arXiv 2408.118542024-09-19cs.CLcs.AIcs.LG

当原始数据占优：大语言模型嵌入在医学机器学习应用的数值数据表示中是否有效？

When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications?

University of Colorado（科罗拉多大学）；University of Wisconsin Madison（威斯康星大学麦迪逊分校）；Mass General Brigham, Harvard Medical School（哈佛医学院麻省总医院）；Boston Children Hospital, Harvard Medical School（哈佛医学院波士顿儿童医院）；Loyola University Chicago（芝加哥洛约拉大学）；Dana-Farber Cancer Institute（达纳-法伯癌症研究所）

Yanjun Gao, Skatje Myers, Shan Chen, Dmitriy Dligach, Timothy A Miller, Danielle Bitterman, Matthew Churpek, Majid Afshar

备注：: Accepted to Findings of EMNLP 2024

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究评估大语言模型嵌入在医学机器学习中表示数值数据的有效性，发现原始数据特征仍占优，但零样本嵌入表现有竞争力，为未来研究提供方向。

摘要：

大语言模型（LLMs）的引入推动了数据表示和分析的进步，在医学问答方面带来了显著进展。尽管有这些进步，将表格数据，尤其是临床环境中至关重要的数值数据，整合到LLM范式中尚未得到深入探索。在本研究中，我们利用电子健康记录（EHR）数据，检验了LLM最后隐藏状态的向量表示在医学诊断和预后中的有效性。我们将这些嵌入与原始数值EHR数据作为特征输入到擅长表格数据学习的传统机器学习（ML）算法（如极限梯度提升）时的性能进行比较。我们专注于指令微调的LLM在零样本设置下表示异常生理数据，并评估其作为特征提取器以增强ML分类器预测诊断、住院时间和死亡率的能力。此外，我们考察了提示工程技术对零样本和少样本LLM嵌入的影响，以全面衡量其影响。尽管研究结果表明原始数据特征在医学ML任务中仍然占优，但零样本LLM嵌入表现出有竞争力的结果，为医学应用的未来研究指明了一条有前景的途径。

英文摘要：

The introduction of Large Language Models (LLMs) has advanced data representation and analysis, bringing significant progress in their use for medical questions and answering. Despite these advancements, integrating tabular data, especially numerical data pivotal in clinical contexts, into LLM paradigms has not been thoroughly explored. In this study, we examine the effectiveness of vector representations from last hidden states of LLMs for medical diagnostics and prognostics using electronic health record (EHR) data. We compare the performance of these embeddings with that of raw numerical EHR data when used as feature inputs to traditional machine learning (ML) algorithms that excel at tabular data learning, such as eXtreme Gradient Boosting. We focus on instruction-tuned LLMs in a zero-shot setting to represent abnormal physiological data and evaluating their utilities as feature extractors to enhance ML classifiers for predicting diagnoses, length of stay, and mortality. Furthermore, we examine prompt engineering techniques on zero-shot and few-shot LLM embeddings to measure their impact comprehensively. Although findings suggest the raw data features still prevails in medical ML tasks, zero-shot LLM embeddings demonstrate competitive results, suggesting a promising avenue for future research in medical applications.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。