Summary of Leveraging Open-source Large Language Models For Encoding Social Determinants Of Health Using An Intelligent Router, by Akul Goel et al.
Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router
by Akul Goel, Surya Narayanan Hari, Belinda Waltman, Matt Thomson
First submitted to arxiv on: 30 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 The paper presents an intelligent routing system for Social Determinants of Health (SDOH) coding using open-source large language models (LLMs). The authors highlight the challenge of choosing the best model from thousands available, especially considering clinical notes contain trusted health information. They propose a language model router that directs medical record data to optimal LLMs for specific SDOH codes, achieving state-of-the-art performance of 97.4% accuracy across 5 codes, including homelessness and food insecurity. The system is validated using synthetic data generation and validation paradigm, increasing the scale of training data without requiring privacy-protected medical records. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper finds a way to use computers to help doctors code important health information correctly. Doctors often have trouble finding the right words to describe things like whether someone has a place to live or access to food. The authors want to make it easier by using special computer models that can help with this task. They create a system that picks the best model for each specific job and get really good results, almost as good as expensive commercial systems. |
Keywords
» Artificial intelligence » Language model » Synthetic data
