AI Filter Improves Positive Predictive Value of Atrial Fibrillation Detection by an Implantable Loop Recorder.

OBJECTIVES: The purpose of this study was to determine whether incorporation of a 2-part artificial intelligence (AI) filter can improve the positive predictive value (PPV) of implantable loop recorder (ILR)-detected atrial fibrillation (AF) episodes. BACKGROUND: ILRs can detect AF. Devices transmit data daily. It is critical that the PPV of ILR-detected AF events be high. METHODS: In total, 1,500 AF episodes were evaluated from patients with cryptogenic stroke or known AF who underwent ILR implantation (Reveal LINQ, Medtronic, Minneapolis, Minnesota). Each episode was annotated as either a true or false AF episode to determine the PPV. A 2-part AI-based filter (Cardiologs, Paris, France) was then employed using a deep neural network (DNN) for AF detection. The impact of this DNN filter on the PPV was then assessed. RESULTS: The cohort included 425 patients (mean age 69 ± 10 years; 62% men) with an ILR. After excluding 17 (1.1%) uninterpretable electrocardiograms, 800 (53.9%) of the remaining 1,483 episodes were manually adjudicated to represent an actual atrial arrhythmia. The PPV of ILR-detected AF episodes was 53.9% (95% confidence interval (CI): 51.4% to 56.5%), which increased to 74.5% (95% CI: 71.8% to 77.0%; p < 0.001) following use of the DNN filter. The increase was greatest for AF episodes ≤30 min. The most common reason for a false-positive AF event was premature atrial contractions. There was a negligible failure to identify true AF episodes. CONCLUSIONS: Despite currently available ILR programming options, designed to maximize PPV in a given population, false-positive AF episodes remain common. An AI-based solution may significantly reduce the time and effort needed to adjudicate these false-positive events.

Detection of atrial fibrillation using an implantable loop recorder following cryptogenic stroke: implications for post-stroke electrocardiographic monitoring.

PURPOSE: Approximately 10-40% of strokes are cryptogenic (CS). Long-term electrocardiographic (ECG) monitoring has been recommended in these patients to search for atrial fibrillation (AF). An unresolved issue is whether ambulatory ECG (AECG) monitoring should be performed first, followed by an implantable loop recorder (ILR) if AECG monitoring is non-diagnostic, or whether long-term ECG monitoring should be initiated using ILRs from the onset. The purpose of this study was to assess, using an ILR, AF incidence in the first month after CS. METHODS: We enrolled consecutive CS patients referred for an ILR. All patients were monitored via in-hospital continuous telemetry from admission until the ILR (Medtronic [Minneapolis, MN] LINQ™) was implanted. The duration and overall burden of all AF episodes ≥ 2 min was determined. RESULTS: The cohort included 343 patients (68 ± 11 years, CHA2DS2-VASc 3.5 ± 1.7). The time between stroke and ILR was 3.7 ± 1.5 days. During the first 30 days, only 18 (5%) patients had AF. All episodes were paroxysmal, lasting from 2 min to 67 h and 24 min. The median AF burden was 0.85% (IQR 0.52, 10.75). During 1 year of follow-up, 67 (21%) patients had AF. CONCLUSION: The likelihood of AF detection by an ILR in the first month post-CS is low. Thus, the diagnostic yield of 30 days of AECG monitoring is likely to be limited. These data suggest a rationale for proceeding directly to ILR implantation prior to hospital discharge in CS patients, as many have AF detected during longer follow-up.