Envisioning a world of big, AI-ready—and free—healthcare data, a top medical school leads by example

The academic medical institution that maintains the world’s best-stocked library of curated, patient-deidentified and AI-ready data is going 100% open source with its digital riches.

Stanford Health announced the move Aug. 2, saying it already has nine available datasets containing more than 1 million useable assets—specifically annotated medical images—and is likely to hit 2 million within the next year.

As part of the expansion, the Center for Artificial Intelligence in Medicine and Imaging (AIMI) at Stanford University School of Medicine is partnering with Microsoft’s AI for Health program.

The two are rolling out a new platform that will be not only free to AI developers but also “more automated, accessible and visible” to all interested parties, Stanford says.

Further, the platform will have the potential to marshal and incorporate medical images from institutions around the world.

More from the announcement:

Part of the idea is to create an open and global repository. The platform will also provide a hub for sharing research, making it easier to refine different models and identify differences between population groups. The platform can even offer cloud-based computing power so researchers don’t have to worry about building local, resource-intensive clinical machine-learning infrastructure."

That’s still not the end of Stanford’s plan. Eventually the Microsoft Azure-hosted platform will supply standardized machine learning tools and pretrained algorithms—“AI software in a box”—to facilitate crowdsourced AI research.

Stanford points out that medical imaging datasets must be carefully annotated by physicians before they’re ready for AI. This makes them expensive to purchase or build.

It also makes medical data proprietors, including competitive industry players, disinclined to share.

“We love that corporations are doing all this work, but we don’t love the fact that the opportunity to share information is asymmetric,” says Stanford radiologist Matthew Lungren, co-director of AIMI. “If they amass data but then lock it down, they will be the only ones who can innovate, which would shut out the important contributions by computer scientists and clinicians around the world. That’s not a position we want to be in.”

Full announcement here, free access to Stanford’s medical datasets here.

Dave Pearson

Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.

Trimed Popup
Trimed Popup