Improved detection of paroxysmal atrial fibrillation utilizing a software-assisted electrocardiogram approach

Abstract

Background: Automated complexity-based statistical stroke risk analysis (SRA) of electrocardiogram (ECG) recordings can be used to estimate the risk of paroxysmal atrial fibrillation (pAF). We investigated whether this method could improve the reliability of detection of patients at risk for pAF.

Methods and results: Data from 12-lead ECGs, 24-h Holter ECGs, and SRA based on separate 1-hour Holter ECG snips were collected from three groups: 70 patients with a history of pAF but who showed no AF episode in the 12-lead ECG at study entry; 19 patients with chronic AF (at study entry); and 100 young healthy individuals. AF episodes were detected by Holter ECG in 19 of the 70 non-chronic AF patients (27.1% overall, 18.6% in the first hour), and 37 of these 70 patients were classified as at risk for pAF by SRA (representing a sensitivity of 52.9% based on the first hour of analyzed recording). Fifty-four of the 70 patients also showed a sinus rhythm in the first hour. SRA detected pAF risk in 23 of these 54 patients (representing a sensitivity of 42.6%). The Holter data showed at least 1 AF episode and at least 1 hour of sinus rhythm in nine of the patients with pAF. For these patients, SRA classified 77.8% as being at risk in the first hour after the end of the AF episode, and 71.4% and 42.9% as being at risk in the second and third hours, respectively. SRA detected almost all cardiologist-confirmed AF episodes that had been recorded in 1-hour ECG snips (sensitivity, 99.2%; specificity, 99.2%).

Conclusions: This outpatient study confirms previous findings that routine use of SRA could improve AF detection rates and thus may shorten the time between AF onset and initiation of prevention measures for patients at high risk for stroke.

Figure 1. Overview of the study flow.

AF =  atrial fibrillation; ECG =  electrocardiogram; SRA =  stroke risk analysis.