Clinical Electrophysiology -> Atrial Fibrillation & Atrial Flutter: -> Electrocardiography D-PO02 - Poster Session II (ID 47) Poster

D-PO02-204 - Atrial Signal Clarity Is Critical If Artificial Intelligence (AI) Is To Be Used To Distinguish Atrial Fibrillation (AF) From Rhythms That Mimic AF (ID 1058)

Disclosure

 D. Paris: Nothing relevant to disclose.

Audio File Upload
Video File Upload

Abstract

Background: The diagnosis of atrial fibrillation (AF) with Artificial intelligence (AI), either with medically prescribed ECG monitors or non-prescription devices such as watches, is not to be taken lightly. Little focus has been placed on the cost, anxiety and potential therapeutic consequences of a false positive diagnosis. The potential value of AI in AF diagnostics is not debated here, but if it is to be used, the ECG used to determine the truth set should be capable of sorting AF from its various mimickers. Many current methods are limited by the duration of the ECG and the fidelity of the P-wave. These limitations can lead to misdiagnosis of other arrhythmias with RR interval variability as AF.
Objective: Our objective was to build an AI to detect AF with better than 90% sensitivity and 90% specificity capable of identifying the onset and offset of episodic AF events, without conflating other atrial (or ventricular) arrhythmias that mimic AF.
Methods: For this work, we used ECG recordings from 579 patients who wore the Carnation Ambulatory Monitor (CAM) (Bardy Diagnostics, Inc., Seattle, WA). 74 patients with persistent AF, 143 patients with paroxysmal AF, and 362 patients without AF. Included in the 362 patients were 103 patients with dense atrial or ventricular ectopy, and both atrial flutter and sustained atrial tachycardia with variable conduction. This distinction relates to differences in medical and procedural management, and stroke risk.
Results: Our validation was comprised of four hours of CAM ECG data chosen at random from 50 AF-positive patients and 50 AF-negative patients (400 hours total). AF presence and duration were confirmed by a team of experienced electrophysiology clinicians. The AI differentiates AF not only from normal sinus rhythm, but also from other conditions such as atrial ectopy, ventricular ectopy, atrial flutter and atrial tachycardia with variable conduction. Our results were 97% sensitive and 98% specific with a positive predictivity of 94% for detecting 30 seconds of AF or longer.
Conclusion: Our P-wave centric continuous ECG monitoring technology allows our neural network, or AI, to differentiate between AF and a host of rhythms that mimic AF. AI systems that do not make these distinctions may mislead both patients and clinicians.

Collapse