arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.08290cs.LGcs.CL
收藏

重新发现CNN在基于文本的原始电子健康记录编码中的多功能性

Rediscovery of CNN's Versatility for Text-based Encoding of Raw Electronic Health Records

KAIST(韩国科学技术院);Google Cloud AI Research(谷歌云人工智能研究院)

Eunbyeol Cho, Min Jae Lee, Kyunghoon Hur, Jiyoun Kim, Jinsung Yoon, Edward Choi

AI总结:

本文重新评估了分层CNN在原始电子健康记录文本编码中的效能,证明其以更少参数和训练时间在重建、预测、生成等任务上超越现有模型,并利用EHR层次结构提升性能,提供构建编码器的实用指南。

摘要:

充分利用电子健康记录(EHR)中丰富的信息正迅速成为医学领域的一个重要课题。近期工作提出了一个有前景的框架,该框架将原始EHR数据中的全部特征嵌入,无论其形式和医学代码标准如何。然而,该框架仅专注于以最小预处理方式编码EHR,未能考虑如何在计算和内存使用方面学习高效的EHR表示。在本文中,我们寻找一种多功能的编码器,不仅将大数据缩减为可管理的大小,而且能很好地保留患者的核心信息以执行多样化的临床任务。我们发现,分层结构的卷积神经网络(CNN)在重建、预测和生成等多种任务上通常优于最先进的模型,即使参数更少、训练时间更短。此外,利用EHR数据固有的层次结构可以提升任何骨干模型和所执行临床任务的性能。通过大量实验,我们提供了具体证据,将我们的研究发现推广到实际应用中。我们基于探索多种设置时获得的研究发现,给出了构建编码器的明确指南。

英文摘要:

Making the most use of abundant information in electronic health records (EHR) is rapidly becoming an important topic in the medical domain. Recent work presented a promising framework that embeds entire features in raw EHR data regardless of its form and medical code standards. The framework, however, only focuses on encoding EHR with minimal preprocessing and fails to consider how to learn efficient EHR representation in terms of computation and memory usage. In this paper, we search for a versatile encoder not only reducing the large data into a manageable size but also well preserving the core information of patients to perform diverse clinical tasks. We found that hierarchically structured Convolutional Neural Network (CNN) often outperforms the state-of-the-art model on diverse tasks such as reconstruction, prediction, and generation, even with fewer parameters and less training time. Moreover, it turns out that making use of the inherent hierarchy of EHR data can boost the performance of any kind of backbone models and clinical tasks performed. Through extensive experiments, we present concrete evidence to generalize our research findings into real-world practice. We give a clear guideline on building the encoder based on the research findings captured while exploring numerous settings.

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。

↑