Veno-arterial extracorporeal membrane oxygenation (V-A ECMO) is used as rescue therapy for severe cardiopulmonary failure. We tested whether the ratio of CO₂ elimination at the lung and the V-A ECMO (V̇co_2ECMO/V̇co_2Lung) would reflect the ratio of respective blood flows and could be used to estimate changes in pulmonary blood flow (Q̇_Lung), i.e., native cardiac output. Four healthy pigs were centrally cannulated for V-A ECMO. We measured blood flows with an ultrasonic flow probe. V̇co_2ECMO and V̇co_2Lung were calculated from sidestream capnographs under constant pulmonary ventilation during V-A ECMO weaning with changing sweep gas and/or V-A ECMO blood flow. If ventilation-to-perfusion ratio (V̇/Q̇) of V-A ECMO was not 1, the V̇co_2ECMO was normalized to V̇/Q̇ = 1 (V̇co_2ECMONorm). Changes in pulmonary blood flow were calculated using the relationship between changes in CO₂ elimination and V-A ECMO blood flow (Q̇_ECMO). Q̇_ECMO correlated strongly with V̇co_2ECMONorm (r² 0.95–0.99). Q̇_Lung correlated well with V̇co_2Lung (r² 0.65–0.89, P < = 0.002). Absolute Q̇_Lung could not be calculated in a nonsteady state. Calculated pulmonary blood flow changes had a bias of 76 (−266 to 418) mL/min and correlated with measured Q̇_Lung (r² 0.974–1.000, P = 0.1 to 0.006) for cumulative ECMO flow reductions. In conclusion, V̇co₂ of the lung correlated strongly with pulmonary blood flow. Our model could predict pulmonary blood flow changes within clinically acceptable margins of error. The prediction is made possible with normalization to a V̇/Q̇ of 1 for ECMO. This approach depends on measurements readily available and may allow immediate assessment of the cardiac output response.