Atrial fibrillation detection via contactless radio monitoring and knowledge transfer

• Published in: Nature communications Vol. 16; no. 1; pp. 4317 - 11
• Main Authors: Yuan, Yuqin, Chen, Jinbo, Zhang, Dongheng, Geng, Ruixu, Gong, Hanqin, Xu, Guixin, Pu, Yu, Lu, Zhi, Hu, Yang, Zhang, Dong, Ma, Likun, Sun, Qibin, Chen, Yan
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 20.05.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/258; 692/4019/592/75/29/1309; 692/700/139; Arrhythmia; Artificial Intelligence; Atrial Fibrillation - diagnosis; Atrial Fibrillation - physiopathology; Cardiac arrhythmia; Diagnosis; EKG; Electrocardiography; Electrocardiography - methods; Female; Fibrillation; Humanities and Social Sciences; Humans; Male; Middle Aged; Monitoring; Morbidity; Mortality; multidisciplinary; Radar; Radio; Science; Science (multidisciplinary); Sensitivity and Specificity
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-025-59482-y

Atrial fibrillation (AF) has been a prevalent and serious arrhythmia associated with increased morbidity and mortality worldwide. The Electrocardiogram (ECG) is considered as the golden standard for AF diagnosis. However, current ECG is primarily used only when symptoms arise or for occasional checkups due to the necessity of contact-based measurements. This limitation results in difficulty of capturing early-stage AF episodes and missed opportunities for timely intervention. Here we introduce a contactless, operation-free, and device-free AF detection framework utilizing artificial intelligence (AI)-powered radio technology. Our approach analyzes the mechanical motion of the heart using radar sensing and leverages AI-powered knowledge transfer from established clinical ECG diagnostic practices to read AF-associated motion patterns precisely. Our system is evaluated on 6258 outpatient visitors, including 229 with AF, and achieves AF detection with a sensitivity of 0.844 (95% Confidence Interval (CI), 0.790-0.884) and a specificity of 0.995 (95% CI, 0.993-0.997), which is comparable to the performance of ECG-based methods. We also provide initial evidence that this system could be deployed in a practical daily life scenario, detecting AF before traditional clinical diagnosis routines. These results highlight its potential to support feasible lifelong proactive monitoring, covering the full spectrum of AF progression. Atrial fibrillation is a prevalent and serious arrhythmia associated with increased morbidity and mortality worldwide. Here the authors show a contactless, operation-free, and device-free AF detection framework utilizing artificial intelligence-powered radio technology, achieving performance comparable to conventional ECG-based methods.