Control of Respiratory Mechanics with Artificial Neural Networks

Airway pressure control of respiratory mechanics is crucial for ventilated patients. However, respiratory mechanics are nonlinear and are varying considerably amongst individual patients. In addition nonlinear interactions of a number of controls such as PEEP, Vt,fl02 - just to name a few - complicate the situation for the respiratory therapist on intensive care units. In this paper an alternative approach to traditional control methods - a neural network predictive controller - is proposed to establish an adaptive control of the airway pressure according to the individual features of a mechanically ventilated patient. The experimental results show that this approach can make the ventilator output follow the command pressure accurately as well as successfully identify the individual nonlinear respiratory mechanics of severely sick patients.Control of Respiratory Mechanics with Artificial Neural Networks Hui Zhu College of Mechanical & Electric Eng.

[1]  John G. Eyles,et al.  Estimating Respiratory Mechanical Parameters in Parallel Compartment Models , 1981, IEEE Transactions on Biomedical Engineering.

[2]  C. Carvalho,et al.  Effect of a protective-ventilation strategy on mortality in the acute respiratory distress syndrome. , 1998, The New England journal of medicine.

[3]  Martin T. Hagan,et al.  Neural networks for control , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[4]  P. Barbini,et al.  Estimating respiratory mechanical parameters of ventilated patients: a critical study in the routine intensive-care unit , 1994, Medical and Biological Engineering and Computing.

[5]  A. Mercat,et al.  Clinical review: Bedside assessment of alveolar recruitment , 2003, Critical care.

[6]  Sebastian Thrun,et al.  Planning with an Adaptive World Model , 1990, NIPS.

[7]  Knut Möller,et al.  Dynamic versus static respiratory mechanics in acute lung injury and acute respiratory distress syndrome , 2006, Critical care medicine.

[8]  W. Weyland,et al.  Improved determination of static compliance by automated single volume steps in ventilated patients , 2005, Intensive Care Medicine.

[9]  P. J. Haley,et al.  Neural generalized predictive control , 1996, Proceedings of the 1996 IEEE International Symposium on Intelligent Control.

[10]  Arthur S Slutsky,et al.  Pressure–Time Curve Predicts Minimally Injurious Ventilatory Strategy in an Isolated Rat Lung Model , 2000, Anesthesiology.

[11]  M Lichtwarck-Aschoff,et al.  Determination of volume-dependent respiratory system mechanics in mechanically ventilated patients using the new SLICE method. , 1994, Technology and health care : official journal of the European Society for Engineering and Medicine.

[12]  G Avanzolini,et al.  Comments on "Estimating respiratory mechanical parameters in parallel compartment models". , 1982, IEEE transactions on bio-medical engineering.

[13]  R. Murray-Smith,et al.  Neural networks for modelling and control of a non-linear dynamic system , 1992, Proceedings of the 1992 IEEE International Symposium on Intelligent Control.