AttributesDictionary.xlsx

The newly inaugurated research database for Electrocardiogram (ECG) signals, which was created under the auspices of Chapman University and Shaoxing People's Hospital (Shaoxing Hospital Zhejiang University School of Medicine), aims to conduct the study of cardiovascular biomedical signals via extensive computer simulations. Certain types of cardiovascular conditions, such as atrial fibrillation, have wide and severe impact on public health, quality of life, and medical expenditures. The non-invasive test, the long term ECG monitor is a major and vital diagnosis tool for detecting such conditions. However, such practice generates considerable amount of data, and presents itself as very challenging since analyzing by experts in the field can be dramatic consumption of time and cost. As such, obtaining the correct and most efficient diagnosis algorithm is of great important to public health. Thanks to the development of modern machine learning and statistical analysis, the more data with creditable labels are available, the better algorithm will be achieved. Thus, we propose this dataset contains 10,646 patients 12-lead ECGs with 500 Hz sampling rate and including 11 common rhythms and 67 conditions, which are labeled by professional experts. The dataset can be widely applied for artificial intelligence or machine learning algorithm research, arrhythmia and other cardiovascular conditions analysis, biomedical signal study, and cluster or classification statistical study.