Supermarket/hypermarket opportunistic screening for atrial fibrillation (SHOPS-AF) using sensors embedded in the handles of supermarket trolleys: A feasibility study.

BACKGROUND: Atrial fibrillation (AF) increases the risk of death, stroke, heart failure, cognitive decline, and healthcare costs but is often asymptomatic and undiagnosed. There is currently no national screening program for AF. The advent of validated hand-held devices allows AF to be detected in non-healthcare settings, enabling screening to be undertaken within the community. METHOD AND RESULTS: In this novel observational study, we embedded a MyDiagnostick single lead ECG sensor into the handles of shopping trolleys in four supermarkets in the Northwest of England: 2155 participants were recruited. Of these, 231 participants either activated the sensor or had an irregular pulse, suggesting AF. Some participants agreed to use the sensor but refused to provide their contact details, or consent to pulse assessment. In addition, some data were missing, resulting in 203 participants being included in the final analyses. Fifty-nine participants (mean age 73.6 years, 43% female) were confirmed or suspected of having AF; 20 were known to have AF and 39 were previously undiagnosed. There was no evidence of AF in 115 participants and the remaining 46 recordings were non-diagnostic, mainly due to artefact. Men and older participants were significantly more likely to have newly diagnosed AF. Due to the number of non-diagnostic ECGs (n = 46), we completed three levels of analyses, excluding all non-diagnostic ECGs, assuming all non-diagnostic ECGs were masking AF, and assuming all non-diagnostic ECGs were not AF. Based on the results of the three analyses, the sensor's sensitivity (95% CI) ranged from 0.70 to 0.93; specificity from 0.15 to 0.97; positive predictive values (PPV) and negative predictive values (NPV) ranged from 0.24 to 0.56 and 0.55 to 1.00, respectively. These values should be interpreted with caution, as the ideal reference standard on 1934 participants was imperfect. CONCLUSION: The study demonstrates that the public will engage with AF screening undertaken as part of their daily routines using hand-held devices. Sensors can play a key role in identifying asymptomatic patients in this way, but the technology must be further developed to reduce the quantity of non-diagnostic ECGs.

AI-based derivation of atrial fibrillation phenotypes in the general and critical care populations.

BACKGROUND: Atrial fibrillation (AF) is the most common heart arrhythmia worldwide and is linked to a higher risk of mortality and morbidity. To predict AF and AF-related complications, clinical risk scores are commonly employed, but their predictive accuracy is generally limited, given the inherent complexity and heterogeneity of patients with AF. By classifying different presentations of AF into coherent and manageable clinical phenotypes, the development of tailored prevention and treatment strategies can be facilitated. In this study, we propose an artificial intelligence (AI)-based methodology to derive meaningful clinical phenotypes of AF in the general and critical care populations. METHODS: Our approach employs generative topographic mapping, a probabilistic machine learning method, to identify micro-clusters of patients with similar characteristics. It then identifies macro-cluster regions (clinical phenotypes) in the latent space using Ward's minimum variance method. We applied it to two large cohort databases (UK-Biobank and MIMIC-IV) representing general and critical care populations. FINDINGS: The proposed methodology showed its ability to derive meaningful clinical phenotypes of AF. Because of its probabilistic foundations, it can enhance the robustness of patient stratification. It also produced interpretable visualisation of complex high-dimensional data, enhancing understanding of the derived phenotypes and their key characteristics. Using our methodology, we identified and characterised clinical phenotypes of AF across diverse patient populations. INTERPRETATION: Our methodology is robust to noise, can uncover hidden patterns and subgroups, and can elucidate more specific patient profiles, contributing to more robust patient stratification, which could facilitate the tailoring of prevention and treatment programs specific to each phenotype. It can also be applied to other datasets to derive clinically meaningful phenotypes of other conditions. FUNDING: This study was funded by the DECIPHER project (LJMU QR-PSF) and the EU project TARGET (10113624).