LU electrocardiography database: a new open-access validation tool for delineation algorithms

We report a new Lobachevsky University database (LUDB) of ECG signals that contains 200 samples of 10-second 12-lead electrocardiograms (ECG) from different subjects. The boundaries of the ECG signal complexes are manually annotated by cardiologists for all samples and independently for each lead. The database is representative of a variety of signal morphologies. In addition, all records have an attributed diagnosis. These features make LUDB a promising tool for validating ECG delineation algorithms across a broad range of ECG signal shapes and patient diagnoses. A case study for the recently proposed wavelet-based algorithm is presented.