Accurate estimation of arterial viscoelastic properties is essential for realistic modeling of cardiovascular hemodynamics. In one-dimensional fluid– structure interaction models, the relationship between pressure and vessel deformation is governed by both elastic and viscous effects. Viscous effects can play an important role in the blood flow but are often disregarded due to the difficulty of measuring them with accuracy. One way of extracting this viscoleastic parameters from measured pressure, flow or arterial cross-sectional area data are Physics-Informed Neural Networks (PINN). The model is trained by minimizing a composite loss function combining data fitting and physical consistency. PINNs enable the simultaneous reconstruction of both the hemodynamic fields and the underlying viscoelastic parameters, which are often very difficult to estimate.