Skip to main content
  • Conference Abstract
  • Open access
  • Published:

2.7 Machine Learning on Central Hemodynamic Quantities Using Noninvasive Measurements: How Far Can We Go?



Transforming peripheral noninvasive measurements to obtain central hemodynamic quantities, such as cardiac output (CO) and central systolic blood pressure (cSBP), is a highly emerging field [1,2]. However, no holistic investigation has been performed to assess the amount of information contained in each peripheral measurement for the prediction of central values. This can be attributed to the inherent difficulty of creating a complete and accurate database; mainly due to the invasive nature of the gold standard techniques [3,4].


To meet this need, we exploit synthetic data from a previously validated cardiovascular model (CVm) [5]. Our study relies on peripheral quantities including brachial pressure, heart rate (HR), and pulse wave velocity (PWV) simulated by the CVm. A Random Forest model was trained using 2744 synthetic instances and, subsequently, was tested against a subset of 800. Correlations and feature importances of the input parameters were reported (Figure 1).


Our results demonstrated that precise estimates of CO and cSBP were yielded with an RMSE of 0.39 L/min and 1.39 mmHg, respectively (Figures 2 and 3). Low biases were observed, namely 0.03 ± 0.39 L/min for CO and −0.08 ± 1.39 mmHg for cSBP. PWV, HR, and brachial pulse pressure were found to be the most correlated features with CO, whereas brachial SBP was plausibly shown to be the significant determinant of cSBP for our model (Figures 4 and 5).


These findings pave the way for better devising central hemodynamics’ predictions. In the future, our ultimate goal is to examine the sensitivity of cardiac parameters estimation (i.e., elastance) to noninvasive peripheral measurements.

Correlation matrix.

Scatterplot (A) and Bland-Altman plot (B) between predicted and reference CO values

Scatterplot (A) and Bland-Altman plot (B) between predicted and reference CO values.

Feature importances for CO prediction.

Feature importances for cSBP.


  1. Hope SA, Tay DB, Meredith IT, Cameron JD. Use of arterial transfer functions for the derivation of aortic waveform characteristics. J Hypertens 2003;21:1299–305.

    Google Scholar 

  2. Swamy G, Mukkamala R. Estimation of the aortic pressure waveform and beat-to-beat relative cardiac output changes from multiple peripheral artery pressure waveforms. IEEE Trans Biomed Eng 2008;55:1521–9.

    Google Scholar 

  3. Avolio A. Central aortic blood pressure and cardiovascular risk: a paradigm shift? Hypertension 2008;51:1470–1.

  4. Jansen JRC, Schreuder JJ, Mulier JP, Smith NT, Settels JJ, Wesseling KH. A comparison of cardiac output derived from the arterial pressure wave against thermodilution in cardiac surgery patients. Br J Anaesth 2001;87:212–22.

    Google Scholar 

  5. Reymond P, Merenda F, Perren F, Rüfenacht D, Stergiopulos N. Validation of a one-dimensional model of the systemic arterial tree. Am J Physiol Heart Circ Physiol 2009;297:H208–H22.

    Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Vasiliki Bikia.

Rights and permissions

This is an open access article distributed under the CC BY-NC 4.0 license (

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bikia, V., Pagoulatou, S. & Stergiopulos, N. 2.7 Machine Learning on Central Hemodynamic Quantities Using Noninvasive Measurements: How Far Can We Go?. Artery Res 25 (Suppl 1), S16–S18 (2019).

Download citation

  • Published:

  • Issue Date:

  • DOI: