Belfast’s PulseAI Gains 510(k) Clearance for Wearable ECG AI

PulseAI announced on November 5, 2026 that the U.S. Food and Drug Administration had granted 510(k) clearance for its AI-powered arrhythmia analysis model for wearables, giving the Belfast medical technology company a regulatory milestone as it seeks to integrate automated electrocardiogram (ECG) interpretation into existing devices and software.

The FDA explains that a 510(k) is a premarket submission intended to demonstrate that a device is substantially equivalent to a legally marketed device that is not subject to premarket approval. PulseAI’s technology is designed for compatible ECG devices and software platforms: recordings are submitted for automated analysis in the cloud, and structured results return to the connected application for clinical review.

“With FDA clearance, our focus now is bringing this capability into the devices and platforms in use by millions every day,” said founder and CEO Dr Alan Kennedy.

Why Inconclusive Readings Matter

PulseAI is targeting the workload created after a wearable records an ECG. Inconclusive interpretations can require manual review, repeat recordings and patient follow-up. The company presents fewer unresolved results as a way to reduce staff time spent assessing patient-generated ECGs and potentially allow clinical services to accommodate more recordings with existing resources. Those are potential workflow benefits, not quantified cost savings.

PulseAI describes atrial fibrillation (AF), the condition examined in the study behind the announcement, as the most common sustained heart rhythm disorder; it can occur without symptoms and, when untreated, is associated with around a fivefold higher risk of ischaemic stroke, depending on individual risk factors.

What the Study Measured

A prospective study in Heart Rhythm compared Apple Watch’s native algorithm with an AI-enabled neural network on identical ECG recordings from 296 analyzable participants at an Irish teaching hospital between November 2022 and February 2023. Participants were admitted for ablation, cardioversion or electrophysiological testing, and AF prevalence was 21.6%.

The researchers applied three reporting frameworks: naive reporting excludes inconclusive outputs, pragmatic reporting counts them as incorrect, and intention-to-diagnose permits three attempts. Apple Watch sensitivity and specificity were 96.1% and 97.9% under naive reporting, 78.1% and 81.0% under pragmatic reporting, and 92.2% and 91.0% under intention-to-diagnose. The differences show how excluding unresolved readings can inflate reported diagnostic performance.

The study found that the AI algorithm reduced first-attempt inconclusive results from 17.6% to 1.4%, a 92% reduction. Its pragmatic sensitivity and specificity were 98.4% and 96.1%; under intention-to-diagnose, they were 98.4% and 96.6%. Repeatability was near-perfect for AI, with kappa 0.96, versus substantial for Apple Watch at 0.77.

The researchers placed the results in a specific context: AF detection from Apple Watch recordings in a cardiac-procedure cohort with higher arrhythmia prevalence than community populations, not performance for every arrhythmia or wearable. PulseAI funded the study, and the authors disclosed employment, directorship, shareholder and advisory ties to the company. To mitigate potential bias, physicians blinded to PulseAI results independently verified Apple Watch ECG interpretations, and the protocol and statistical analysis plan were preregistered.

Financing and Commercial Rollout

A January 12, 2026 financing announcement supplies the commercial lead-up. Innovation Ulster Limited led PulseAI’s seed round, with participation from The Mortara Group and The Francis Crick Institute. The investment was designated for scaling AI-ECG deployment, advancing FDA 510(k) work and clinical validation, productization for enterprise and OEM integration, and expanding partnerships with device manufacturers and hospital networks. Justin Mortara, former CEO of Mortara Instruments, was named incoming chair of the board.

The clearance completes one stated objective from that program while leaving the deployment objectives in view. The study addresses a measurable barrier to wearable ECG use, unresolved AF readings on Apple Watch, but the remaining commercial question is whether PulseAI can convert its planned device, platform, manufacturer and hospital integrations into deployments.