A study, published in the European Heart Journal–Digital Health, shows the predictive potential of a deep-learning model in identifying patients at risk of atrial fibrillation (AF) following monitoring with a 24-hour ambulatory electrocardiogram (ECG), despite no documented prior AF, according to researchers.
Led by Jagmeet Singh (Harvard Medical School, Boston, USA) the study involved training Cardiologs’ deep neural network to predict the near-term presence or absence of AF by only using the first 24 hours of an extended Holter recording.
Results showed that the network was able to predict whether AF would occur in the near future with an area under the receiver operating curve, sensitivity, and specificity of 79.4%, 76%, and 69%, respectively, and outperformed ECG features previously shown to be predictive of AF. These results showed a ten-point improvement compared to a baseline model using age and sex, researchers suggested.
The study is the first of its kind to demonstrate the capability of artificial intelligence in predicting AF in the short-term using 24-hour Holter compared to resting 12-lead ECGs, the developer of the deep-learning model, Cardiologs, said in a press release. While 12-lead ECG gives access to a larger view of the hearts’ activity for a short period, 24-hour Holter provides longer-duration signals, therefore, offering additional inputs for predicting models.
“Cardiologs’ study shows that 24-hour Holter data can be used to enhance current monitoring capabilities, bringing hope to high-risk patients who would benefit from proactive treatment and AF mitigation strategies. By getting patients the care they need sooner and potentially preventing more severe outcomes, we could help save many lives,” said Singh.
