Protecting data security is one of the primary concerns when it comes to developing AI algorithms.
With that concern in mind, UC San Francisco’s Center for Digital Health Innovation (CDHI), Fortanix, Intel, and Microsoft Azure recently announced a partnership “to establish a confidential computing platform with privacy-preserving analytics to accelerate the development and validation of clinical algorithms.”
The organizations will leverage the confidential computing capabilities of Fortanix Confidential Computing Enclave Manager, Intel’s Software Guard Extensions (SGX) hardware-based security capabilities, Microsoft Azure’s confidential computing infrastructure, and UCSF’s BeeKeeperAI privacy preserving analytics to calibrate a proven clinical algorithm against a simulated data set.
“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,” said Rachael Callcut, MD, director of data science at CDHI and co-developer of the BeeKeeperAI solution. “Bringing together these technologies creates an unprecedented opportunity to accelerate AI deployment in real-world settings.”
A clinical-grade algorithm that quickly identifies individuals who require a blood transfusion in the emergency department will be used as a reference standard to compare validation results, the press release stated. In addition, the algorithm will test whether the model or the data are vulnerable to intrusion at any point. Along with validation, the overall collaborative goal is to support multi-site clinical trials that will boost the development of regulated AI solutions.
“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 Michael Blum, MD, associate vice chancellor for informatics, executive director of CDHI and professor of medicine at UCSF.
“Much of the cost and expense was driven by the data acquisition, preparation, and annotation activities. With this new technology, we expect to markedly reduce the time and cost, while also addressing data security concerns.”
Future phases will utilize HIPAA-protected data within the context of a federated environment, enabling algorithm developers and researchers to conduct multi-site validations. The ultimate aim, in addition to validation, is to support multi-site clinical trials that will accelerate the development of regulated AI solutions.