Flahy uses knowledge graphs to support AI-powered healthcare

AI helps companies interpret biological data for drug development and more personalized care.

Health technology company Flahy Inc. applies this approach to clinical decision support, bringing together information that could impact a person’s next step in prevention or treatment, it says Jagjit Singh (Pictured right), founder and CEO of Flahy.

“There is so much knowledge that we have to process,” he said “The knowledge layer is very important because it connects your data layer to your model layer and tells the model exactly what facts are important and what a particular data point implies. We process a large context of biological and clinical information spread across a large graph. And that decides… for a given individual what decision tree or path to take from here in terms of making a better treatment decision.”

Singh spoke to theCUBE host, John Furrier (left)for theCUBE + NYSE Wired: AI lights Interview series on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how knowledge graphs can connect patient information to support personalized healthcare decisions. (*Disclosure below.)

Using knowledge graphs in AI-powered healthcare

According to Singh, Flahy’s team spent years building a graph-based information database and training their model to recognize relationships between data points. He illustrated the approach using a hypothetical patient whose genetic mutation and cholesterol markers could influence the interpretation of a new clinical finding.

“I’m looking for that one person [who] had a genetic mutation and this specific marker for high cholesterol. Would the way this person should be treated change if I receive a new clinical signal? That is a completely different question. It’s a graphic design issue.”

Singh said Flahy is working with graph technology companies, including Neo4j Inc. One challenge is incorporating wearable device metrics into a graph along with other health information so the system can interpret changes over time.

“We developed our own proprietary engines,” he said. “When you look at clinical decision making or the problem I’m trying to solve, it’s always a traversal problem. When you’re dealing with longitudinal data, you have to find a way to fit it into a particular graph. For me, that was a challenge that we’re trying to solve effectively by connecting the dots across different modalities.”

According to Singh, AI-powered healthcare requires a clear explanation of how information influences a decision. Flahy’s consumer offering, FlahyLife, combines biological and health information to guide next steps in prevention, early detection and treatment selection, according to the company.

“We work with leading clinical laboratories and health systems and seek to leverage our platform toward better clinical decision-making and closing care gaps,” Singh said. “If you could just connect the graph, you could make the right case. You’re mentoring the right people for the right test at the right time.”

Here’s the full video interview, part of SiliconANGLE and theCUBE’s coverage theCUBE + NYSE Wired: AI lights Interview series:

(*Disclosure: TheCUBE is a paid media partner for theCUBE + NYSE Wired: AI Luminaries interview series. Neither Neo4j, the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over theCUBE or SiliconANGLE content.)

Photo: SiliconANGLE