Impact of compressed sensing on clinically relevant metrics for ambulatory ECG monitoring

Abstract

Recent research has examined the combination of compressed sensing with over-complete dictionaries for the lossy compression of electrocardiogram (ECG) signals. The application of dictionary learning to automatically create the dictionary is described. A novel analysis of the reconstructed signals using a range of clinical metrics based around QRS feature extraction and heart rate variability is employed. Two methods for dictionary creation are proposed: patient specific and patient agnostic. A detailed comparison of each approach is described. Considering ambulatory ECG monitoring as an application, each methodology is analysed for a wide range of compression ratios.

A Comparative Analysis of Methods for Evaluation of ECG Signal Quality after Compression

“…Another method for quality assessment of ECG signal after compression based on the sensitivity (SE) and specificity (SP) of QRS detection [ 26 , 52 ] is introduced by ( 40 ) and ( 41 ). The authors use the equation for positive predictivity (+P) for calculation of specificity.…”

“…The QRS complexes were detected in the reconstructed signal and their positions were compared with annotations. A tolerance of 88 ms on both sides was considered [ 52 ]. In [ 25 ] the authors use SE and +P with correct equations.…”

“…The percentage similarity (PSim) [ 26 , 52 ] is a measure based on features derived from detected QRS complexes. Initially, the QRS complexes are detected, then the features ( p ) are calculated, mean normal-to-normal (NN), standard deviation of NN (SDNN), low-frequency/high-frequency (LF/HF) ratio using Lomb periodogram to compute the power spectral density for low frequencies (0.04-0.15Hz), and high frequencies (0.15-0.4Hz), and high-frequency (HF) power.…”

Compressed sensing ECG using restricted Boltzmann machines

“…A QRS detector different from that used in [20] is employed in this paper, which may have contributed to the difference in performance. In addition, the results in [20] were obtained with all the records from the MIT-BIH Arrhythmia Database, while our results correspond to the selected subset of ECG records. The work in [24] evaluates QRS detection on reconstructed signals after using compression methods.…”

The ECG Signal Compression Using an Efficient Algorithm Based on the DWT

“…The problem with this process is the possibility of losing some important features of the ECG signal. This loss could influence negatively the analysing of the heart condition [7][8][9].…”