QRS detection in single-lead, telehealth electrocardiogram signals: Benchmarking open-source algorithms

Background and objectives: A key step in electrocardiogram (ECG) analysis is the detection of QRS complexes, particularly for arrhythmia detection. Telehealth ECGs present a new challenge for automated analysis as they are noisier than traditional clinical ECGs. The aim of this study was to identify the best-performing open-source QRS detector for use with telehealth ECGs. Methods: The performance of 18 open-source QRS detectors was assessed on six datasets. These included four datasets of ECGs collected under supervision, and two datasets of telehealth ECGs collected without clinical supervision. The telehealth ECGs, consisting of single-lead ECGs recorded between the hands, included a novel dataset of 479 ECGs collected in the SAFER study of screening for atrial fibrillation (AF). Performance was assessed against manual annotations. Results: A total of 12 QRS detectors performed well on ECGs collected under clinical supervision (F1 score ≥0.96). However, fewer performed well on telehealth ECGs: five performed well on the TELE ECG Database; six performed well on high-quality SAFER data; and performance was poorer on low-quality SAFER data (three QRS detectors achieved F1 of 0.78-0.84). The presence of AF had little impact on performance. Conclusions: The Neurokit and University of New South Wales QRS detectors performed best in this study. These performed sufficiently well on high-quality telehealth ECGs, but not on low-quality ECGs. This demonstrates the need to handle low-quality ECGs appropriately to ensure only ECGs which can be accurately analysed are used for clinical decision making. Author summary: The electrocardiogram (ECG) is a vital tool for assessing heart health. Traditionally, ECGs are recorded in clinical settings, but with advances in technology, mobile devices and smartwatches can now be used to record ECGs in daily life. However, ECG recordings from these devices often contain more noise, posing challenges for accurate analysis. In this study, we evaluated 18 different algorithms for detecting heartbeats in ECGs. Our aim was to identify the best-performing algorithm for use with ECGs recorded using mobile devices. We tested each algorithm on 995 ECG recordings and compared their performance against manually-annotated heartbeats. From our analysis, we identified the two best-performing algorithms. These algorithms performed well when analysing high-quality ECGs obtained under clinical supervision and from mobile devices. However, their performance degraded significantly when analysing noisy ECGs from mobile devices. These findings highlight the importance of selecting robust algorithms for ECG analysis, particularly for data collected outside clinical environments. Furthermore, the study demonstrates the need to ensure that only ECGs which can be accurately analysed are used for clinical decision making.