Oracle (NYSE: ORCL) and the Buck Institute for Research on Aging announced a collaboration to use Oracle Life Sciences Data Intelligence for aging-related research, including an effort to develop an FDA-grade vitality measurement tool.

The Buck Institute will use Oracle's platform, which includes more than 122 million de-identified longitudinal health records, to build patient cohorts and analyze decades of health data. Researchers aim to identify early clinical signals linked to frailty and chronic disease and develop a predictive model for age-related decline.

The work is part of the THRIVE consortium, led by Stanford University, which operates under the PROSPR program funded by the Advanced Research Projects Agency for Health (ARPA-H), an agency within the U.S. Department of Health and Human Services. The consortium's goal includes developing a validated measure of physical and mental capacity to help predict long-term health trajectories.

One research objective is to pursue qualification for what the organizations describe as the first FDA-grade "Intrinsic Capacity Score," intended as a vitality measure for healthy aging.

"Understanding how and why we age is one of the most complex challenges in modern medicine," said Dr. David Furman of the Buck Institute. "Oracle Life Sciences Data Intelligence, together with the depth and breadth of its real-world data, will enable us to begin to link early clinical signals and long-term outcomes."

Seema Verma, executive vice president and general manager of Oracle Health and Life Sciences, said the collaboration combines AI-driven analytics with a large collection of de-identified longitudinal health data to help researchers identify earlier signals of age-related decline.

Oracle Life Sciences Data Intelligence is described as a cloud-native analytics environment that incorporates generative AI capabilities and unifies multiple data sources into a single research workspace. The platform allows researchers to build cohorts, run queries, and conduct bioinformatics workflows without extensive data preparation.