Diagnostic Accuracy of a Smartphone-Operated, Single-Lead Electrocardiography Device for Detection of Rhythm and Conduction Abnormalities in Primary Care

Abstract

PURPOSE To validate a smartphone-operated, single-lead electrocardiography (1L-ECG) device (AliveCor KardiaMobile) with an integrated algorithm for atrial fibrillation (AF) against 12-lead ECG (12L-ECG) in a primary care population. METHODS We recruited consecutive patients who underwent 12L-ECG for any nonacute indication. Patients held a smartphone with connected 1L-ECG while local personnel simultaneously performed 12L-ECG. All 1L-ECG recordings were assessed by blinded cardiologists as well as by the smartphone-integrated algorithm. The study cardiologists also assessed all 12L-recordings in random order as the reference standard. We determined the diagnostic accuracy of the 1L-ECG in detecting AF or atrial flutter (AFL) as well as any rhythm abnormality and any conduction abnormality with the simultaneously performed 12L-ECG as the reference standard. RESULTS We included 214 patients from 10 Dutch general practices. Mean ± SD age was 64.1 ± 14.7 years, and 53.7% of the patients were male. The 12L-ECG diagnosed AF/AFL, any rhythm abnormality, and any conduction abnormality in 23, 44, and 28 patients, respectively. The 1L-ECG as assessed by cardiologists had a sensitivity and specificity for AF/AFL of 100% (95% CI, 85.2%-100%) and 100% (95% CI, 98.1%-100%). The AF detection algorithm had a sensitivity and specificity of 87.0% (95% CI, 66.4%-97.2%) and 97.9% (95% CI, 94.7%-99.4%). The 1L-ECG as assessed by cardiologists had a sensitivity and specificity for any rhythm abnormality of 90.9% (95% CI, 78.3%-97.5%) and 93.5% (95% CI, 88.7%-96.7%) and for any conduction abnormality of 46.4% (95% CI, 27.5%-66.1%) and 100% (95% CI, 98.0%-100%). CONCLUSIONS In a primary care population, a smartphone-operated, 1L-ECG device showed excellent diagnostic accuracy for AF/AFL and good diagnostic accuracy for other rhythm abnormalities. The 1L-ECG device was less sensitive for conduction abnormalities.

A short guide for medical professionals in the era of artificial intelligence

“…A study concluded that the device managed to distinguish between atrial fibrillation and a normal heart rhythm with a sensitivity of 93, and a specificity of 94%, respectively. Its sensitivity increased to 99% when a medical professional reviewed the reading 26 .…”

Single-lead ECGs (AliveCor) are a feasible, cost-effective and safer alternative to 12-lead ECGs in community diagnosis and monitoring of atrial fibrillation

“…There is mounting evidence for the utility of integrating singlelead ECGs into healthcare provision in a number of settings. [10][11][12][13][14][15][16] This pilot initiative aimed to test the feasibility of integrating a single-lead hand-held ECG system, the AliveCor, into community monitoring of treatment in patients with recently diagnosed fast AF and opportunistic community diagnosis of AF.…”

Rövid útmutató egészségügyi szakemberek számára a mesterséges intelligencia korában • A Short Guide for Medical Professionals in the Era of Artificial Intelligence

“…Egy tanulmány megállapította, hogy a KardiaBand 93 százalékos érzékenységgel és 94 százalékos specificitással képes megkülönböztetni a pitvarfibrillációt és a normális szívritmust. Az érzékenység 99 százalékosra nőtt, amikor orvos is értékelte az adatokat (Himmelreich et al, 2019).…”