arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.04820cs.CL
收藏

基于EHR的计算表型分析的自然语言处理

Natural Language Processing for EHR-Based Computational Phenotyping

Harvard T.H. Chan School of Public Health(哈佛大学陈曾熙公共卫生学院)

Zexian Zeng, Yu Deng, Xiaoyu Li, Tristan Naumann, Yuan Luo

摘要:

本文综述了自然语言处理(NLP)应用于电子健康档案(EHR)的计算表型分析的最新进展。基于NLP的计算表型分析具有许多应用,包括诊断分类、新表型发现、临床试验筛选、药物基因组学、药物相互作用(DDI)和药物不良事件(ADE)检测,以及全基因组和全表型关联研究。在计算表型的算法开发和资源建设方面取得了重大进展。在被调查的方法中,设计良好的关键字搜索和基于规则的系统往往取得良好的性能。然而,关键字和规则列表的构建需要大量的手动工作,这是难以扩展的。受监督的机器学习模型受到青睐,因为它们能够从数据中获取分类模式和结构。最近,深度学习和无监督学习受到越来越多的关注,前者因其性能而受到青睐,后者因其发现新表型的能力而受到青睐。集成异构数据源变得越来越重要,并且在提高模型性能方面显示出了希望。通常,更好的性能是通过结合多种形式的信息来实现的。尽管取得了这些进展,但基于NLP的计算表型分析仍然面临挑战和机遇,包括更好的模型可解释性和可推广性,以及临床叙述中特征关系的适当表征

英文摘要:

This article reviews recent advances in applying natural language processing (NLP) to Electronic Health Records (EHRs) for computational phenotyping. NLP-based computational phenotyping has numerous applications including diagnosis categorization, novel phenotype discovery, clinical trial screening, pharmacogenomics, drug-drug interaction (DDI) and adverse drug event (ADE) detection, as well as genome-wide and phenome-wide association studies. Significant progress has been made in algorithm development and resource construction for computational phenotyping. Among the surveyed methods, well-designed keyword search and rule-based systems often achieve good performance. However, the construction of keyword and rule lists requires significant manual effort, which is difficult to scale. Supervised machine learning models have been favored because they are capable of acquiring both classification patterns and structures from data. Recently, deep learning and unsupervised learning have received growing attention, with the former favored for its performance and the latter for its ability to find novel phenotypes. Integrating heterogeneous data sources have become increasingly important and have shown promise in improving model performance. Often better performance is achieved by combining multiple modalities of information. Despite these many advances, challenges and opportunities remain for NLP-based computational phenotyping, including better model interpretability and generalizability, and proper characterization of feature relations in clinical narratives

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。

↑