Detecting Paroxysmal Atrial Fibrillation From an Electrocardiogram in Sinus Rhythm

Gruwez, Henri; Barthels, Monika; Haemers, Peter; Verbrugge, Frederik H.; Dhont, Sebastiaan; Meekers, Evelyne; Wouters, Femke; Nuyens, Dieter; Pison, Laurent; Vandervoort, Pieter; Pierlet, Noella

doi:10.1016/j.jacep.2023.04.008

Cited by 4 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The core concept of “AI-ECG on SR-ECG” arises from the question: “Who is at high risk for AF and should undergo long-term ECG monitoring?” The CNN models using SR-ECG, taking into account previous findings 8 – 10 , 13 and those from the present study, could identify individuals at high risk of AF. It is noteworthy that the best performance for such screening was achieved with the all-lead ECG, available only in the clinical setting.…”

Section: Discussionmentioning

confidence: 58%

“…Using AI-enabled ECG to predict AF using the 12-lead SR-ECG has already been reported by other study groups, 8 – 10 , 20 which found a high predictive ability for AF using the AUC: 0.90 in the study by Attia et al, 11 and 0.87 in the studies by Raghunath et al 9 and Gruwez et al 10 It is quite surprising that the SR-ECG can predict AF with such high predictive capability. In our previous study, in which we excluded patients with structural heart diseases, we obtained an AUC of 0.86, 13 and in the present study without any exclusion criteria, we obtained an AUC of 0.872.…”

Section: Discussionmentioning

confidence: 79%

“… 9 Additionally, Gruwez et al in Belgium reported on AI-enabled ECG analysis. 10 These studies have had a significant effect because of the high predictive ability, with an area under the curve (AUC) of approximately 0.9.…”

mentioning

confidence: 99%

“…We previously reported on a convolutional neural network (CNN) model for AF detection using SR-ECG, 13 which achieved comparable AUC values to previous studies. 8 – 10 In the present study, using the same dataset, we conducted an analysis to assess the lead-specific performance of the CNN model.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Lead-Specific Performance for Atrial Fibrillation Detection in Convolutional Neural Network Models Using Sinus Rhythm Electrocardiography

Suzuki,

Motogi,

Umemoto

et al. 2024

Circ Rep

View full text Add to dashboard Cite

Background: We developed a convolutional neural network (CNN) model to detect atrial fibrillation (AF) using the sinus rhythm ECG (SR-ECG). However, the diagnostic performance of the CNN model based on different ECG leads remains unclear. Methods and Results: In this retrospective analysis of a single-center, prospective cohort study, we identified 616 AF cases and 3,412 SR cases for the modeling dataset among new patients (n=19,170). The modeling dataset included SR-ECGs obtained within 31 days from AF-ECGs in AF cases and SR cases with follow-up ≥1,095 days. We evaluated the CNN model’s performance for AF detection using 8-lead (I, II, and V1–6), single-lead, and double-lead ECGs through 5-fold cross-validation. The CNN model achieved an area under the curve (AUC) of 0.872 (95% confidence interval (CI): 0.856–0.888) and an odds ratio of 15.24 (95% CI: 12.42–18.72) for AF detection using the eight-lead ECG. Among the single-lead and double-lead ECGs, the double-lead ECG using leads I and V1 yielded an AUC of 0.871 (95% CI: 0.856–0.886) with an odds ratio of 14.34 (95% CI: 11.64–17.67). Conclusions: We assessed the performance of a CNN model for detecting AF using eight-lead, single-lead, and double-lead SR-ECGs. The model’s performance with a double-lead (I, V1) ECG was comparable to that of the 8-lead ECG, suggesting its potential as an alternative for AF screening using SR-ECG.

show abstract

Section: Discussionmentioning

confidence: 58%

Section: Discussionmentioning

confidence: 79%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Lead-Specific Performance for Atrial Fibrillation Detection in Convolutional Neural Network Models Using Sinus Rhythm Electrocardiography

Suzuki,

Motogi,

Umemoto

et al. 2024

Circ Rep

View full text Add to dashboard Cite

show abstract

“…Studies identifying patients who will develop AF based on a sinus rhythm ECG can be divided into 2 categories, depending on the number of leads recorded and whether the ECG is of short or long duration. The converging results of studies using AI and based on a 10 second 12-lead ECG with a high signal sampling rate indicate that global prevention of AF can be envisaged using ML, even better than with clinical scores (Attia et al 2019, Khurshid et al 2022, Baek et al 2021, Gruwez et al 2023. As the prediction window extends over several weeks at least, this prevention would mainly consist in the application of hygienic-dietary measures such as weight loss, abstention from alcohol and possibly a preference for beta-blocker therapy for hypertensive patients.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based atrial fibrillation detection and onset prediction using QT-dynamicity

Grégoire,

Gilon,

Vaneberg

et al. 2024

Physiol. Meas.

View full text Add to dashboard Cite

ObjectiveThis study examines the value of ventricular repolarization using QT dynamicity for two different types of atrial fibrillation (AF) prediction. ApproachWe studied the importance of QT-dynamicity 1) in the detection and 2) the onset prediction (i.e. forecasting) of paroxysmal AF episodes using gradient-boosted decision trees (GBDT), an interpretable machine learning technique. We labeled 176 paroxysmal AF onsets from 88 patients in our unselected Holter recordings database containing paroxysmal AF episodes. Raw ECG signals were delineated using a wavelet-based signal processing technique. A total of 44 ECG features related to interval and wave durations and amplitude were selected. and the GBDT model was trained with a Bayesian hyperparameters selection for various windows. Main resultsThe mean age of the patients was 75.9±11.9 (range 50-99), the number of episodes per patient was 2.3±2.2 (range 1-11), and CHA2DS2-VASc score was 2.9±1.7 (range 1-9). For the detection of AF, we obtained an area under the receiver operating curve (AUROC) of 0.99 (CI 95% 0.98 - 0.99) using a 30s window. Features related to RR intervals were the most influential, followed by those on QT intervals. For the AF onset forecast, we obtained an AUROC of 0.739 (0.712-0.766) using a 120s window. R wave amplitude and QT dynamicity as assessed by Spearman’s correlation of the QT-RR slope were the best predictors. SignificanceThe QT dynamicity can be used to accurately predict the onset of AF episodes. Ventricular repolarization, as assessed by QT dynamicity, adds information that allows for better short time prediction of AF onset, compared to relying only on RR intervals and HRV. Communication between the ventricles and atria is mediated by the autonomic nervous system. The variations in intraventricular conduction and ventricular repolarization changes resulting from the influence of the ANS play a role in the initiation of AF.

show abstract

Artificial intelligence predicts undiagnosed atrial fibrillation in patients with embolic stroke of undetermined source using sinus rhythm electrocardiograms

Choi,

Kim,

Cho

et al. 2024

Heart Rhythm

View full text Add to dashboard Cite

Detecting Paroxysmal Atrial Fibrillation From an Electrocardiogram in Sinus Rhythm

Cited by 4 publications

References 44 publications

Lead-Specific Performance for Atrial Fibrillation Detection in Convolutional Neural Network Models Using Sinus Rhythm Electrocardiography

Lead-Specific Performance for Atrial Fibrillation Detection in Convolutional Neural Network Models Using Sinus Rhythm Electrocardiography

Machine learning-based atrial fibrillation detection and onset prediction using QT-dynamicity

Artificial intelligence predicts undiagnosed atrial fibrillation in patients with embolic stroke of undetermined source using sinus rhythm electrocardiograms

Contact Info

Product

Resources

About