Smartphone detection of atrial fibrillation having difficulty with abnormal ECG

Smartphone detection of atrial fibrillation having difficulty with abnormal ECG

New findings show that portable health technologies for detecting atrial fibrillation are associated with a high rate of false positives and inconclusive outcomes in patients with certain heart conditions.

The largest real-world study to date has indicated that the use of these devices is particularly challenging in patients with abnormal electrocardiograms (ECGs). Both improved algorithms and machine learning can help the tools provide more accurate diagnoses, according to the researchers.

“With the increasing use of smartwatches in medicine, it is important to learn about the medical conditions and abnormalities in the electrocardiogram that can influence and alter the detection of atrial fibrillation by the smartwatch in order to improve the care of our patients,” said study lead author Mark Strick. MD, PhD, LIRYC Institute, Purdue University Hospital. “Smart clock detection for atrial fibrillation has great potential, but is more difficult in patients with pre-existing heart disease.”

In theory, the use of extended cardiac monitoring in patients and the use of implantable cardiovascular electronic devices may increase the detection of atrial fibrillation. However, hardware limitations include short battery life and a lack of instant feedback.

New smartphone tools with the ability to record ECG tape and perform automated diagnostics may overcome the above limitations and lead to timely diagnosis. Strick noted that previous studies have validated the accuracy of the Apple Watch for diagnosing atrial fibrillation in “a limited number of patients with similar clinical profiles.”

Investigators tested the accuracy of the Apple Watch ECG app in detecting atrial fibrillation in patients with a variety of ECG abnormalities.

Their study included a total of 734 consecutive hospitalized patients. They each underwent a 12-line ECG, with immediate follow-up by a 30-second Apple Watch recording.

The investigators reported that the automated single-lead ECG AF detections for each smartwatch were categorized as “no signs of atrial fibrillation,” “atrial fibrillation,” or “inconclusive reading.” The recordings were submitted to an electrophysiologist who performed a blind reading, and assigned each a diagnosis of ‘atrial fibrillation’, ‘absence of atrial fibrillation’, or ‘the diagnosis unclear’. A blind electrophysiologist analyzed the last 100 randomly selected traces to determine the ‘agreement of observers’.

The results indicated that the Smartwatch ECG failed to produce an automatic diagnosis in about one in five patients.

In addition, the investigators reported that the risk of having a false-positive instrumental detection of atrial fibrillation was higher for patients with premature atrial and ventricular contractions (PACs/PVCs), sinus node dysfunction, and second- or third-degree atrioventricular block.

For those with atrial fibrillation, the risk of having false negative tracking (missing AF) was reported to be higher for patients with ventricular conduction abnormalities (intraventricular conduction delays) or rhythms controlled by an implantable pacemaker. Furthermore, cardiac electrophysiologists had a high level of agreement on the differentiation between atrial fibrillation and non-atrial fibrillation.

The data indicate that the smartphone app correctly identified 78% of patients in AF and 81% who were not in AF. Meanwhile, electrophysiologists identified 97% of patients with atrial fibrillation and 89% who were not in atrial fibrillation.

Subjects with PVCs were three times more likely to be diagnosed with false positive atrial fibrillation than a Smartwatch ECG according to the data, and the identification of patients with atrial tachycardia (AT) and atrial flutter (AFL) was considered very poor.

“These observations are not surprising, because the automatic detection algorithms of smart watches rely solely on cycle fluctuation,” Strick added. “Ideally, it would be better for the algorithm to distinguish between PVCs and AF. Any algorithm that is limited to analyzing cycle variability will have poor accuracy in AT/AFL detection. Machine learning methods may increase the accuracy of smartwatch AF detection in these patients” .

The article titled “The Role of Co-Presence of ECG Shapes in the Accuracy of Smartwatch ECG Detection of Atrial Fibrillation” is published in Canadian Journal of Cardiology.

#Smartphone #detection #atrial #fibrillation #difficulty #abnormal #ECG

Leave a Comment

Your email address will not be published. Required fields are marked *