Deep learning unmasks the ECG signature of Brugada Syndrome

<b>Abstract</b><br/><p><span dir="ltr">One in ten cases of sudden cardiac death strikes without warning as the result of an inherited arrhythmic cardiomyopathy, </span><span dir="ltr">such as Brugada Syndrome (BrS). Normal physiological variations often obscure visible signs of this and related life-</span><span dir="ltr">threatening channelopathies in conventional electrocardiograms (ECGs). Sodium channel blockers can reveal previously </span><span dir="ltr">hidden diagnostic ECG features, however, their use carries the risk of life-threatening proarrhythmic side effects. The </span><span dir="ltr">absence of a non-invasive test places a grossly underestimated fraction of the population at risk of SCD. Here, we present </span><span dir="ltr">a machine learning algorithm that extracts, aligns, and classifies ECG waveforms for the presence of BrS. This protocol, </span><span dir="ltr">which succeeds without the use of a sodium channel blocker (88.4% accuracy, 0.934 AUC in validation), can aid clinicians </span><span dir="ltr">everywhere to identify the presence of this potentially life-threatening heart disease more easily.</span></p>