A new AI assisted approach aligns data standards and accelerates interoperability in biomedical research
We demonstrate how Large Language Models (LLMs) accelerate biomedical data harmonization through automated Common Data Element (CDE) generation. We processed 31 datasets including clinical taxonomies and research data dictionaries through OpenAI's Generative Pre-trained Transformer - 4 (API Model gpt-4-0613), generating comprehensive metadata for each element using a template-based system. Subject-matter experts validated outputs, finding 94% of generated metadata fields required no revision overall, with an unweighted accuracy of 83.8%, unweighted, for semi-structured sources. Dramatically faster than manual approaches. Our system uses ElasticSearch with weighted field matching to identify semantic equivalences between variables, avoiding duplicate CDEs while building a standardized repository. Testing with Alzheimer's Disease Neuroimaging Initiative (ADNI) and Global Parkinson's Genetic Program (GP2) datasets showed 32.4% of previously unseen headers successfully mapped to our CDEs, with interoperability scores averaging 53.8/100 based on matching, completeness, and compliance metrics. This approach automates the most tedious aspects of data integration, reducing barriers to cross-study collaboration in biomedical research.
Authors
- Elise Marsan (ORCID: https://orcid.org/0000-0003-1975-290X)
- Mukta Phatak (ORCID: https://orcid.org/0009-0003-2126-3723)
- Lietsel Jones (ORCID: https://orcid.org/0000-0001-5293-0654)
- Alifiya Kapasi (ORCID: https://orcid.org/0000-0003-1911-8482)
- Brittany N. Dugger (ORCID: https://orcid.org/0000-0003-2141-8855)
- Patrick Brannelly (ORCID: https://orcid.org/0000-0001-6430-954X)
- Mathew J. Koretsky (ORCID: https://orcid.org/0000-0003-4341-3991)
- Michael Griswold
- Faraz Faghri (ORCID: https://orcid.org/0000-0001-5744-8728)
- Cornelis Blauwendraat (ORCID: https://orcid.org/0000-0001-9358-8111)
- PK Chiang
- Dan Vitale (ORCID: https://orcid.org/0000-0002-0637-3671)
- Nicole Kuznetsov (ORCID: https://orcid.org/0009-0005-9847-0282)
- Laurel Screven (ORCID: https://orcid.org/0000-0002-1330-7779)
- Owen Bianchi
- Bryant Jen
- Sara Bandres-Ciga
- Paige Jarreau
- Kristin Levine
- Hampton Leonard
- Lana Sargent (ORCID: https://orcid.org/0000-0001-5555-9985)
- Yang Fann
- Timothy Hohman (ORCID: https://orcid.org/0000-0002-3377-7014)
- Shannon Ballard
- Caroline Pantazis
- David Gutman
- Kate Andersh
- Andrew B. Singleton
- Hirotaka Iwaki
- Abhradeep Mukherjee
- Syed Shah
- Rodney Alan Long
- John F. Crary
- Mike A. Nalls
- Sarah Biber
- Kendall van Keuren-Jensen
Institutions
- Rush University Medical Center (US)
- National Institutes of Health (US)
- Allen Institute for Brain Science (US)
- Emory University (US)
- Virginia Commonwealth University (US)
- Vanderbilt University (US)
- University of Washington (US)
- Data Tecnica International (United States) (US)
- National AIDS Housing Coalition (US)
- Office of the Director (US)
- Fukushima National College of Technology (JP)
- Rafiki Coalition (US)
- National Institute of Neurological Disorders and Stroke (US)
- National Institute on Aging (US)
- Office of Extramural Research (US)
- Jackson State University (US)
- University of California, Davis (US)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2026-06-12
- DOI
- https://doi.org/10.1038/s41746-026-02795-z
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institutes of Health