Flahy taps knowledge graphs to connect patient data for smarter clinical decisions

Machine learning is enabling healthcare organizations to make sense of biological data in ways that support drug development and more tailored patient care. Flahy Inc., a healthcare technology firm, is channeling this capability into clinical decision support by assembling disparate information sources that shape whether a patient should pursue prevention, early detection or a specific treatment path, according to Jagjit Singh, the company's founder and chief executive officer.

There's so much knowledge that we have to process. The knowledge layer is very critical because it connects your data layer to your model layer and it tells the model exactly what facts matter and what a specific data point implies. We process a big context of biological and clinical information that's spread across a big graph. And that decides … for a given person what decision tree or what route to take from here in terms of better treatment decision-making.

Jagjit Singh, founder and CEO of Flahy

Singh discussed the role of knowledge graphs in personalizing healthcare decisions during an appearance on theCUBE, SiliconANGLE Media's livestreaming studio, as part of the theCUBE + NYSE Wired: AI Luminaries interview series.

Building relationships across patient data

Flahy has invested years constructing a graph-structured data repository and refining algorithms that detect connections between different data elements, Singh explained. He offered an example involving a hypothetical patient: if someone carries a particular genetic mutation and shows elevated cholesterol, a new clinical finding might warrant a different treatment approach than it would for someone without those characteristics.

I'm looking for this one person [who] had a genetic mutation and this specific high cholesterol marker. If I have a new clinical signal, would that change how this person should be treated? That is a very different question. It's a graphical question by design.

Jagjit Singh

Flahy partners with graph database vendors including Neo4j Inc. to power its system. A significant hurdle involves integrating readings from wearable devices into the graph structure alongside other clinical and biological data, enabling the platform to track how a patient's condition evolves.

We have created our own proprietary engines. If you look at clinical decision-making or the problem that I'm trying to solve, it is always a traversal problem. When it comes to longitudinal data, you have to find a way to put it in a specific graph. For me, that's been a challenge which we are effectively trying to solve in terms of how to connect the dots across separate modalities.

Jagjit Singh

Transparency in how data drives clinical decisions is essential for AI-powered healthcare systems, Singh noted. Flahy's consumer product, FlahyLife, merges biological markers and health data to inform decisions about prevention, screening and treatment options.

https://www.youtube.com/embed/Sr0BjMxUJXo?feature=oembed

We are working with leading clinical laboratories and health systems and trying to deploy our platform in terms of better clinical decision making and closing care gaps. If you could simply connect the graph, you can reason in a correct way. You're serving the right people for the right test at the right time.

Jagjit Singh