program, an ongoing collaboration between MIT and Takeda launched in 2020, which combines the experience of both MIT and Takeda to solve problems at the intersection of medicine, artificial intelligence, and healthcare. This new method could revolutionize the pharmaceutical manufacturing process, allowing drug production to be more sustainable, cost-effective, and efficient.