MIT-Takeda Researchers Combine AI & ML to Develop Estimator for Manufacturing Medicine
Pharmaceutical companies have always relied on cutting-edge technologies to deliver reliable drugs in a timely manner to the market. Over the last few years, Artificial Intelligence (AI) and Machine Learning (ML) have been an integral part of the process and healthcare providers and pharmaceutical executives are turning to them for feasible solutions.
From identifying diseases and accurate diagnosis to helping patients with clinical trials and drug manufacturing, AI and ML transformed the consumer healthcare industry. A global report for the pharmaceutical industry by Research and Market indicates that by 2026, AI spending is likely to cross $3.6 billion.
Recently, a research team from MIT-Takeda Program made a breakthrough in the process of characterizing rough particle surfaces in pharmaceutical powders and pills. The team combined physics and machine learning to classify the particles in a mixture.
Recommended: CancerGPT – This Proposed LLM-Powered Model Will Predict Drug Pair Synergies
The Process of Manufacturing and the Human Operator’s Role
During the manufacturing process, companies are required to isolate the particular pharmaceutical ingredient that is active from a suspension and dry it. A human operator is needed to keep an eye on an industrial drier, stir the material, and wait for the mixture to acquire the proper properties for condensing into medicine. The operator’s observations are crucial in this process.
Physics-Enhanced Autocorrelation-Based Estimator (PEACE) – The Breakthrough
In a recent publication published in Nature Communications, researchers from MIT and Takeda discuss techniques for making that process less subjective and significantly more effective.
The authors of the research develop a method to classify the rough surfaces that distinguish particles in a mixture using physics and machine learning. The method, which employs a physics-enhanced autocorrelation-based estimator (PEACE), could alter how pills and powders are manufactured in the pharmaceutical industry, improving accuracy and efficiency while reducing the number of defective batches of pharmaceutical products.
The Team’s Vision
The team’s effort is a component of an ongoing partnership between MIT and Takeda that was started in 2020. The MIT-Takeda Program seeks to address issues at the nexus of medical treatment, artificial intelligence, and healthcare care by utilizing the expertise of both MIT and Takeda.
In pharmaceutical manufacture, pausing an industrial-sized drier and removing samples from the production line for testing is typically required to determine whether a component is appropriately combined and dried.
Takeda researchers believe that AI could enhance the task and lessen production-slowing stoppages. Initially, the research team intended to train the model’s computer to take the position of a human operator using videos. But selecting the videos to train the model became a subjective matter. And so, the MIT-Takeda team chose to dry and filter particles while laser-illuminating them, then use physics and machine learning to determine the particle size distribution.
Recommended: World’s First AI Healthcare Radio Station Now Streaming Through Spotify
The Role of AI and ML – What the Authors Believe
The laser’s interaction with the mixture is described by a physics-derived equation, and the particle sizes are described by machine learning. George Barbastathis, professor of mechanical engineering at MIT and corresponding author of the study says that since the method doesn’t need to be stopped and started, the complete task is safer and more productive than standard operating procedure.
Because of how quickly the neural network can be trained thanks to physics, the machine learning algorithm generally does not need a lot of datasets to learn how to do its job.
Currently, only slurry products—where crystals float in a liquid—are employed as inline processes in the pharmaceutical business for particle measurements. During the mixing process, it’s impossible to measure the individual powder particles. Slurries can be converted into powders, however, when a liquid is filtered and dried, its composition changes and new measures are needed.
Using the PEACE mechanism not only expedites and improves the procedure but also makes the task safer because it necessitates fewer interactions with potentially dangerous substances, according to the authors.
To Sum It Up
The implications for the pharmaceutical industry could be enormous, allowing drug manufacturers to be more effective, sustainable, and affordable by lowering the number of tests that businesses need to do while developing products. The pharmaceutical industry has constantly struggled with the process of observing the characteristics of a drying mixture. This step is going to be a game-changer in terms of monitoring real-time particle size distribution. By leveraging AI, pharmaceutical firms have higher chances of increasing their revenue potential, marketing plans, sales productivity, and customer service.
In the future, this mechanism can be well embedded into various other industrial pharmaceutical operations as well.
[To share your insights with us, please write to firstname.lastname@example.org].
Comments are closed.