Detection of electrocardiogram QRS complex based on modified adaptive threshold

Abstract

<p>It is essential for medical diagnoses to analyze Electrocardiogram (ECG signal). The core of this analysis is to detect the QRS complex. A modified approach is suggested in this work for QRS detection of ECG signals using existing database of arrhythmias. The proposed approach starts with the same steps of previous approaches by filtering the ECG. The filtered signal is then fed to a differentiator to enhance the signal. The modified adaptive threshold method which is suggested in this work, is used to detect QRS complex. This method uses a new approach for adapting threshold level, which is based on statistical analysis of the signal. Forty-eight records from an existing arrhythmia database have been tested using the modified method. The result of the proposed method shows the high performance metrics with sensitivity of 99.62% and a positive predictivity of 99.88% for QRS complex detection.</p>

A New and Lightweight R-Peak Detector Using the TEDA Evolving Algorithm

“…The work presented in [35] proposes an advanced approach for detecting the QRS complex in ECG signals. The method begins with preprocessing the ECG signal, including band-pass filtering to remove noise, differentiation to highlight rapid changes indicative of the QRS complex, and application of the Hilbert transform to form the signal envelope.…”

Heartbeat detector from ECG and PPG signals based on wavelet transform and upper envelopes

“…These heartbeat improvements can be accomplished by applying two different procedures that we named as type-A or type-B processes. The type-A processes consist of a signal rectification (the absolute value or the square of the data) followed by a sliding window integrator [ 17 , 18 , 20 , 24 , 26 , 32 , 36 – 38 ], and sometimes the Shanon energy is set in an intermediate stage [ 18 , 24 , 26 , 31 , 38 ], where QRS is accented with respect to the remaining signal elements by concentrating the energy around them, which is calculated as , where d [ n ] is the first derivative of the rescaled data between [0, 1]. As a result of the type-A process, the heartbeat appears as a kind of concave bell with a width approximately equal to the QRS-complex.…”

“…The type-B processes are adaptive multiresolution techniques that decompose a signal into a set of signals with different frequency ranges associated with each one, so that temporal and frequency information is obtained simultaneously. Candidate selection is realized by choosing the levels to contain the frequency information associated with the QRS [ 20 , 27 , 39 – 41 ]. This way, type-A processes are simple and highly accurate, but sensitive to outliers, whereas type-B processes are more robust to outliers, but more complex.…”

“…This is typically accomplished by using fixed or adaptive thresholds. Hence, a heartbeat is associated with the time point at which these thresholds were exceeded [ 19 , 20 , 22 , 25 , 30 , 33 , 38 , 42 – 44 ]. The accuracy of these techniques in determining the temporal location of the heartbeats is between 96.69% and 99.99%.…”

“… [ 32 ] MBA; NSR WT; AT 99.99 B [ 18 ] MBA BPF; SE; Digital first-order differentiator; HT 99.85 [ 19 ] 12 database BPF; Smoothing; EV 99.92 [ 41 ] MBA Variable frequency complex decomposition method 99.89 [ 33 ] MBA; QT EMD 99.89 Integrated P-wave detection. [ 20 ] MBA BPF; HT; AT 99.50 [ 45 ] MBA; QT; CPSC20195 NN 99.96 [ 21 ] MBA BPF; Variance; AT 99.69 [ 22 ] MBA BPF; Exponencial Transform; AT 99.71 [ 34 ] QT; NST; INCART; CPSC2019 a WT; NN 97.48 ECG split into 10 s. [ 43 ] MBA …”