Endpoints
SimulResp quality was evaluated on accuracy, robustness, repeatability and reproducibility. Accuracy was evaluated by the ability of SimulResp to produce physiological values of a healthy child within the normal range (pH 7.40 +/- 0.5; PaCO2 40 +/- 5 mmHg, PaO2 90 +/- 10 mmHg; SaO2 97% +/- 3%) when simulated fictive subjects and reference values when replicated clinical situations. Robustness, defined as the ability of the SimulResp prediction to remain stable within time when the conditions remained stable, was evaluated by comparing the blood gas values of each fictive patient at a VPCE of 30 minutes, 3 and 24 hours. Repeatability, defined as the ability of the SimulResp prediction to remain equal when the simulation is repeated within the same conditions (the same method, in the same operator with the same equipment within short intervals of time), was evaluated by comparing each blood gas values of each simulation for the same patient at a VPCE of 24 hours. Reproducibility, defined as the ability of the SimulResp prediction to remain equal when the simulation is repeated for the same patient but within different conditions (the same method but by a different operator and equipment) was evaluated by comparing simulation ran by OF and DB for the same patient at a VPCE of 24 hours.