Mitsubishi Tanabe, Hitachi join forces in AI-enabled clinical trials

Doctor typing on laptop
Mitsbishi Tanabe applies Hitachi’s artificial intelligence technology to make clinical trials more efficient and to drive down drug development costs. (Getty/shironosov)

In the face of increasing drug pricing pressure, pharma companies are actively looking for ways to reduce development costs. Through a new collaboration, Mitsubishi Tanabe Pharma will apply Hitachi’s digital technology such as artificial intelligence to make clinical trials more efficient.

The partnership focuses on cutting the time spent on searching and collecting information from medical papers and in the planning stage of clinical trials.

Instead of relying on a human researcher to do that, the pair wants to utilize AI technology such as natural language processing and deep learning to automate the process. A test run since the idea’s inception in 2017 has confirmed that the approach can shorten the time spent on information search and collection by about 70%, and that the data collected and organized are also accurate, the companies reported.

FierceBiotech Executive Breakfast

Getting Real: The Changing Tide on Real-World Evidence in Drug Development

Join FierceBiotech and a panel of industry experts for an executive breakfast at BIO. We will discuss the impacts of real-world evidence on drug development and address the important questions that companies are facing including where to find the right talent & technology and how to deploy it internally or with partners. Join us in Philadelphia on June 5th for this important discussion.

Now, they’re rolling out the solution—which is based on Hitachi’s IoT platform called Lumada—on full scale to the pharmaceutical industry in Japan and around the globe. The two Japanese firms will also work closely to create new products that will eventually cover different aspects of the entire clinical trial process.

Wider adoptions of electronic health records and cloud-based clinical research management tools give artificial intelligence and machine learning an opportunity to work in the clinical development process, and many companies have emerged in the field.

Roivant's Datavant, for example, uses AI to collect and analyze datasets from clinical trial and real-world settings to inform future trial design and data interpretation. New York-based Owkin, which recently nabbed a $11 million series A, is applying transfer learning and federated learning to analyze molecular and imaging libraries as well as patient datasets to uncover complex biomarker patterns that cause disease. 

Suggested Articles

Yale researchers discovered that AstraZeneca’s anti-VEGF cancer drug cediranib may boost the effectiveness of PARP inhibitors.

AbbVie became yet another biopharma learning that aggressive brain cancer glioblastoma is one of the toughest cancers out there.

With the Shire deal done, Takeda is looking to lighten the load a little from its central R&D base. To that end, it has launched a new biotech, Phathom.