Key result
Novel multi-lead ECG algorithm achieves >97% sensitivity for wave delineation, outperforming single-lead tools.
Why the study?
Existing publicly available ECG databases have limitations that LUDB aims to overcome by providing superior validation data for ECG delineation algorithms.
Population
200 recordings of 10-second 12-lead ECGs from different subjects
Comparison
LUDB versus existing publicly available ECG databases
Design
Open-access validation tool with expert manual annotations
Authors
Loading...
Supports ECG algorithm validation with new annotated data; leaves open clinical adoption pending prospective testing.
LUDB provides a high-quality, manually annotated open-access database of 12-lead ECGs to facilitate the development and validation of novel ECG analysis algorithms.
Kalyakulina et al. (2020) studied Cardiovascular diseases and healthy participants (n=200). Wavelet-based multi-lead ECG delineation algorithm vs. ecg-kit tool (single-lead delineator) was evaluated on Sensitivity and Positive Predictive Value for P, QRS, and T wave delineation. A novel wavelet-based multi-lead ECG delineation algorithm validated on the new 200-record LUDB database achieved >97% sensitivity for P, QRS, and T waves, outperforming a standard single-lead tool.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: