Key result
Convolutional neural networks accurately estimated cardiac output from peripheral pressure waveforms across radial, temporal, and carotid arteries with comparable predictive ability (r ≥ 0.97, nRMSE ≤ 4.4%).
Why the study?
Invasive cardiac output monitoring bears catheterization risks, motivating noninvasive AI-based estimation from arterial pressure waveforms, but the effects of measurement location, calibration, and noise are unclear.
Does AI-based estimation from peripheral arterial pressure waveforms accurately predict cardiac output in an in silico population?
Does AI-based estimation from peripheral arterial pressure waveforms accurately predict cardiac output in an in silico population?
Machine learning models can accurately estimate cardiac output from peripheral arterial pressure waveforms regardless of the measurement site, even without calibration, in a virtual population.
AI CO estimation from peripheral waveforms may expand site flexibility; leaves open human validation before clinical use.
Monitoring of cardiac output (CO) is a mainstay of hemodynamic management in the acutely or critically ill patient. Invasive determination of CO using thermodilution, albeit regarded as the gold standard, is cumbersome and bears risks inherent to catheterization. In the pursuit of noninvasive methods, prediction of CO from arterial pressure waveforms (even uncalibrated) through AI has garnered increased attention. In the current study we investigate the effect of peripheral blood pressure measurements' (i) location, (ii) calibration and (iii) injected additive noise on the performance of AI-based CO estimation. A large previously generated virtual cohort of n = 3818 subjects with varied hemodynamic profiles served as data bank for arterial pulse waves and reference CO values. Two-layered convolutional neural networks (CNN) yielded CO estimates based on entire pressure traces from the radial, superficial temporal and common carotid arteries. The predictive ability of the CNN models was comparable across arterial locations (r ≥ 0.97, nRMSE ≤ 4.4%) and only slightly compromised following pressure signal normalization from 0 to 1 (r ≥ 0.93, nRMSE ≤ 7.8%). Following noise injection, model performance was preserved (r ≥ 0.94, nRMSE ≤ 6.6%) yet became more sensitive to loss of calibration (r ≥ 0.78, nRMSE ≤ 12.2%). Our study highlights the interchangeability of potential blood pressure measurement locations in the quest for pressure-based CO estimation.
No takes yet. Share an insight, caveat, or question.
Aslanidou et al. (2025) studied Hemodynamic monitoring (n=3,818). Convolutional neural network (CNN) based cardiac output estimation vs. Reference ground truth cardiac output was evaluated on Predictive accuracy of cardiac output estimation (Pearson's r and nRMSE) (r ≥ 0.97, nRMSE ≤ 4.4%). Convolutional neural networks accurately estimated cardiac output from peripheral pressure waveforms across radial, temporal, and carotid arteries with comparable predictive ability (r ≥ 0.97, nRMSE ≤ 4.4%).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: