A new partnership with Mayo Clinic will put Kansas City-stored TripleBlind’s data privacy promise to the test.
“We hope to demonstrate the potential of applying TripleBlind’s data privacy and data clean room solution to accelerate how we develop, test, and deploy AI solutions in healthcare, particularly amidst heavily regulated privacy concerns,” Riddhiman Das, co-founder and CEO, said in a release about the partnership, formally announced in the final days of 2020.
As part of the collaboration, Mayo Clinic researchers will use TripleBlind tools to validate interoperability of encrypted algorithms on encrypted data and the training of new algorithms on encrypted data.
“Our solution will enable Mayo and other health care systems to generate insights from highly regulated data without actually accessing the data – ensuring compliance with HIPAA and other standards,” Das explained.
“Health care systems have to either transfer data or algorithms outside their institution for experts to train or conduct research. This process can take many months and typically involves complicated legal contracts and a significant amount of time from technicians. Our solution eliminates this step, further protecting intellectual property.”
The TripleBlind toolkit will enable Mayo Clinic to strengthen its current practices by allowing technicians to complete diagnostic services using data wherever it’s stored, he explained.
The partnership is build around three milestones that include: validating that an algorithm already created and trained by Mayo Clinic can be delivered to remote hospitals and used locally; demonstrating TripleBlind’s toolset can be applied to train a Mayo Clinic algorithm to access data remotely and provide diagnostic services; and demonstrating that TripleBlind can support any type of medical data.
“Training novel algorithms on encrypted data sets and facilitating trust between independent parties is critical to the future of AI in medicine,” said Suraj Kapa, M.D., a practicing cardiologist and director of AI for knowledge management and delivery at Mayo Clinic.
“By using advanced mathematical encryption technologies, we will greatly enhance scientific collaboration between groups and allow for more rapid development and scalable implementation of AI-driven tools to advance healthcare.”
Click here to read more about TripleBlind’s recent strategic investment from Accenture.
A year-long research project sparked the relationship between the TripleBlind and Mayo Clinic, Das said, noting such work has already proven outlined goals of the new partnership can be realistically achieved.
“This partnership really is a great way to show how TripleBlind’s privacy tools can be applied for all kinds of healthcare applications. From building AI systems using data from multiple different sources to build more accurate and less biased systems, to allowing folks to access data from countries with strict data protection laws in a compliant and private way — this is a real paradigm shift in how we approach AI in healthcare,” he explained.
“This partnership really helps bolster confidence in our unique inventions around data and algorithm privacy.”