The RITMIA™ Smartphone App for Automated Detection of Atrial Fibrillation: Accuracy in Consecutive Patients Undergoing Elective Electrical Cardioversion

الملخص EN

Background.

The RITMIA™ app (Heart Sentinel™, Parma, Italy) is a novel application that combined with a wearable consumer-grade chest-strap Bluetooth heart rate monitor, provides automated detection of atrial fibrillation (AF), and may be promising for sustainable AF screening programs, since it is known that prolonged monitoring leads to increased AF diagnosis.

Objective.

The purpose of this study was to examine whether RITMIA™ could accurately differentiate sinus rhythm (SR) from AF compared with gold-standard physician-interpreted 12-lead electrocardiogram (ECG).

Design.

In this observational prospective study consecutive patients presenting for elective cardioversion (ECV) of AF, from November 2017 to November 2018, were enrolled.

Patients underwent paired 12-lead ECG and RITMIA™ recording, both before and after ECV procedure.

The RITMIA™ automated interpretation was compared with 12-lead ECG interpreted by the agreement of two cardiologists.

The latter were blinded to the results of the App automated diagnosis.

Feasibility, sensitivity, specificity, and K coefficient for RITMIA™ automated diagnosis were calculated.

Results.

A total of 100 consecutive patients were screened and enrolled.

Five patients did not undergo ECV due to spontaneous restoration of SR.

95 patients who actually underwent ECV were included in the final analysis.

Mean age was 66.2±10.7 years; female patients were 20 (21.1%).

There were 190 paired ECGs and RITMIA™ recordings.

The RITMIA™ app correctly detected AF with 97% sensitivity, 95.6% specificity, and a K coefficient of 0.93.

Conclusions.

The automated RITMIA™ algorithm very accurately differentiated AF from SR before and after elective ECV.

The only hardware required by this method is a cheap consumer-grade Bluetooth heart rate monitor of the chest-strap type.

This robust and affordable RITMIA™ technology could be used to conduct population-wide screening in patients at risk for silent AF, thanks to the long-term monitoring applicability.