As smart watches come packed with several health features, earlier studies have validated the accuracy of the Apple Watch for the diagnosis of atrial fibrillation (AF) in a limited number of patients with similar clinical profiles. However, in patients with a variety of coexisting ECG abnormalities, there is still a long way to go for smartwatch developers, reveal researchers in the larest study to date.
The study in the Canadian Journal of Cardiology, published by Elsevier, found that the use of smartwatches is challenging in patients with abnormal ECGs.
Better algorithms and machine learning may help these tools provide more accurate diagnoses, investigators said.
“With the growing use of smartwatches in medicine, it is important to know which medical conditions and ECG abnormalities could impact and alter the detection of AF by the smartwatch in order to optimise the care of our patients,” said lead investigator Marc Strik from LIRYC institute, Bordeaux University Hospital, Bordeaux, France.
“Smartwatch detection of AF has great potential, but it is more challenging in patients with pre-existing cardiac disease,” Strik noted.
The study included 734 hospitalised patients. Each patient underwent a 12-lead ECG, immediately followed by a 30-second Apple Watch recording.
The smartwatch’s automated single-lead ECG AF detections were classified as “no signs of atrial fibrillation,” “atrial fibrillation,” or “inconclusive reading.”
In approximately one in every five patients, the smartwatch ECG failed to produce an automatic diagnosis.
The risk of having a false positive automated AF detection was higher for patients with premature atrial and ventricular contractions (PACs/PVCs), sinus node dysfunction, and second- or third-degree atrioventricular-block.
The smartphone app correctly identified 78 per cent of the patients who were in AF and 81 per cent who were not in AF.
The electrophysiologists identified 97 per cent of the patients who were in AF and 89 per cent who were not.
“These observations are not surprising, as smartwatch automated detection algorithms are based solely on cycle variability,” Dr Strik noted.
“Ideally, an algorithm would better discriminate between PVCs and AF. Any algorithm limited to the analysis of cycle variability will have poor accuracy in detecting AT/AFL. Machine learning approaches may increase smartwatch AF detection accuracy in these patients,” he added.
This is the first “real-world” study focusing on the use of the Apple Watch as a diagnostic tool for AF, said Andres F. Miranda-Arboleda and Adrian Baranchuk, Division of Cardiology, Kingston Health Science Center, Canada.
“In a certain manner, the smartwatch algorithms for the detection of AF in patients with cardiovascular conditions are not yet smart enough. But they may soon be,” they said.