New Study Shows Briya's AIRE AI Research Platform Expands Steatotic Liver Disease Identification by 360% Using Previously Overlooked Radiology Data

Briya AIRE's analysis of 28,795 abdominal ultrasound reports found 78% of steatotic liver patients were identified only through unstructured radiology reports

NEW YORK, Oct. 8, 2026 /PRNewswire/ -- Briya, the health AI company redefining healthcare research with AIRE, a trusted AI platform, today announced results from a real-world study demonstrating how AI and natural language processing (NLP) can uncover under-documented cases of metabolic dysfunction-associated steatotic liver disease (MASLD) from unstructured radiology reports. Using AIRE, researchers identified 360% more steatotic liver patients than structured data alone revealed. The technology then enabled risk stratification for patients at risk of progression, creating opportunities to intervene before the disease becomes irreversible, with the potential to save lives.

The study demonstrates how healthcare organizations, pharma companies and research and consulting firms can use existing routine data to identify overlooked patients, strengthen risk stratification and generate real-world evidence without additional diagnostic procedures or burden on clinical workflows.

"Briya AIRE fundamentally changed how we were able to identify patients for this study," said Gadi Lalazar, MD, Head of the Liver Unit at Shaare Zedek Medical Center. "Many of these patients may not have known they had steatotic liver disease because the finding was buried in an ultrasound report performed for some other reason. Identifying them earlier creates an opportunity for physicians to initiate treatment before the disease progresses to more serious and potentially irreversible stages." 

The findings demonstrate how unlocking information from unstructured radiology reports gives researchers access to larger, more representative patient populations without requiring additional data collection. The study, titled "Leveraging Real-World Data and NLP to Identify At Risk Metabolic Dysfunction Associated Steatohepatitis in the General Population," will be presented at AASLD's The Liver Meeting 2026 by Dr. Or Shaked, Director of Medical Research Solutions at Briya, on November 6 at 1:00 PM MT during the "MASLD/MASH - Epidemiology and Natural History, Prevention and Outcomes" session. (Abstract 2476)

The study analyzed 28,795 abdominal ultrasound reports from 20,422 unique patients between 2020 and 2024 and identified an additional 4,036 patients with a steatotic liver. This expanded the relevant study population by 360%, from 1,122 to 5,158 patients.

The findings revealed a major gap when looking at structured records or diagnostic codes alone. Only 22% of identified steatotic liver patients had a documented diagnosis in structured EHR fields, while 78% were identified exclusively through Briya AIRE's NLP analysis of unstructured ultrasound data. External expert validation found 94% precision and 97% recall for steatotic liver detection.

With a more complete study population, researchers then assessed the risk of disease progression using existing laboratory data and ultrasound reports. The analysis identified 4,368 patients whose FIB-4 scores placed them above the conventional at-risk threshold.

"AIRE's specialized research agents were used to extract information from unstructured fields, harmonize it with existing structured data and build the study population," said Dr. Or Shaked of Briya. "The goal is to take on more of the complex data preparation work so researchers can use more of the available information and focus on answering scientific questions that can ultimately influence care."

AIRE enabled the researchers to extract clinically relevant information from tens of thousands of radiology reports and incorporate it into the study population alongside existing clinical and laboratory data. Doing this manually would have required extensive review and data preparation, making it difficult to apply consistently at scale. By automating much of that labor-intensive work, AIRE significantly accelerated the research timeline.

About Briya

Briya is the health AI company behind AIRE, a scientific AI platform built to expand research capacity and deliver better evidence. AIRE handles the operational complexity between fragmented data and defensible evidence, while preserving scientific rigor and keeping researchers in control. Combining scientific AI, NLP and no-code advanced analytics with secure access to a global real-world data network, AIRE gives researchers across life sciences, healthcare and service firms more room for science.

Visit us at briya.com. 

Media Contact:

Ellie Hanson
FINN Partners for Briya
[email protected] 

SOURCE Briya