A novel approach to phase space reconstruction of single lead ECG for QRS complex detection

•A novel approach to reconstructed phase space (RPS) of single lead ECG is proposed for QRS complex detection.•Traditional two-dimensional RPS (x(t), x(t + τ)) is improved as three-dimensional coordinate (x, y, t). The third parameter t is an indispensable time index to locate the position of QRS complex.•The algorithm was tested on three public benchmark databases, including the MIT-BIH Arrhythmia Database, the Long-term ST Database and the MIT-BIH Noise Stress Test Database.•The proposed algorithm achieved better performance on QRS complex detection when in comparison with the state-of-the-art methods.

Two-dimensional reconstructed phase space (RPS) of single lead Electrocardiogram (ECG) is usually implemented by plotting the ECG amplitude x(t + τ) versus x(t) into the two-dimensional coordinate system, where the value of time delay τ determined the morphology of the reconstructed trajectory. However, the value of τ is very difficult to select because different theories derived different τ. In this paper, a novel approach to phase space reconstruction of single lead ECG without using τ is proposed. The first two coordinates (x, y) from (x, y, t) were projected into the x-y coordinate system, where x is the amplitude of the ECG and y is the first order difference of x. Besides, time t is corresponding to the sampling time moment. As QRS complex is usually the most striking waveform that dominant with the highest amplitude or the highest slope, the largest semi-circle in the RPS is usually derived from QRS complex. The location of QRS complex in the original ECG is determined by the time coordinate t that corresponds to the largest semi-circle in the x-y coordinate system. The algorithm was developed at the MIT-BIH Arrhythmia Database (109494 beats within 24 h in total) and was tested on the Long-term ST Database (8897780 beats within 1991.8 h in total). The accuracy (ACC), the sensitivity (SEN) and the positive predictivity value (PPV) for the MIT-BIH Arrhythmia Database were 99.81%, 99.87% and 99.93%, respectively; while the corresponding values for the Long-term ST Database were 99.87%, 99.96% and 99.91%, respectively. Meanwhile, the consuming time was only 6.73 ms for processing 6 s' ECG data. Furthermore, the anti-noise ability of the proposed method was tested on the MIT-BIH Noise Stress Test Database (4265 beats in total at each noise level for one lead ECG). Both ACC and PPV were higher than 85% and the SEN was higher than 99% even when the signal-to-noise ratio (SNR) was as low as 0 dB. In conclusion, the proposed algorithm achieves better performance on QRS complex detection when in comparison with the state-of-the-art methods, and it is suited for the detection of QRS complex in the ECG associated with poor signal quality and severe arrhythmia.