NHLBI Standardized Research Data to Aid AI

The agency has developed a new converter tool to modernize 12 petabytes of medical research data.

Updated on Sept. 22, 2026 in Heart Disease

Isometric editorial illustration of modular industrial data storage units, representing the standardization of complex medical research datasets for artificial intelligence. — The National Heart, Lung and Blood Institute has deployed a new converter tool to standardize 12 petabytes of medical research data for future AI development. AI Illustration. Upload story photo >

Live Poll

Do you believe standardizing federal research data will lead to better health outcomes for the public?

The National Heart, Lung and Blood Institute (NHLBI) has deployed a converter box designed to map clinical concepts to standardized ontological concepts. This initiative aims to optimize the value of 12 petabytes of research data for future AI applications.

Why it matters

Standardizing vast clinical datasets is critical for advancing medical discovery and artificial intelligence. By streamlining data formats, researchers hope to extract better insights from complex health archives.

The initiative currently manages 12 petabytes of research data. The agency has set a target of 80 percent data coverage across the BioData Catalyst system.

The players

National Heart, Lung and Blood Institute

This federal agency is a division of the NIH focused on heart, blood, lung, and sleep research.

eSimplicity

This technology firm was awarded a federal contract in 2026 to modernize legacy information systems.

University of North Carolina

This research institution is collaborating on the standardization of clinical data concepts.

The details

Developed alongside researchers at the University of North Carolina and Research Triangle Park, the new converter box outputs information in JSON or YAML schema formats. The project is part of a broader effort to modernize legacy systems, following a March 2026 contract award to eSimplicity.

March 2026: NIH awarded a modernization contract to eSimplicity.
June 2026: HHS announced the upcoming sunsetting of NIH NITAAC contracts.
September 21, 2026: The Federal News Network reported on the new converter box.
October 2026: NITAAC governmentwide contracts are scheduled to be sunset.
December 3, 2026: The Potomac Officers Club will host the Healthcare Summit.

Deeper Dive

This project integrates directly with the NHLBI BioData Catalyst program to enhance clinical research capabilities. It represents a significant technical expansion of the platform's ability to process and analyze massive health datasets.

Standardized data allows for faster development of AI-driven medical treatments and diagnostic tools. Patients may eventually benefit from more accurate research findings as data becomes more interoperable.

The takeaway

Standardization is the fundamental bridge that allows modern AI to interpret diverse and messy medical records. Consistent data formats will remain a major priority for federal health agencies as they move away from legacy infrastructure.