UCSF, Fortanix, Intel, Microsoft team up to accelerate clinical AI development

The organizations say they expect the platform, announced Wednesday, to reduce the time and cost associated with creating clinical grade AI algorithms while maintaining data security.
By Kat Jercich
09:01 AM
UCSF Mission Bay campus

(Wikimedia Commons)

UC San Francisco announced Wednesday that its Center for Digital Health Innovation had formed a collaboration with Fortanix, Intel and Microsoft Azure to establish a platform to accelerate the development and validation of clinical algorithms.

According to CDHI, the BeeKeeperAI platform will accelerate the development of clinical artificial intelligence algorithms by 1,000 times – from 30 months to one day. 

The platform's "zero-trust" environment, said the organizations, will protect both an algorithm's intellectual property and healthcare data privacy.

"While we have been very successful in creating clinical grade AI algorithms that can safely operate at the point of care, such as immediately identifying life threatening conditions on X-rays, the work was time-consuming and expensive," said Dr. Michael Blum, associate vice chancellor for informatics and executive director of CDHI, in a statement provided to Healthcare IT News. 

"Much of the cost and expense was driven by the data acquisition, preparation and annotation activities," Blum continued. "With this new technology, we expect to markedly reduce the time and cost while also addressing data security concerns."

WHY IT MATTERS

Unbiased algorithm models depend on highly detailed clinical data for development, optimization and validation. Those used in clinical care must perform across diverse patient populations and be equipment agnostic.

By leveraging the resources of the collaborating organizations, the platform will calibrate a proven clinical algorithm – which rapidly identifies those needing a blood transfusion in the emergency department following trauma – against a simulated data set, said the groups involved in the partnership. 

"Validation and security of AI algorithms is a major concern prior to their implementation into clinical practice. This has been an oftentimes insurmountable barrier to realizing the promise of scaling algorithms to maximize potential to detect disease, personalize treatment, and predict a patient’s response to their course of care,” Dr. Rachael Callcut, CDHI director of data science and codeveloper of the BeeKeeperAI solution, said in a statement. 

"Bringing together these technologies creates an unprecedented opportunity to accelerate AI deployment in real-world settings," Callcut added.

The organizations say the specifically curated patient datasets will remain at all times under control of the healthcare institution via Azure. Multiple parties will be able to leverage the system without needing to trust each other. 

"This collaboration with UCSF, Fortanix and Microsoft Azure demonstrates the amazing potential of confidential computing with Intel’s hardware-rooted protection defending the data," said Anil Rao, vice president of data center security and systems architecture for the platform hardware engineering division at Intel. 

In addition to validation, the ultimate goal, according to the coalition, will be to support multisite clinical trials, thus speeding the innovation of AI tools overall.

THE LARGER TREND

The use of clinical AI and machine learning has come to the forefront in recent years, particularly in research settings. 

"The possibilities are endless in what we can accomplish together with AI/ML in medicine and patient care," Mayo Clinic's Dr. Tufia Haddad told Healthcare IT News in September.

"Think of the data shackled in our EHRs, labs, radiology and pathology images. The breadth of data contained within a single patient genome and microbiome. And all the data our patients generate each day that we do not yet routinely collect," she continued.

And the novel coronavirus pandemic has spurred more innovation. This past week, researchers at the University of Minnesota said they, in partnership with Epic, had validated an AI algorithm that can assess chest X-rays for potential cases of COVID-19.

"Our Cognitive Computing platform quickly pulls the X-ray, runs the algorithm, and shows the resulting prediction directly in Epic software that doctors, nurses and support staff use every day – speeding up treatment and helping protect staff," said Drew McCombs, an Epic developer, in a statement about the tool.

ON THE RECORD

"It is a privilege to work with UCSF and other technology innovators to use Confidential Computing to unlock the potential of healthcare data, and then create breakthroughs in clinical research that will help transform the healthcare industry and save lives," said Ambuj Kumar, CEO and cofounder of Fortanix, in a statement provided to Healthcare IT News.

Kat Jercich is senior editor of Healthcare IT News.
Twitter: @kjercich
Email: kjercich@himss.org
Healthcare IT News is a HIMSS Media publication.

Want to get more stories like this one? Get daily news updates from Healthcare IT News.
Your subscription has been saved.
Something went wrong. Please try again.