Monitoring under uncertainty in intensive care units (ICUs)

Medical informatics has changed tremendously over the past few decades, and changes in the approach to uncertainty are probably the most important advances in this field. The envisioned role of computer programs in health care is perhaps the most important. Uncertainty is the central, critical fact about medical reasoning. Particularly in the intensive care unit (ICU) environment, where decisions must often be made quickly, or that physicians will follow it rather than openly or surreptitiously limiting care on their own. This paper surveys the utilization of fuzzy logic on the basis of two medical applications. The first, an intelligent on-line monitoring program for the intensive care data of patients with Acute Respiratory Distress Syndrome (ARDS), so called FuzzyARDS which is using the concept of fuzzy automata, and the second is a fuzzy knowledge-based control system, FuzzyKBWean, which was established as a real-time application based on the use of a Patient Data Management System (PDMS) in an ICU. These two complex systems confirm that fuzzy logic is quite suitable for medical application in a per definition uncertainty environment as an ICU, because of its tolerance to some imprecision.