Summary of Sdoh-gpt: Using Large Language Models to Extract Social Determinants Of Health (sdoh), by Bernardo Consoli et al.
SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH)
by Bernardo Consoli, Xizhi Wu, Song Wang, Xinyu Zhao, Yanshan Wang, Justin Rousseau, Tom Hartvigsen, Li Shen, Huanmei Wu, Yifan Peng, Qi Long, Tianlong Chen, Ying Ding
First submitted to arxiv on: 24 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces SDoH-GPT, a novel method for extracting social determinants of health (SDoH) from unstructured medical notes. The approach leverages contrastive examples and concise instructions, eliminating the need for extensive medical annotations or human intervention. SDoH-GPT achieves significant reductions in time and cost, outperforming traditional methods with superior consistency. The combination of SDoH-GPT and XGBoost ensures high accuracy and computational efficiency, maintaining AUROC scores above 0.90. Testing across three datasets confirms the method’s robustness and accuracy. This study demonstrates the potential of Large Language Models (LLMs) to revolutionize medical note classification. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to look at medical notes to find important information about people’s health. The old way was time-consuming and expensive, but this new method uses computer programs to do it quickly and cheaply. It works by giving the program examples of what to look for and then letting it figure out how to identify that information on its own. This method is really good at finding what we’re looking for and is much faster and cheaper than the old way. |
Keywords
» Artificial intelligence » Classification » Gpt » Xgboost
