This paper proposes a beat detection algorithm specially tailored to be used with 12 channel ECG records. The algorithm first obtains beat positions on each channel, and then combines this information to get an improved estimate. The detection process involves two stages: 1) single-channel detection: implemented by improving one of the most popular methods (Pan-Tompkins) developed to detect beat positions; and 2) multichannel detection: an algorithm that combines the information of the beat positions obtained in each of the 12 channels. In this way, our results clearly improve those obtained with the single-channel detection method, discarding detection errors, false positives, and duplicated beats. Besides, our single-channel method significantly reduces the temporal error when estimating the positions of QRS complexes. In the multichannel detection, the assessment of our algorithm against one-channel based approaches shows a significant improvement in detection outcome (Se = 99.86%, P+ = 99.98%, RMS RR Interval Error = 25.98 ms, F-Score = 0.9992), making it a good starting point for automatic diagnosis of heart conditions.

No abstract

No abstract

This paper proposes a computerized heartbeat detection method in single-channel electrocardiograms (ECGs). First, the well-known Pan-Tompkins technique was implemented, and next, a channel-dependent version was developed, by adjusting threshold values and reducing false QRS detections. The algorithms were tested with the MIT-BIH Arrhythmia Database (original algorithm), and with the St. Petersburg Database (modified version). When validating the performances of the original Pan-Tompkins algorithm, we have achieved a sensitivity of Se = 99.81, at a positive predictivity (P + ) = 99.85%. The F-Score was 0.9587, and the RMS RR Interval Error (RMSRRIE) resulted to be 4,480.46 ms. When analysing the performance of the modified algorithm, results provided an average value of Se = 99.92%, P + = 99.98%, FScore = 0.9718, and a mean value of 111.05 ms. for the RMSRRIE. In conclusion, the improved PanTompkins algorithm provides higher values for sensitivity and positive predictivity, increased F-Score, and it significantly reduces the temporal error when estimating the positions of QRS complexes. Thus, it could be used as a starting point to detect heartbeat positions in more sophisticated computerized detection systems.

No abstract