Application of adaptive fuzzy controllers for the automation of medical devices

This paper describes an adaptive fuzzy control algorithm that may be used for the automation of medical devices. The automation system consists of a set of controllers containing the expertise of the physician and a main fuzzy controller that creates new rules based on this knowledge plus additional information about the patient. An adaptive mechanism evaluates the performance of the controller by using reference models and modifies its rules when needed. As a test case the automation of an extra-corporeal support system is presented, where a centrifugal pump speed is adjusted based on desired pressures and flow values.