Prediction of Paroxysmal Atrial Fibrillation From Complexity Analysis of the Sinus Rhythm ECG: A Retrospective Case/Control Pilot Study

Abstract

Paroxysmal atrial fibrillation (PAF) is the most common cardiac arrhythmia, conveying a stroke risk comparable to persistent AF. It poses a significant diagnostic challenge given its intermittency and potential brevity, and absence of symptoms in most patients. This pilot study introduces a novel biomarker for early PAF detection, based upon analysis of sinus rhythm ECG waveform complexity. Sinus rhythm ECG recordings were made from 52 patients with (n = 28) or without (n = 24) a subsequent diagnosis of PAF. Subjects used a handheld ECG monitor to record 28-second periods, twice-daily for at least 3 weeks. Two independent ECG complexity indices were calculated using a Lempel-Ziv algorithm: R-wave interval variability (beat detection, BD) and complexity of the entire ECG waveform (threshold crossing, TC). TC, but not BD, complexity scores were significantly greater in PAF patients, but TC complexity alone did not identify satisfactorily individual PAF cases. However, a composite complexity score (h-score) based on within-patient BD and TC variability scores was devised. The h-score allowed correct identification of PAF patients with 85% sensitivity and 83% specificity. This powerful but simple approach to identify PAF sufferers from analysis of brief periods of sinus-rhythm ECGs using hand-held monitors should enable easy and low-cost screening for PAF with the potential to reduce stroke occurrence.

Detecting paroxysmal atrial fibrillation from normal sinus rhythm in equine athletes using Symmetric Projection Attractor Reconstruction and machine learning

“…Notably, Attia and colleagues 40 obtained more than 180,000 adult ECG recordings and achieved an accuracy of 79.4% (ROC AUC of 0.87) for a single 10-second, 12-lead recording extracted up to 31 days before a recorded AF (or atrial flutter) ECG, which rose to 83.3% when all available sinus rhythm recordings from the 31 days were used. Alexeenko and colleagues 41 extended the complexity analysis from equine ECGs 19 to a pilot study using repeated 28-second single-lead sinus rhythm ECG from 52 older adult subjects, and discriminated PAF patients with a ROC AUC of 0.92, indicating the earlier methodology applied to equine ECG (ROC AUC of 0.95) was appropriate for the analysis of human ECG data. We recommend that a similar study be undertaken to extend the detection of PAF using the SPAR method to larger volumes of human data.…”

“…While our study focused on retrospective equine data, there has been a recent surge of interest in both the retrospective detection and prospective prediction of PAF in human sinus rhythm ECGs, driven by clinical need, and supported by larger labelled datasets, advances in machine learning techniques and more powerful hardware.Notably, Attia et al40 obtained over 180,000 adult ECG recordings, and achieved an accuracy of 79.4% (ROC AUC of 0.87) for a single 10-second, 12-lead recording extracted up to 31 days before a recorded atrial fibrillation (or atrial flutter) ECG, which rose to 83.3% when all available sinus rhythm recordings from the 31 days were used. Alexeenko et al41 extended the complexity analysis from equine…”

A synopsis of wearable commercially available biometric‐monitoring devices and their potential applications during gallop racing

“…The ECG is not typically an element of routine veterinary checks unless an arrhythmia warrants further investigation (Reef, 1985; Reef et al, 2014). Moreover, AF, for instance, can be complex to predict using an ECG due to the intermittency and often brevity of the disorder (Alexeenko et al, 2021). Obtaining a good quality ECG trace is highly dependent on electrode position, skin contact and calls for a trained practitioner's interpretation of the signal (Frippiat et al, 2021; Keen & O'Connor, 2021).…”

Study of P wave dispersion in patients with paroxysmal atrial fibrillation and its role in prediction of atrial fibrillation recurrence

“…The prevalence of PAF may be underestimated, as many episodes (including some lasting more than 48 h) are asymptomatic. Also, the duration of recurrent AF episodes varies over time in each individual, and progression to persistent or permanent AF is common [ 1 ].…”