Electrocardiogram sampling frequency for the optimal performance of complexity analysis and machine learning models: Discrimination between patients with and without paroxysmal atrial fi brillation using sinus rhythm electrocardiograms

BACKGROUND The current clinical practice to diagnose atrial fi brillation (AF) requires repeated episodic monitoring and signifi- cantly underperform in their ability to detect AF episodes. OBJECTIVE There is therefore potential for artificial intelligence- based methods to assist in the detection of AF. Better understanding of the optimal parameters for this detection can potentially improve the sensitivity for detecting AF. METHODS Ten-second, 12-lead electrocardiogram signals were analyzed using complexity algorithms combined with machine learning techniques to predict patients who had a previously detected AF episode but had since returned to normal sinus rhythm. An investigation was performed into the impact of the sampling frequency of the electrocardiogram signal on the accuracy of the machine learning models used.RESULTS Using a single complexity algorithm showed a peak accuracy of 0.69 when using signals sampled at 125 Hz. In particular, it was noted that improved accuracy occurred when using lead V6 compared with other available leads. CONCLUSION Based on these results, there is potential for 12-lead electrocardiogram signals to be recorded at 125 Hz as standard and used in conjunction with complexity analysis to aid in the detection of patients with AF.