Diversifying Healthcare AI with Federated Learning

Podcast, Videos


Dr. Ittai Dayan, Co-founder & CEO of Rhino Health, shared how his company is transforming the way healthcare AI solutions are created, adopted and measured. He also explored how to create equitable access to advanced AI-based diagnostics and treatment pathways, how biopharma companies can leverage federated learning to overcome the challenges of accessing real-world data, and more.

Here is a sneak peek of our conversation:

Q: So many different use cases, they’re basically incalculable, probably. One that comes to mind are traditional things like data registries and the ability to do data discovery. Tell us a little bit about how Rhino Health enables these components.

A: That’s a great question. Data registries, Rhino can be a compliment to; meaning you may already have a centralized data registry, but when you want to expand your search and glean additional insights from additional data modalities, you could use that index in order to discover more data and then work on that data. For example, taking a patient registry, you work on re-structured data and then add to that, imaging data.

Another example is a data registry with a hospital in Israel that has a massive amount of endoscopy and difficult surgical data which can be queried from an online tool that’s privacy-preserving. Then, when you know what to write, data exists when you need to actually work on that data, and you can run that entire process without requiring direct access to the data at any given step.

Another way to look at it is to build new registries from scratch and alleviate the need to centralize so much data. These registries, for example, could have better lineage back to the electronic medical record. They could have the ability to rediscover their identity by a hospital based on need. For example, I’ve identified patients who have a higher risk of having a complication, and I’d like to inform the doctors. That’s something that today, closing that loop is incredibly complicated with the chain of custody with that data takes until it’s made available.

In terms of discovering data, our platform is ultimately what you make of it. You can bring in your own custom software from a command line code to complicated software with GUI and you can run them on the Edge. If you have data discovery tools like using the NLP on clinical notes or doing most structured search on Dycom imaging data. You can do that using the platform and the pretty cool thing is you can do that in a privacy-preserving way while the data remains on premises or wherever the data custodian keeps it.

For more of our discussion, you can watch the whole Fireside Chat with Dr. Ittai Dayan, or listen to the podcast version, below.

To check out previous Fireside Chats and to make sure that you don’t miss any future updates, subscribe to our newsletter or follow us on YouTube, LinkedIn, Twitter, Facebook or our podcast. If you enjoyed this episode, kindly leave a review on iTunes.

About Impetus Digital

Impetus Digital is the spark behind sustained healthcare stakeholder communication, collaboration, education, and insight synthesis. Our best-in-class technology and professional services ensure that life science organizations around the world can easily and cost-effectively grow and prosper—from brand or idea discovery to development, commercialization, execution, and beyond—in collaboration with colleagues, customers, healthcare providers, payers, and patients.