深度电子病历分析研究综述

An Overview of Research on Deep Electronic Health Record Analysis

伴随医院信息化建设,大量的电子病历数据得以保存,但如何分析和利用这些数据成为医疗健康领域一个重要的研究课题。深度电子病历分析以深度学习技术为基础,通过特征自学习,避免了在数据预处理和特征工程上耗费大量时间,而且还能有效捕获数据间的未知关系,提高算法性能。本文首先概述了5类常用的深度学习模型及其变体,其次详细分析了这5类模型在电子病历分析上的应用情况,最后从数据异质性、公开数据集和模型可解释性三个方面对这一领域当前的机遇和挑战做了总结。

With the development of hospital informatization, the vast amounts of raw electronic health records have been saved. Buthow to analyze and utilize these data becomes an important research topic in the field of healthcare. Based on deep learning tech-nologies, deep electronic health record analysis models not only can learn features directly from the data itself, avoiding the cost oftime on data preprocessing and feature engineering, but also can gain high performance by effectively capturing latent relationshipsbetween data. In this paper, five commonly used deep learning models and their variants are firstly discussed, and then analyzessome electronic health record analysis applications in detail. Finally, we summarize the current opportunities and challenges fromthree aspects: data heterogeneity, public datasets and model interpretability.