Health AI Central
Peer-Reviewed Publication
J Am Med Inform Assoc2026;33(1):67-78.January 1, 2026Journal Article

SDoH-GPT: using large language models to extract social determinants of health.

Bernardo Consoli1,2, Haoyang Wang1, Xizhi Wu3, Song Wang1, Xinyu Zhao4, Yanshan Wang3, Justin Rousseau5, Tom Hartvigsen6, Li Shen7, Huanmei Wu8, Yifan Peng9,10, Qi Long7, Tianlong Chen4, Ying Ding1
1School of Information, University of Texas at Austin, Austin, TX 78712, United States.
2School of Technology, Pontifical Catholic University of Rio Grande do Sul, Porto Alegre 90619-900, Brazil.
3Department of Health Information Management, University of Pittsburgh, Pittsburgh, PA 15261, United States.
4Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States.
5Department of Neurology, University of Texas Southwestern Medical Center, Dallas, TX 75390, United States.
6School of Data Science, University of Virginia, Charlottesville, VA 22903, United States.
7Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA 19104, United States.
8College of Public Health, Temple University, Philadelphia, PA 19122, United States.
9Department of Population Health Sciences, Weill Cornell Medicine, New York, NY 10065, United States.
10Department of Radiology, Weill Cornell Medicine, New York, NY 10065, United States.
PubMed PMC DOI PDF

Abstract

OBJECTIVE: Extracting social determinants of health (SDoHs) from medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. Here, we introduce SDoH-GPT, a novel framework leveraging few-shot learning large language models (LLMs) to automate the extraction of SDoH from unstructured text, aiming to improve both efficie…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.