SDoH-GPT: using large language models to extract social determinants of health
Journal of the American Medical Informatics Association · 01.01.2026 · 33 (1) · 67-78
DOI: 10.1093/jamia/ocaf094 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 10.06.2025. Verfasst von Bernardo Consoli und 13 weiteren Autor:innen. Beteiligte Einrichtung: School of Information, University of Texas at Austin, Austin, TX 78712, United States. Hauptthemen laut MEDLINE: Social Determinants of Health, Natural Language Processing, Electronic Health Records, Machine Learning. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, NLM NIH HHS, NIH.
Abstract (Originalsprache)
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 efficiency and generalizability. Materials and Methods SDoH-GPT is a framework including the few-shot learning LLM methods to extract the SDoH from medical notes and the XGBoost classifiers which continue to classify SDoH using the annotations generated by the few-shot learning LLM methods as training datasets. The unique combination of the few-shot learning LLM methods with XGBoost utilizes the strength of LLMs as great few shot learners and the efficiency of XGBoost when the training dataset is sufficient. Therefore, SDoH-GPT can extract SDoH without relying on extensive medical annotations or costly human intervention.
Results
Our approach achieved tenfold and twentyfold reductions in time and cost, respectively, and superior consistency with human annotators measured by Cohen's kappa of up to 0.92. The innovative combination of LLM and XGBoost can ensure high accuracy and computational efficiency while consistently maintaining 0.90+ AUROC scores.
Discussion
This study has verified SDoH-GPT on three datasets and highlights the potential of leveraging LLM and XGBoost to revolutionize medical note classification, demonstrating its capability to achieve highly accurate classifications with significantly reduced time and cost.
Conclusion
The key contribution of this study is the integration of LLM with XGBoost, which enables cost-effective and high quality annotations of SDoH. This research sets the stage for SDoH can be more accessible, scalable, and impactful in driving future healthcare solutions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information, University of Texas at Austin, Austin, TX 78712, United States.
- School of Technology, Pontifical Catholic University of Rio Grande do Sul, Porto Alegre 90619-900, Brazil.
- Department of Health Information Management, University of Pittsburgh, Pittsburgh, PA 15261, United States.
- Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States.
- Department of Neurology, University of Texas Southwestern Medical Center, Dallas, TX 75390, United States.
- School of Data Science, University of Virginia, Charlottesville, VA 22903, United States.
ORCID-Profile: Song Wang, Justin Rousseau, Li Shen, Yifan Peng, Qi Long
Förderung
- NIH HHS
- NLM NIH HHS
- NIH
Zitieren
APA
Consoli, B., Wang, H., Wu, X., Wang, S., Zhao, X., Wang, Y., Rousseau, J., Hartvigsen, T., Shen, L., Wu, H., Peng, Y., Long, Q., Chen, T., & Ding, Y. (2026). SDoH-GPT: using large language models to extract social determinants of health. Journal of the American Medical Informatics Association, 33(1), 67-78. https://doi.org/10.1093/jamia/ocaf094
Vancouver
Consoli B, Wang H, Wu X, Wang S, Zhao X, Wang Y, et al. SDoH-GPT: using large language models to extract social determinants of health. Journal of the American Medical Informatics Association. 2026;33(1):67-78. doi:10.1093/jamia/ocaf094
BibTeX
@article{Consoli2026,
author = {Consoli, Bernardo and Wang, Haoyang and Wu, Xizhi and Wang, Song and Zhao, Xinyu and Wang, Yanshan and Rousseau, Justin and Hartvigsen, Tom and Shen, Li and Wu, Huanmei and Peng, Yifan and Long, Qi and Chen, Tianlong and Ding, Ying},
title = {SDoH-GPT: using large language models to extract social determinants of health},
journal = {Journal of the American Medical Informatics Association},
year = {2026},
volume = {33},
number = {1},
pages = {67--78},
doi = {10.1093/jamia/ocaf094}
}
EUVIMED