How to get the accuracy of a 12-lead ECG with an Apple Watch

Multichannel Electrocardiograms Obtained by a Smartwatch for the Diagnosis of ST-Segment Changes – JAMA Cardiology

Multichannel Electrocardiograms Obtained by a Smartwatch for the Diagnosis of ST-Segment Changes – JAMA Cardiology

Some researchers at Magna Grecia University have experimented with a technique to use Apple’s smartwatch instead of a traditional ECG.

In the study, published in JAMA Cardiology, Carmen Anna Maria Spaccarotella, Alberto Polimeni, Serena Migliorino and others asked themselves whether a smartwatch could record multi-lead electrocardiograms (ECG) and detect changes in the ST segment.

In the sample of 100 patients, Apple Watch was able to record multi-channel ECGs (leads I, II, III, V1, V2, V3, V4, V5 and V6) according to standard ECGs. In addition, the magnitude of ST segment variations detected with the smartwatch was comparable to that of standard ECGs.

The study was conducted from April 19, 2019 to January 23, 2020. The study involved 54 patients with ST elevation myocardial infarction, 27 patients with non-ST elevation myocardial infarction and 19 healthy individuals. The watch was placed in different body positions to obtain 9 bipolar ECG traces (corresponding to Einthoven leads I, II, and III and pre-cordial leads V1-V6) that were compared to a 12-lead simultaneous standard ECG.

The concordance between the results of the smartwatch recordings and the standard ECG was evaluated using the Cohen κ coefficient and the Bland-Altman analysis.

Using the standard ECG readings as reference, the ST segment elevation of the smartwatch demonstrated sensitivity of 93% and specificity of 95%. For the non-ST segment elevation, sensitivity was 94% and specificity 92%.

The results of this study suggest that the use of ECGs recorded on smartwatches could be useful for early detection of acute coronary syndromes; these data should be further examined in patients with suspected myocardial infarction where false positive and false negative results could be better characterized.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s