16 papers
Smartwatch Photoplethysmography-Derived Heart Age via ECG-Guided Cross-Modal Pretraining as a Digital Biomarker of Vascular Aging
Donglin Xie, Xueying Gui, Yutian Zhu +9
Digital biomarkers of cardiovascular aging, often termed heart or vascular age, have been widely studied, but most rely on resting electrocardiography (ECG), imaging, or specialize…
ImputeECG: Deep Learning Reconstruction of Complete 12-Lead Electrocardiograms from Incomplete Recordings for Cardiac Assessment
Xiaocheng Fang, Haoyu Wang, Jieyi Cai +14
Complete digital 12-lead electrocardiograms (ECGs) are essential for AI-enabled cardiovascular assessment, yet many clinical ECG records, particularly those digitized from ECG imag…
UniECG: Understanding and Generating ECG in One Unified Model
Jiarui Jin, Haoyu Wang, Xiang Lan +3
Electrocardiogram (ECG) interpretation is a fundamental skill in medical education, yet students often need more than static examples to connect waveform evidence with diagnostic r…
AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling
Guangkun Nie, Xiaocheng Fang, Gongzheng Tang +5
Photoplethysmography (PPG) is widely used as a non-invasive and accessible modality for continuous health monitoring. However, despite being a peripheral hemodynamic signal intrins…
Wearable Single-Lead ECG Detects Fine-Grained Structural Heart Disease Through Echo-Report Supervision
Chenyang He, Qinghao Zhao, Shun Huang +9
Structural heart disease (SHD) is a primary driver of heart failure and cardiovascular mortality, yet early detection remains constrained by the limited accessibility of echocardio…
Fine-tuning an ECG Foundation Model to Predict Coronary CT Angiography Outcomes
Yujie Xiao, Qinghao Zhao, Gongzheng Tang +12
Coronary artery disease (CAD) remains a major global public health burden, yet scalable pre-imaging risk stratification tools are limited. In this multicenter study, we developed a…