Suppr超能文献

哈佛-埃默里心电图数据库。

The Harvard-Emory ECG Database.

作者信息

Koscova Zuzana, Li Qiao, Robichaux Chad, Junior Valdery Moura, Ghanta Manohar, Gupta Aditya, Rosand Jonathan, Aguirre Aaron, Hong Shenda, Albert David E, Xue Joel, Parekh Aarya, Sameni Reza, Reyna Matthew A, Westover M Brandon, Cliford Gari D

机构信息

Department of Biomedical Informatics, School of Medicine, Emory University, Atlanta, 30322, US.

Department of Neurology, Massachusetts General Hospital, Boston, 02114, US.

出版信息

medRxiv. 2025 May 9:2024.09.27.24314503. doi: 10.1101/2024.09.27.24314503.

Abstract

The Harvard-Emory ECG Database (HEEDB) is a large collection of 12-lead electrocardiogram (ECG) recordings, developed through a collaboration between Harvard University and Emory University. The database consists of 10,608,417 unique ECG recordings from 1,818,247 patients from Massachusetts General Hospital (MGH) and 1,452,964 recordings from 552,481 patients from Emory University Hospital (EUH) collected in clinical settings as part of routine patient care since the early 1990s. Continuously updated with new data, the recordings consist of 10-second, 12-lead ECGs sampled at 250 and 500 Hz, and stored in WFDB format. Future updates will include demographic information such as age, sex, race, and ethnicity. Additionally, 12SL annotations-encompassing ECG diagnoses, morphology, and rhythms-are available for 10,471,531 recordings from MGH and 1,268,277 recordings from EUH. Shortly, ICD-9/10 codes, CPT codes, and medication history will also be made publicly available.

摘要

哈佛-埃默里心电图数据库(HEEDB)是一个大型的12导联心电图记录集,由哈佛大学和埃默里大学合作开发。该数据库包含来自麻省总医院(MGH)1,818,247名患者的10,608,417份独特心电图记录,以及自20世纪90年代初以来在临床环境中作为常规患者护理一部分收集的来自埃默里大学医院(EUH)552,481名患者的1,452,964份记录。随着新数据的不断更新,这些记录包括以250和500赫兹采样的10秒12导联心电图,并以WFDB格式存储。未来的更新将包括年龄、性别、种族和民族等人口统计信息。此外,MGH的10,471,531份记录和EUH的1,268,277份记录提供了包含心电图诊断、形态和节律的12SL注释。不久之后,ICD-9/10代码、CPT代码和用药史也将公开提供。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/df87/12083575/053eb45bc0fb/nihpp-2024.09.27.24314503v2-f0001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验