Optimising implantable loop recorder alerts with artificial intelligence: role of R-wave amplitude and workload...

Area of Science:

• Cardiology
• Medical Devices
• Artificial Intelligence

Background:

• Implantable loop recorders (ILRs) generate false-positive (FP) alerts, increasing clinical workload and potentially delaying patient care.
• AccuRhythm AI is a cloud-based algorithm designed to reduce FP alerts from Reveal LINQ and LINQ II devices.
• R-wave sensing amplitude is a potential factor influencing FP alert rates.

Purpose of the Study:

• To assess the impact of AccuRhythm AI on reducing FP alerts and clinician burden.
• To evaluate the influence of R-wave sensing amplitude on FP alert incidence.

Main Methods:

• A multicentre, retrospective study of 800 patients with Reveal LINQ or LINQ II devices.
• Analysis of automated artificial intelligence (AI) reports comparing FP rates and transmission burden before and after AI activation.
• Evaluation of the relationship between R-wave amplitude and FP incidence.

Main Results:

• AccuRhythm AI reduced false pause alerts by 62% and false atrial fibrillation alerts by 33%, saving 210 clinician hours over 6 months.
• In Reveal LINQ patients (n=465), FP+ patients decreased from 55.5% to 15.1% post-AI (p<0.001), saving 1128 hours.
• Residual false alerts were associated with R-wave amplitudes <0.4 mV.

Conclusions:

• AccuRhythm AI significantly reduces FP alerts and clinician workload without compromising diagnostic accuracy.
• Optimal device implantation and signal quality, particularly R-wave amplitude, remain critical for alert specificity.