Beat-to-beat cardiac output inference using heart sounds

Cardiac output (CO) change is the primary compensatory mechanism that responds to oxygenation demand. Its continuous monitoring has great potential for the diagnosis and management of cardiovascular diseases, both in hospital as well as in ambulatory settings. However, CO measurements are currently limited to hospital settings only. In this paper, we present an extension of the model proposed by Finkelstein for beat-to-beat CO assessment. We use a nonlinear model consisting of a two-layer feed-forward artificial neural network. In addition to demographic (body surface area and age) and physiological parameters (HR), surrogates of contractility, afterload and mean arterial pressure based on systolic time intervals (STIs), estimated from echocardiography and heart sounds are used as inputs to our models. The results showed that the proposed models — with echocardiography as reference — produce better estimations of stroke volume/CO than the Finkelstein model (12.83±10.66 ml vs 7.23±6.6 ml), as well as higher correlation (0.46 vs 0.82).

[1]  A. Weissler,et al.  Systolic Time Intervals in Heart Failure in Man , 1968, Circulation.

[2]  X. Aubert,et al.  Is pulse transit time a good indicator of blood pressure changes during short physical exercise in a young population? , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[3]  J Conway,et al.  Baroreflex control of stroke volume in man: an effect mediated by the vagus. , 1992, The Journal of physiology.

[4]  Sabino Scolletta,et al.  Cardiac output monitoring by pressure recording analytical method in cardiac surgery. , 2004, European journal of cardio-thoracic surgery : official journal of the European Association for Cardio-thoracic Surgery.

[5]  R. Klabunde.  Cardiovascular Physiology Concepts , 2021 .

[6]  J. Muehlsteff,et al.  Comparison of systolic time interval measurement modalities for portable devices , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[7]  Validation of the USCOM-1A cardiac output monitor in hemodynamic unstable intensive care patients , 2006 .

[8]  R. Stewart,et al.  Influence of heart rate on stroke volume variability in atrial fibrillation in patients with normal and impaired left ventricular function. , 1998, The American journal of cardiology.

[9]  L. Critchley,et al.  A Meta-Analysis of Studies Using Bias and Precision Statistics to Compare Cardiac Output Measurement Techniques , 1999, Journal of Clinical Monitoring and Computing.

[10]  Rui Pedro Paiva,et al.  Assessing Systolic Time-Intervals from Heart Sound: A Feasibility Study , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  Marston Band,et al.  A method and apparatus for measuring the cardiac output , 1997 .

[12]  S. Gottlieb,et al.  Impedance cardiography: More questions than answers , 2006, Current cardiology reports.

[13]  C. Leier,et al.  Effect of afterload on left ventricular performance in experimental animals. Comparison of the pre-ejection period and other indices of left ventricular contractility. , 1982, Journal of medicine.

[14]  R. Jansen,et al.  Finapres arterial pulse wave analysis with Modelflow is not a reliable non-invasive method for assessment of cardiac output. , 2002, Clinical science.

[15]  J. Muehlsteff,et al.  Assessing PEP and LVET from heart sounds: Algorithms and evaluation , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  J. Alfie,et al.  Contribution of stroke volume to the change in pulse pressure pattern with age. , 1999, Hypertension.

[17]  D. Morel,et al.  Pre-ejection period to estimate cardiac preload dependency in mechanically ventilated pigs submitted to severe hemorrhagic shock. , 2011, The Journal of trauma.

[18]  J. Dawson,et al.  Cardiac output monitoring: basic science and clinical application , 2008, Anaesthesia.