Deep learning applied to ECGs could help identify patients at high risk of AF

Atrial fibrillation (AF) is recognized as an irregular and often very rapid heart rhythm, affecting one-quarter of patients older than 80 years. As per studies patients with AF are 5 times more likely to experience a stroke and have up to a 25% risk of dying within 30 days of stroke. Deep learning applied to electrocardiograms (ECGs) has been successfully used for early identification of several cardiovascular diseases.

A new study in JAMA Cardiology finds that deep learning applied to ECGs could help identify patients at high risk of AF who could be considered for intensive monitoring programs to help prevent adverse cardiac events. Many cases of AF go undetected, since at least one-third are asymptomatic deep learning in ECG might be new diagnostic technique.

Researchers conducted a prognostic study was performed on ECGs acquired from January 1, 1987, to December 31, 2022, at 6 US Veterans Affairs (VA) hospital networks and 1 large non-VA academic medical center. Participants included all outpatients with 12-lead ECGs in sinus rhythm. A convolutional neural network using 12-lead ECGs from 2 US VA hospital networks was trained to predict the presence of AF within 31 days of sinus rhythm ECGs. The model was tested on ECGs held out from training at the 2 VA networks as well as 4 additional VA networks and 1 large non-VA academic medical center.

The key findings of the study are

• A total of 907 858 ECGs from patients across 6 VA sites were included in the analysis. 6.4% were female, and 93.6% were male, with CHA2DS2-VASc (congestive heart failure, hypertension, age, diabetes mellitus, prior stroke or transient ischemic attack or thromboembolism, vascular disease, age, sex category) .

• A total of 0.2% were American Indian or Alaska Native, 2.7% were Asian, 10.7% were Black, 4.6% were Latinx, 0.7% were Native Hawaiian or Other Pacific Islander, 62.4% were White, 0.4% were of other race or ethnicity (which is not broken down into subcategories in the VA data set), and 18.4% were of unknown race or ethnicity.

• At the non-VA academic medical center (72 483 ECGs), 52.5% were female, with CHA2DS2-VASc score of 1.6 (1.4).

• A total of 0.1% were American Indian or Alaska Native, 7.9% were Asian, 9.4% were Black, 2.9% were Latinx, 0.03% were Native Hawaiian or Other Pacific Islander, 74.8% were White, 0.1% were of other race or ethnicity, and 4.7% were of unknown race or ethnicity.

• A deep learning model predicted the presence of AF within 31 days of a sinus rhythm ECG on held-out test ECGs at VA sites with an area under the receiver operating characteristic curve (AUROC) of 0.86 , accuracy of 0.78, and F1 score of 0.30.

• At the non-VA site, AUROC was 0.93; accuracy, 0.87; and F1 score, 0.46. The model was well calibrated, with a Brier score of 0.02 across all sites.

• Among individuals deemed high risk by deep learning, the number needed to screen to detect a positive case of AF was 2.47 individuals for a testing sensitivity of 25% and 11.48 for 75%.

Researchers concluded that “Deep learning of outpatient sinus rhythm ECGs predicted AF within 31 days in populations with diverse demographics and comorbidities. Similar models could be used in future AF screening efforts to reduce adverse complications associated with this disease.”

Reference: Yuan N, Duffy G, Dhruva SS, et al. Deep Learning of Electrocardiograms in Sinus Rhythm From US Veterans to Predict Atrial Fibrillation. JAMA Cardiol. Published online October 18, 2023. doi:10.1001/jamacardio.2023.3701