Software implementation of fuzzy decision making in determining the severity of respiratory distress

In the paper a software implementation of fuzzy decision-making in medicine is described. Known models of fuzzy multi-criteria decision making are applied in two situations: the first, with all features of the same importance and without interaction between criteria, and the second, with interacting criteria. The practical usage of both approaches is shown in a medical application in determining the severity of respiratory distress of a patient in an intensive care unit, which is of extreme clinical relevance. In the first case the Bellman-Zadehpsilas approach is used, and in the second case, the Choquet integral is used. Proposed models are used in developed prototype software, implemented in Java and described in the paper. It provides possible decisions for available patient symptoms, and it gathers data about adequacy of the first and the second approach in real situations. The results are given, and the directions for possible further work are pointed out.