Exploring nurse- and allied health professional-led opportunistic atrial fibrillation screening with artificial intelligence-enabled devices in community and primary care

Undiagnosed atrial fibrillation (AF) is a leading cause of preventable ischemic stroke, particularly in the ageing populations. While traditional screening relies on physician-interpreted 12-lead electrocardiography (ECG), which is considered the gold standard, the increasing availiability of new artificial intelligence (AI)-enabled devices, such as single-lead ECG and photoplethysmography (PPG) tools, offer decentralised and scalable alternatives. This mini review argues that AI-enabled, nurse- and allied health professional (AHP)-led opportunistic screening represents a necessary paradigm shift in AF detection in the community and primary care setting. It is transitioning from a reactive, physician-dependent model to a proactive, community-based approach to provide early, timely and accessible interventions to reduce the risks of stroke. These devices have demonstrated good diagnostic accuracy when compared with ECG. Nurse-led opportunistic screening was found to be cost-effective and to reduce stroke risk by facilitating earlier anticoagulant initiation. Widespread adoption has been hindered by substantial barriers such as false positive results, a lack of standardised training, and liability concerns regarding AI interpretation. However, nurses and AHPs are uniquely positioned to lead opportunistic AF screening initiatives using AI technology. To maximise the clinical impact and solidify this new paradigm, future implementation strategies should prioritise workforce training, robust data governance, and the integration of AI findings into established clinical pathways to enable physician confirmation.