A novel method of trans-esophageal Doppler cardiac output monitoring utilizing peripheral arterial pulse contour with/without machine learning approach.

Transesophageal Doppler (TED) velocity in the descending thoracic aorta (DA) is used to track changes in cardiac output (CO). However, CO tracking by this method is hampered by substantial change in aortic cross-sectional area (CSA) or proportionality between blood flow to the upper and lower body. To overcome this, we have developed a new method of TED CO monitoring. In this method, TED signal is obtained primarily from the aortic arch (AA). Using AA velocity signal, CO (COAA-CSA) is estimated by compensating changes in the aortic CSA with peripheral arterial pulse contour. When AA cannot be displayed properly or when the quality of AA velocity signal is unacceptable, our method estimates CO (CODA-ML) from DA velocity signal first by compensating changes in the aortic CSA, and by compensating changes in the blood flow proportionality through a machine learning of the relation between the CSA-adjusted CO and a reference CO (COref). In 12 anesthetized dogs, we compared COAA-CSA and CODA-ML with COref measured by an ascending aortic flow probe under diverse hemodynamic conditions (COref changed from 723 to 7316 ml·min-1). Between COAA-CSA and COref, concordance rate in the four-quadrant plot analysis was 96%, while angular concordance rate in the polar plot analysis was 91%. Between CODA-ML and COref, concordance rate was 93% and angular concordance rate was 94%. Both COAA-CSA and CODA-ML demonstrated "good to marginal" tracking ability of COref. In conclusion, our method may allow a robust and reliable tracking of CO during perioperative hemodynamic management.