Key result
An algorithm using slope thresholding and relative magnitude comparison achieved a high detection sensitivity of 99.8% for characteristic points on 12-lead ECG data from the PTB database.
The proposed algorithm demonstrates high sensitivity (99.8%) for automatic detection of ECG characteristic features, potentially improving automated ECG analysis.
The paper proposes a simple and efficient algorithm for automatic detection of the characteristic points (Q, R, S, T, P peaks and onset and offset points) from a single lead digital ECG data. The squared double difference signal of the ECG data is used to localize the QRS regions and the significant peak in the QRS regions are detected by relative magnitude comparison and peak intervals are processed according to some criteria to ensure accuracy of detection. Next the other peaks in the QRS region are detected with respect to the significant peak to make the algorithm adaptive to different QRS morphologies. The T wave features are then detected by magnitude and slope threshold based search on selected windows. The performance of the algorithm is tested on 12-lead ECG data from the PTB diagnostic ECG database, and a high detection sensitivity of 99.8% is detected.
No takes yet. Share an insight, caveat, or question.
Sadhukhan et al. (2012) studied ECG analysis. Algorithm using slope thresholding and relative magnitude comparison was evaluated on Detection sensitivity of ECG characteristic points. An algorithm using slope thresholding and relative magnitude comparison achieved a high detection sensitivity of 99.8% for characteristic points on 12-lead ECG data from the PTB database.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: