A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients

Abstract

This newly inaugurated research database for 12-lead electrocardiogram signals was created under the auspices of Chapman University and Shaoxing People’s Hospital (Shaoxing Hospital Zhejiang University School of Medicine) and aims to enable the scientific community in conducting new studies on arrhythmia and other cardiovascular conditions. Certain types of arrhythmias, such as atrial fibrillation, have a pronounced negative impact on public health, quality of life, and medical expenditures. As a non-invasive test, long term ECG monitoring is a major and vital diagnostic tool for detecting these conditions. This practice, however, generates large amounts of data, the analysis of which requires considerable time and effort by human experts. Advancement of modern machine learning and statistical tools can be trained on high quality, large data to achieve exceptional levels of automated diagnostic accuracy. Thus, we collected and disseminated this novel database that contains 12-lead ECGs of 10,646 patients with a 500 Hz sampling rate that features 11 common rhythms and 67 additional cardiovascular conditions, all labeled by professional experts. The dataset consists of 10-second, 12-dimension ECGs and labels for rhythms and other conditions for each subject. The dataset can be used to design, compare, and fine-tune new and classical statistical and machine learning techniques in studies focused on arrhythmia and other cardiovascular conditions.

Accurate deep neural network model to detect cardiac arrhythmia on more than 10,000 individual subject ECG records

“…In this work, we used a new large ECG database [78] collected by Chapman University and Shaoxing People's Hospital (Shaoxing Hospital Zhejiang University School of Medicine). The database includes a large number of individual subjects - more than 10,000 - with 12-lead ECG signals sampled at a higher than usual sampling rate of 500 Hz.…”

“…Therefore, the construction of new large public datasets plays a vital role for studies on arrhythmia. As described herein, we used one of the largest public ECG datasets to detect rhythm classes [78] . The database includes 12-lead ECG signals collected from more than 10,000 individual subjects.…”

Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL

“…IV: Sex prediction performance for models trained on all patients and evaluated on all/normal/abnormal subpopulations in terms of accuracy (acc) and area under the receiver operating curve (AUC). The notation follows the one introduced in Table I. all healthy non-healthy Method ACC AUC ACC AUC ACC AUC inception1d .834 (13) .916(09) .896 (16) .958 (10) .785 (18) .876 (16) xresnet1d101 .849 (12) .920(09) .900 (15) .960(09) .806 (18) .881 (16) resnet1d wang .840 (12) .909 (10) .892 (16) .955 (10) .797 (18) .869 (17) fcn wang .831 (13) .909 (10) .882 (17) .949 (11) .796 (18) .875(16) lstm .834 (13) .911 (10) .884 (16) .952 (10) .789 (19) .874(16) lstm bidir…”

“…In addition, many of the freely accessible databases contain only single lead recordings, which makes comprehensive diagnosis and clinical validation difficult. Large and comprehensive databases with 12-lead recordings, however, are rather an exception such as [17] focusing on arrhythmia, which is why the underlying data set is of great importance for the development of algorithmic solutions. Second, the existing datasets typically provide only the raw data, but there exist no clearly defined benchmarking tasks with corresponding evaluation procedures.…”

Detection of Atrial Fibrillation Using 1D Convolutional Neural Network

“…ECG is a medical signal which tests the abnormality of the heart by measuring its electrical activity. A beat of ECG signals can be observed by five characteristic waves-P, Q, R, S, and T-as shown in Figure 1 [6]. P wave stands for atrial depolarization; QRS complex corresponds to the depolarization of the right and left ventricles, and contraction of the ventricular muscles; T wave represents repolarization of the ventricles.…”