In this article, a dynamic model of the cardio-respiratory system is developed, which uses an electrocardiogram (ECG) signal as input. Identification of two models of the Hammerstein − Wiener type is carried out, in order to obtain the mass flow of air in the respiratory process and the blood flow, starting from the ECG signal. These flows are coupled in turn with a phenomenological-based dynamic model that describes respiratory dynamics. From the developed model, it is possible to obtain as a result the concentrations of oxygen (O <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> ) and carbon dioxide (CO <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> ) in different parts of the body for different ECG signals.