Key result
A deep learning model evaluated sinus rhythm echocardiograms and predicted the presence of concurrent paroxysmal atrial fibrillation with an AUC of 0.71, outperforming clinical risk factors and left atrial size.
Why the study?
Atrial fibrillation is often missed by intermittent screening, and TTEs may provide complementary structural information to identify occult AF during sinus rhythm.
Does a deep learning model evaluating echocardiogram videos improve the prediction of concurrent paroxysmal atrial fibrillation in patients in sinus rhythm compared to clinical variables and left atrial size?
Observational (n=111,319)
No
Does a deep learning model evaluating echocardiogram videos improve the prediction of concurrent paroxysmal atrial fibrillation in patients in sinus rhythm compared to clinical variables and left atrial size?
Effect estimate: AUC 0.71 (95% CI 0.69-0.73)
Absolute Event Rate: 0.71% vs 0.67%
A deep learning model applied to routine echocardiogram videos can identify patients with occult paroxysmal atrial fibrillation better than clinical risk scores or left atrial size alone.
May aid detection of occult paroxysmal AF on routine echoes; hypothesis-generating and requires prospective validation.
Background Atrial fibrillation (AF) can often be missed by intermittent screening given its frequently paroxysmal and asymptomatic presentation. Deep learning algorithms have been developed to identify patients with paroxysmal AF from electrocardiograms (ECGs) in sinus rhythm. Transthoracic echocardiograms (TTEs) may provide additional structural information complementary to ECGs that could also be used to help identify occult AF. Objective We sought to determine whether deep learning evaluation of echocardiograms of patients in sinus rhythm could identify occult AF. Methods We identified patients who had TTEs performed between 2004 and 2021. We created a two-stage model that (1) distinguished which TTEs were in sinus rhythm and which were in AF and then (2) predicted which of the TTEs in sinus rhythm were in patients with paroxysmal AF. Models were trained from video-based convolutional neural networks using TTE parasternal long axis (PLAX) videos. The AF prediction performance was compared to prediction using clinical variables, CHADSVASc score, and left atrial (LA) size. Results Our model trained on 111,319 TTE videos distinguished TTEs in AF from those in sinus rhythm with high accuracy (AUC 0.96, 0.95-0.96). A total of 72,181 TTE videos were in sinus rhythm. When tested on a held-out sample, the model predicted the occurrence of concurrent AF with an AUC of 0.71 (0.69-0.73). Using the max F1 threshold, the PPV was 0.20 and the NPV was 0.95. The model performed better than predicting concurrent AF using clinical risk factors (AUC 0.67, 0.65-0.69), LA area (AUC 0.63, 0.62-0.64), and CHADSVASc (AUC 0.61, 0.60-0.62). Conclusion A deep learning model distinguished AF from sinus rhythm TTEs with high accuracy and predicted the presence of AF within 90 days of sinus rhythm TTEs moderately well, better than clinical variables or LA size alone. TTEs may help inform automated opportunistic AF screening efforts.
No takes yet. Share an insight, caveat, or question.
Stein et al. (2023) conducted an observational in Occult Atrial Fibrillation (n=111,319). Deep learning evaluation of echocardiogram videos vs. Clinical variables, CHADSVASc score, and left atrial size was evaluated on Prediction of concurrent paroxysmal atrial fibrillation from sinus rhythm echocardiograms (AUC 0.71, 95% CI 0.69-0.73). A deep learning model evaluated sinus rhythm echocardiograms and predicted the presence of concurrent paroxysmal atrial fibrillation with an AUC of 0.71, outperforming clinical risk factors and left atrial size.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: