Summary of When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation For Medical Machine Learning Applications?, by Yanjun Gao et al.
When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications?
by Yanjun Gao, Skatje Myers, Shan Chen, Dmitriy Dligach, Timothy A Miller, Danielle Bitterman, Matthew Churpek, Majid Afshar
First submitted to arxiv on: 15 Aug 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 explores the potential of Large Language Models (LLMs) in medical diagnostics and prognostics using electronic health record (EHR) data. It compares the performance of vector representations from last hidden states of LLMs with raw numerical EHR data as feature inputs to traditional machine learning algorithms, such as eXtreme Gradient Boosting. The study focuses on instruction-tuned LLMs in a zero-shot setting to represent abnormal physiological data and evaluates their utilities as feature extractors to enhance ML classifiers for predicting diagnoses, length of stay, and mortality. Additionally, it examines prompt engineering techniques on zero-shot and few-shot LLM embeddings to measure their impact comprehensively. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how Large Language Models (LLMs) can help with medical questions and answers using health records. It compares the LLMs’ ability to understand data with traditional ways of analyzing numbers from these records. The paper also talks about how well these models do when they’re not trained on specific data, but instead use general knowledge to make predictions. Overall, this research shows that LLMs have potential in medical applications, especially when combined with other machine learning techniques. |
Keywords
» Artificial intelligence » Extreme gradient boosting » Few shot » Machine learning » Prompt » Zero shot
