[Skip to Content]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address Please contact the publisher to request reinstatement.
[Skip to Content Landing]
Views 2,617
Citations 0
In This Issue of JAMA Cardiology
May 2019


JAMA Cardiol. 2019;4(5):399. doi:10.1001/jamacardio.2018.3195

Hyperkalemia is common in patients with chronic kidney disease, often asymptomatic, and associated with fatal arrhythmias. Galloway and coauthors developed and validated a deep convolutional neural network for detection of hyperkalemia using 1 576 581 electrocardiograms (ECGs) from 449 380 patients and validated in 61 965 patients with stage 3 or greater chronic kidney disease. Using only 2 ECG leads (leads I and II), a deep-learning model detected hyperkalemia in patients with renal disease with an area under the receiver operating characteristic curve of 0.853 to 0.883. The application of artificial intelligence to the ECG may enable screening for hyperkalemia. Prospective studies of this deep-learning model are warranted.