An Improved Blood Gas Intelligent Hybrid Model for Mechanically Ventilated Patients in the Intensive Care Unit

A. Wang, G. Panoutsos, M. Mahfouf, and G.H. Mills (UK)

Keywords

Ventilated patient model, blood gas, Neural-Fuzzy

Abstract

SOPAVent (Simulation of Patients under Artificial Ventilation) is a blood gas model for mechanically ventilated patients in intensive care units (ICU). A set of parameters is required before the model is able to predict the patient’s blood gases. Although most of the parameters required can be obtained from routine ICU measurements, some have to be estimated, such as shunt, relative dead space (Kd) and carbon dioxide production (VCO2), for such parameters measurements are not always available. In this paper, some recent work on improving the model parameter prediction and data collection is presented, with the aim of enabling the model to be used in routine ICU environments (i.e. be independent of any invasive measurements). Modifications include the development of a new data driven model for VCO2 prediction, the update of the current Kd model and shunt estimation method and finally the development of automatic data collection algorithms. Based on these improvements, the new SOPAVent model is validated against blood gas measurements from 12 patients under different ventilator settings and the results show that the new SOPAVent model performance is better compared to the previous model, hence providing more accurate and reliable predictions of blood gases.

Important Links:

Go Back