When Takeda Pharmaceutical Co. and the MIT School of Engineering launched their collaboration focused on artificial intelligence in healthcare and drug development in February 2020, society was getting ready to a world-changing pandemic and AI was removed from the buzzword it’s today.
At the tip of this system, the world looks very different. AI has turn into a transformative technology in lots of industries, including healthcare and pharmaceuticals. At the identical time, the pandemic has modified the way in which many corporations approach healthcare and the way in which they develop and sell medicines.
The program was groundbreaking for each MIT and Takeda.
When this system was launched, those involved hoped it will help solve tangible, real-world problems. By the tip of this system, it has produced a catalog of recent research, discoveries and lessons learned, including a patent for a system that would improve the manufacture of small molecule drugs.
Ultimately, this system enabled each corporations to put the inspiration for a world where AI and machine learning play a central role in medicine by leveraging Takeda's expertise in biopharmaceuticals and MIT researchers' deep understanding of AI and machine learning.
“The MIT-Takeda Program has had an incredible impact and is a shining example of what could be achieved when experts from industry and academia work together to develop solutions,” says Anantha Chandrakasan, MIT's chief innovation and strategy officer, dean of the School of Engineering, and Vannevar Bush Professor of Electrical Engineering and Computer Science. “The program has not only produced research that has advanced the usage of AI and machine learning in healthcare, but has also opened up latest opportunities for MIT faculty and students through fellowships, funding, and networking.”
What made this program unique was that it focused on several specific drug development challenges that Takeda needed help solving. MIT faculty had the chance to pick projects based on their area of ​​expertise and general interest, allowing them to explore latest areas in healthcare and drug development.
“The focus was on Takeda’s most difficult business problems,” says Anne Heatherington, chief data and technology officer for research and development at Takeda and director of the Data Sciences Institute.
“These were problems that our local colleagues were really scuffling with,” adds Simon Davies, executive director of the MIT-Takeda Program and Takeda's global head of statistical and quantitative sciences. Takeda saw a possibility to collaborate with MIT's world-class researchers working just just a few blocks away. Takeda, a worldwide pharmaceutical company with global headquarters in Japan, has its global business units and R&D center just across the corner from the institute.
The program allowed MIT faculty to pick the topics they desired to work on from a pool of potential Takeda projects. Teams including MIT researchers and Takeda staff then tackled research questions in two rounds. Over the course of this system, staff worked on 22 projects covering topics akin to drug discovery and research, clinical drug development, and drug manufacturing. Over 80 MIT students and college worked in teams with greater than 125 Takeda researchers and staff to deal with these research questions.
The projects not only addressed difficult problems, but in addition the potential for scalable solutions inside Takeda or across the biopharmaceutical industry.
Some of this system's findings have already led to larger studies. For example, one group's results showed that using artificial intelligence to research speech can enable earlier detection of frontotemporal dementia while making the diagnosis faster and cheaper. Similar algorithmic analyses of the speech of patients diagnosed with ALS can even help doctors understand the progression of the disease. Takeda continues to check each AI applications.
Other discoveries and AI models that emerged from this system's research have already made an impact. For example, using a physics model and AI learning algorithms may help detect particle size, mixing, and consistency of powdered small molecule drugs, speeding up production times. Based on their research in this system, collaborators have filed a patent for this technology.
For injectable drugs akin to vaccines, AI-powered inspections can even reduce process time and the variety of false rejections. Replacing human visual inspections with AI processes has already shown measurable impact for the pharmaceutical company.
Heatherington adds: “The lessons we now have learned lay the inspiration for our next endeavor, which is to embed AI and Gen-AI (generative AI) into the whole lot we do going forward.”
During the course of this system, greater than 150 Takeda researchers and staff also participated in educational programs organized by the Abdul Latif Jameel Clinic for Machine Learning in Health. In addition to providing research opportunities, this system funded 10 students through SuperUROP, the Advanced Undergraduate Research Opportunities Program, in addition to two cohorts of the DHIVE program in health innovation, a part of the MIT Sandbox Innovation Fund Program.
Although the formal program has ended, certain features of the collaboration will proceed, akin to the MIT-Takeda Fellows, which support graduate students of their groundbreaking research in health and AI. During its lifetime, this system supported 44 MIT-Takeda Fellows and can proceed to support MIT students through an endowed fund. Organic collaboration between MIT and Takeda researchers may also proceed. And this system's partners are working to create a model for similar academic and industry partnerships to amplify the impact of this unique collaboration.