Key result
The modified ECG de-noising technique using wavelet decomposition and threshold method achieved nearly 100% accuracy for QRS complex and QT intervals, though accuracy degraded at lower signal-to-noise ratios.
Why the study?
Distant and continuous health monitoring for heart diseases is sensitive to noise due to lack of expert intervention, creating a need for noise-free ECG data to properly treat patients.
A modified ECG de-noising technique using wavelet decomposition effectively restores QRS and QT intervals from noisy signals, though PR and ST interval restoration remains challenging at low signal-to-noise ratios.
Wavelet de-noising may aid QRS/QT detection in noisy ECGs but requires caution for PR/ST intervals; leaves open clinical validation at varying SNR.
According to recent survey due to drastically changing weather and unhealthy lifestyle, irrespective of age people are suffer from different health issues, among them heart related diseases are very common. So to prevent some emergency health hazards due to such kind of diseases distant and continuous health monitoring is very useful, but due to lack of expert intervention both processes are very sensitive to noise. So our aim is to get a noise free medical data through above said processes to treat a patient properly. In this work experimental signal data is chosen from a 12 lead noisy ECG database which is formed using a MATLAB coded program by taking noisy and clear data from MIT-BIH noise stress test database and CSE clear ECG database respectively. Generated noisy ECG signals are decomposed using wavelet decomposition. Distorted coefficients generated during the process are recovered using threshold technique and the de-noised signal is achieved using changed coefficients. After de-noising process amplitude and duration of different segments and intervals of de-noised ECG signals for several SNR values and also for clear ECG signals are obtained by running an ECG feature extraction program developed in MATLAB. Compare both parameters to study the performance of the whole de-noising procedure, Again sensitivity, predictivity and detection accuracy are checked for each de-noised data for different SNR values and represent them graphically to detect the accuracy of the process.
No takes yet. Share an insight, caveat, or question.
Sarkar et al. (2023) studied ECG signal noise (n=125). Modified ECG de-noising technique using wavelet decomposition and threshold method vs. Noisy ECG signals was evaluated on ECG parameter detection accuracy (QRS, QT, PR, ST). The modified ECG de-noising technique using wavelet decomposition and threshold method achieved nearly 100% accuracy for QRS complex and QT intervals, though accuracy degraded at lower signal-to-noise ratios.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: