SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH)

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Consoli, Bernardo, Wu, Xizhi, Wang, Song, Zhao, Xinyu, Wang, Yanshan, Rousseau, Justin, Hartvigsen, Tom, Shen, Li, Wu, Huanmei, Peng, Yifan, Long, Qi, Chen, Tianlong, Ding, Ying
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866917731775807488
author	Consoli, Bernardo Wu, Xizhi Wang, Song Zhao, Xinyu Wang, Yanshan Rousseau, Justin Hartvigsen, Tom Shen, Li Wu, Huanmei Peng, Yifan Long, Qi Chen, Tianlong Ding, Ying
author_facet	Consoli, Bernardo Wu, Xizhi Wang, Song Zhao, Xinyu Wang, Yanshan Rousseau, Justin Hartvigsen, Tom Shen, Li Wu, Huanmei Peng, Yifan Long, Qi Chen, Tianlong Ding, Ying
contents	Extracting social determinants of health (SDoH) from unstructured medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. In this study we introduced SDoH-GPT, a simple and effective few-shot Large Language Model (LLM) method leveraging contrastive examples and concise instructions to extract SDoH without relying on extensive medical annotations or costly human intervention. It 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 SDoH-GPT and XGBoost leverages the strengths of both, ensuring high accuracy and computational efficiency while consistently maintaining 0.90+ AUROC scores. Testing across three distinct datasets has confirmed its robustness and accuracy. This study highlights the potential of leveraging LLMs to revolutionize medical note classification, demonstrating their capability to achieve highly accurate classifications with significantly reduced time and cost.
format	Preprint
id	arxiv_https___arxiv_org_abs_2407_17126
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH) Consoli, Bernardo Wu, Xizhi Wang, Song Zhao, Xinyu Wang, Yanshan Rousseau, Justin Hartvigsen, Tom Shen, Li Wu, Huanmei Peng, Yifan Long, Qi Chen, Tianlong Ding, Ying Computation and Language Artificial Intelligence Extracting social determinants of health (SDoH) from unstructured medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. In this study we introduced SDoH-GPT, a simple and effective few-shot Large Language Model (LLM) method leveraging contrastive examples and concise instructions to extract SDoH without relying on extensive medical annotations or costly human intervention. It 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 SDoH-GPT and XGBoost leverages the strengths of both, ensuring high accuracy and computational efficiency while consistently maintaining 0.90+ AUROC scores. Testing across three distinct datasets has confirmed its robustness and accuracy. This study highlights the potential of leveraging LLMs to revolutionize medical note classification, demonstrating their capability to achieve highly accurate classifications with significantly reduced time and cost.
title	SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH)
topic	Computation and Language Artificial Intelligence
url	https://arxiv.org/abs/2407.17126