A genetic mutation and a cholesterol marker can change the treatment question for an individual patient. Flahy Inc. is using knowledge graphs in healthcare to connect those biological details with clinical information and support more personalized decisions about prevention and treatment, according to founder and chief executive officer Jagjit Singh.
Key takeaways
- Flahy links biological and clinical information to support individualized care decisions.
- Neo4j supports its graph technology work alongside proprietary decision engines.
- Wearable readings pose a challenge for tracking health changes within graphs.
In an interview reported by SiliconANGLE on October 11, 2026, Singh described a knowledge layer that connects patient data with AI models. He spoke with host John Furrier for the theCUBE + NYSE Wired: AI Luminaries series, explaining how the company uses relationships among data points to help determine a person’s next clinical step.
How Flahy uses knowledge graphs in healthcare
Flahy brings biological and clinical information into a graph so its models can recognize relationships relevant to an individual’s care. Singh said the team has spent years building its graph-based database and training the model to identify those connections.
“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,” Singh said.
The application is personalized clinical decision support: determining which treatment route fits a person’s biological markers and mutations. Singh illustrated the approach with a hypothetical patient who has both a genetic mutation and a particular high-cholesterol marker. A new clinical signal would raise the question of how those existing details affect treatment selection.
For Flahy, applying knowledge graphs to healthcare means connecting that wider biological context to a decision tree for the individual.
Neo4j collaboration and proprietary decision engines
Flahy works with graph technology companies, including Neo4j Inc., and has built its own engines to address clinical decision-making within graphs, Singh said. He described the underlying task as a traversal problem—working through the graph’s connections to support a care decision.
“We have created our own proprietary engines,” he said. His account links that development to the challenge of connecting information across different data types, including health readings collected over time.
Longitudinal data is a particular difficulty. Wearable-device readings need to sit alongside other health information in a graph that allows the system to interpret changes over time.
“When it comes to longitudinal data, you have to find a way to put it in a specific graph,” Singh said. He described this as a challenge the company is working to solve by connecting separate modalities.
Consumer guidance and clinical deployment
FlahyLife, the company’s consumer offering, combines biological and health information to guide prevention, early detection and treatment selection. It applies the company’s approach to identifying next steps for an individual.
Flahy is also working with clinical laboratories and health systems and trying to deploy its platform to improve clinical decision-making and close care gaps, according to Singh. He described the aim as connecting the graph to help match people with the appropriate test at the appropriate time.
Article produced with the assistance of artificial intelligence and reviewed by the editorial team.