Tag
The paper evaluates ECG biometrics under realistic conditions involving exercise-induced stress and cross-session variability using a Siamese ResNet model, achieving state-of-the-art performance.
Introduces CardioState-JEPA, a cardiac foundation model that learns a shared representation across ECG, PPG, and PCG signals using a delay-aware joint-embedding predictive architecture, improving downstream cardiac classification tasks.
An autopsy study found replicating SARS-CoV-2 in the hearts of Long COVID patients, associated with cardiac symptoms and gene expression changes, suggesting viral persistence drives Long COVID cardiac pathology.