Duality Technologies’ Post

Happy AI Friday! You might not be familiar with the predictive model being built at Dana-Farber Cancer Institute called OncoNPC, but it's exciting for humans concerned about cancer. The goal is to train this model across many disparate datasets, including genomic data, to better identify sites of origin for cancers. In an interview with Center for Healthcare Innovation writer David Raths, Dr. Alexander Gusev described their data challenge: "There's a global challenge in academia of patient and clinical data sharing because it is almost always coming from sensitive patient groups, sometimes who have not consented to have their data shared. But even if they have consented to data sharing, they are still always concerned about de-identification with genetic data." By utilizing Duality's Confidential AI solution, which combines Confidential Computing with Federated Learning, Dr. Gusev and the team can move much faster in terms of both attracting and onboarding new data partners (health care providers) as well as analyzing the data from the partners they already have. "Our hope is that from there we can recruit others...that this can work in a plug-and-play way for two hospitals. I think that'll be the practical way to convince people that this can continue to work at a larger number of institutions." Dr Gusev closed by describing the significance of the ready-to-deploy solution by Duality "The ability to move through different levels of security — to either have just a federated approach where nobody has access to anybody else's data, or, on top of that, have a Trusted Execution Environment where even those individual data analyses are done in highly secure environments — that kind of flexibility is something that's pretty unique that I haven't seen from other tools. I think, especially as we try to expand this out to other institutions, they may have additional restrictions that they want to impose on their individual unit, and this software service allows us to do that. So that's also the future-proofing nature of this. If somebody wants something even more secure, we can toggle that on for them. " Read the interview with Dr. Alexander Gusev here: https://lnkd.in/dv52-ERE #oncology #healthcare #realworlddata #dataprivacy #machinelearning #secureAI #confidentialAI #confidentialcomputing #federatedlearning

This is a perfect example of responsible AI development. Protecting privacy while leveraging data for medical breakthroughs is a win-win.

Like
Reply

To view or add a comment, sign in

Explore topics