A Pulse at Your Fingertips express
During surgery, an anesthesiologist watches a screen where pressure and pulse curves run. But behind these lines hide several other quantities: how much the vessels constrict, how fast the blood flows, how elastic the artery walls are. Precise instruments for measuring them are only used in the most severe cases because it's risky — a needle in the artery, a catheter in the heart.
Researchers proposed the HIPNO system, which reconstructs hidden blood flow parameters from ordinary signals — pulse, arm pressure, ECG. The difficulty is that different combinations of flow, resistance, and vessel elasticity can produce the same pressure. It's like hearing the same melody played on different instruments. HIPNO learns to distinguish these instruments by relying on the physics of circulation. It finds three key coordinates: how quickly blood decays in the vessels, the ratio of flow to elasticity, and the characteristic impedance of the arteries.
On data from nearly a million measurements in 2562 patients, HIPNO predicted the decay rate of the pulse wave 32% more accurately than simple methods, and without losing accuracy in estimating mean pressure. Moreover, if you mentally change one parameter, say increase vascular resistance, the system responds as expected in 90% of cases — meaning it truly separated the hidden factors rather than just memorizing the curves. This separation opens the way to non-invasive assessment of cardiac output and other important indicators.
Original abstract
as written by the authors arXiv:2608.10011v1
Continuous hemodynamic monitoring guides treatment decisions in surgery and intensive care. However, gold-standard signals are only measured in severe cases due to risks associated with invasive measurement. In this work, we introduce HIPNO (Hemodynamic Inference via Physics-informed Neural Operators) to recover hemodynamic state from ubiquitous, non-invasive signals and expand access to advanced monitoring. HIPNO addresses a problem of scale symmetry in physics-informed hemodynamic inference, where different combinations of flow, resistance, and compliance can generate the same observed pressure. We identify the symmetry group of the observation model and parameterize the network in its quotient space. For the 3-element Windkessel model, the quotient coordinates are the compliance-normalized flow $$U=Q/C$$, the decay time constant $$\tau_{WK}=R_2 C$$, and the characteristic-impedance coordinate $$\kappa=R_1 C$$. Across 945499 intraoperative windows from 2562 patients, HIPNO predicts $$\tau_{wave}$$, a proxy for vascular decay derived from pressure, with 32% lower error on the log scale than a population baseline while preserving mean arterial pressure accuracy. Because vascular decay and flow drive occupy separate coordinates, counterfactual perturbations produce the expected directional responses in at least 90% of windows in almost all prespecified scenarios, a separation unavailable to pressure-only baselines. The coordinates are also used as inputs to a calibration model for monitored cardiac output. Finally, the formulation identifies the external compliance or flow reference required to recover absolute physical scale.
The pulse wave velocity in humans is about 5–10 meters per second, comparable to a cheetah's sprint speed.