Clinical Validation of Automated Corrected QT-Interval Measurements From a Single Lead Electrocardiogram Using a Novel Smartwatch

Abstract

IntroductionThe Withings Scanwatch (Withings SA, Issy les Moulineaux, France) offers automated analysis of the QTc. We aimed to compare automated QTc-measurements using a single lead ECG of a novel smartwatch (Withings Scanwatch, SW-ECG) with manual-measured QTc from a nearly simultaneously recorded 12-lead ECG.MethodsWe enrolled consecutive patients referred to a tertiary hospital for cardiac workup in a prospective, observational study. The QT-interval of the 12-lead ECG was manually interpreted by two blinded, independent cardiologists through the tangent-method. Bazett’s formula was used to calculate QTc. Results were compared using the Bland-Altman method.ResultsA total of 317 patients (48% female, mean age 63 ± 17 years) were enrolled. HR-, QRS-, and QT-intervals were automatically calculated by the SW in 295 (93%), 249 (79%), and 177 patients (56%), respectively. Diagnostic accuracy of SW-ECG for detection of QTc-intervals ≥ 460 ms (women) and ≥ 440 ms (men) as quantified by the area under the curve was 0.91 and 0.89. The Bland-Altman analysis resulted in a bias of 6.6 ms [95% limit of agreement (LoA) –59 to 72 ms] comparing automated QTc-measurements (SW-ECG) with manual QTc-measurement (12-lead ECG). In 12 patients (6.9%) the difference between the two measurements was greater than the LoA.ConclusionIn this clinical validation of a direct-to-consumer smartwatch we found fair to good agreement between automated-SW-ECG QTc-measurements and manual 12-lead-QTc measurements. The SW-ECG was able to automatically calculate QTc-intervals in one half of all assessed patients. Our work shows, that the automated algorithm of the SW-ECG needs improvement to be useful in a clinical setting.

Smart devices to measure and monitor QT intervals

“…The Withings ScanWatch (SW, Withings SA, Issy les Moulineaux, France) is an analog watch with an in-built single-lead ECG. It offers, without manual measurement of the SW-ECG or the need for any other software, an automated analysis of the corrected QT interval ( 43 ). An artificial intelligence QTc (AI-QTc) is systematically measured from the smartwatch ECG (SW-ECG).…”

“…Another study examined the accuracy of different ECG-based devices, including the Withings ScanWatch, compared to the 12-lead standard ECG on several tasks. Mannhart et al ( 43 ) compared automated QTc measurements of the Withings ScanWatch with manually measured QTc from a 12-lead recorded ECG. A total of 317 patients referred for cardiac work-up were enrolled in this study.…”

“…The benefit of this Withings ScanWatch is the automated analysis of the corrected QT interval remotely without needing third-party software or manual measurement of SW-ECG. However, this is limited by the finding that the automated algorithm was able to measure QTc in only 56% of cases ( 43 ). On the other hand, a fair agreement was found between the QTc interval durations measured manually on a standard 12-lead ECG and assessed by AI on single-lead SW recordings ( 44 ).…”

Detection of QT interval prolongation using Apple Watch electrocardiogram in children and adolescents with congenital long QT syndrome

“…Second, it would have been ideal to be able to couple acquisition of smartwatch ECG tracings with automated measurement of QTc interval and interpretation of T wave morphologies utilizing artificial intelligence in one goal. Nonetheless, Mannhart et al reported automated calculation of QTc interval was only successful in 56% of adult patients assessed using the Withings Scanwatch (Withings SA, Issy les Moulineaux, France) [22] . Further works are required to refine algorithms for automated measurement of smartwatch-derived QTc interval.…”

Accuracy in detecting atrial fibrillation in single-lead ECGs: an online survey comparing the influence of clinical expertise and smart devices

“…Although the first SL-ECG device was introduced over 10 years ago [17] and new uses of smart devices are currently being explored [18][19][20], the amount of training and experience required to reliably interpret recordings generated by this novel technology remain uncertain. Currently there are no data or studies addressing this topic.…”