Heart-lung interactions measured by electrical impedance tomography

Objective: The clinical value of stroke volume variations to assess intravascular fluid status in critically ill patients is well known. Electrical impedance tomography is a noninvasive monitoring technology that has been primarily used to assess ventilation. We investigated the potential of electrical impedance tomography to measure left ventricular stroke volume variation as an expression of heart-lung interactions. The objective of this study was thus to determine in a set of different hemodynamic conditions whether stroke volume variation measured by electrical impedance tomography correlates with those derived from an aortic ultrasonic flow probe and arterial pulse contour analysis. Design: Prospective animal study. Setting: University animal research laboratory. Subjects: Domestic pigs, 29-50 kg. Interventions: A wide range of hemodynamic conditions were induced by mechanical ventilation at different levels of positive end-expiratory pressure (0-15 cm H2O) and with tidal volumes of 8 and 16 mL/kg of body weight and by hypovolemia due to blood withdrawal with subsequent retransfusion followed by infusions of hydroxyethyl starch. Measurements and Main Results: In eight pigs, aortic stroke volume variations measured by electrical impedance tomography were measured and compared to those derived from an aortic ultrasonic flow probe and from arterial pulse contour analysis. Data for four animals were used to develop and train a novel frequency-domain electrical impedance tomography analysis algorithm, while data for the remaining four were used to test the performance of the novel methodology. Correlation of stroke volume variation measured by electrical impedance tomography and that derived from an aortic ultrasonic flow probe was significant (r(2) = 0.69; p<.001), as was the correlation between stroke volume variation measured by electrical impedance tomography and that derived from arterial pulse contour analysis (r(2) = 0.73; p<.001). Correlation of stroke volume variation derived from an aortic ultrasonic flow probe and that derived from arterial pulse contour analysis was significant too (r(2) = 0.82; p<.001). Bland-Altman analysis comparing stroke volume variation measured by electrical impedance tomography and that derived from an aortic ultrasonic flow probe revealed an overall bias of 1.87% and limits of agreement of +/- 7.02%; when comparing stroke volume variation measured by electrical impedance tomography and that derived from arterial pulse contour analysis, the overall bias was 0.49% and the limits of agreement were +/- 5.85%. Conclusion: Stroke volume variation measured by electrical impedance tomography correlated with both the gold standard of direct aortic blood flow measurements of stroke volume variation and pulse contour analysis, marking an important step toward a completely noninvasive monitoring of heart-lung interactions. (Crit Care Med 2011; 39: 2173-2176)