AI predicts new-onset AFib using 12-lead ECGs

Researchers have developed an AI model that predicts new-onset atrial fibrillation (AFib) using 12-lead electrocardiogram (ECG) data, sharing their findings in Circulation.

“If future AFib could be accurately predicted from a widely used and inexpensive test, this could identify a high-risk population that could then be screened with a continuous monitoring device,” wrote lead author Sushravya Raghunath , PhD, a computational scientist for Geisinger in Danville, Pennsylvania, and colleagues. “Machine learning, in particular deep neural networks (DNNs), can likely assist with this task.”

To test this theory, Raghunath et al. designed a DNN to predict new-onset AFib in patients with no prior history of AFib. The DNN was trained with 1.6 million 12-lead ECGs from 431,000 patients who were treated by a single U.S. health system from 1984 to 2019. To simulate deployment in a real-world situation, a second DNN was trained using data from 1984 to 2010 and then tested on ECG data from 2010 to 2014.

Overall, the team’s AI model achieved an area under the ROC curve of 0.85 and area under the precision-recall curve of 0.22 for predicting new-onset AFib within one year. When the authors simulated real-world deployment with that second DNN, the model’s sensitivity was 69% and its specificity was 81%.

The authors noted that these models could be used to prevent AFib-related stroke or even arrhythmia-induced cardiomyopathy. The earlier a potential case of AFib can be identified, the earlier the patient in question can receive the treatment they need.

“In addition to allowing early treatment for new-onset AFib, a clinical risk prediction tool such as this could be used for the prevention of AFib,” they wrote. “A high-risk prediction of future AFib could bring increased attention to modifiable risk factors such as obesity and obstructive sleep apnea, with the goal of avoiding AFib altogether.”

Click here for the full study.

Michael Walter
Michael Walter, Managing Editor

Michael has more than 16 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.

Around the web

Eleven medical societies have signed on to a consensus statement aimed at standardizing imaging for suspected cardiovascular infections.

Kate Hanneman, MD, explains why many vendors and hospitals want to lower radiology's impact on the environment. "Taking steps to reduce the carbon footprint in healthcare isn’t just an opportunity," she said. "It’s also a responsibility."

Philips introduced a new CT system at ECR aimed at the rapidly growing cardiac CT market, incorporating numerous AI features to optimize workflow and image quality.

Trimed Popup
Trimed Popup