Computer-aided sequential diagnosis via combined and unified recognition algorithms

This paper deals with the sequential recognition of successive patient´s states when undergoing a therapeutic procedure. For this problem, the original concept of recognition is presented in which two kinds of information are available: the learning set (empirical data) and the set of expert rules (knowledge representation). Adopting the probabilistic model and assuming the first-order Markov dependence between patient´s states, the combined and unified diagnostic algorithms are derived. In the first algorithm the authors calculate approximated values of a posteriori probabilities of states from the both sets of data, in the second however, the learning set is transformed into the set of “artificial” expert rules. These algorithms have been applied to the computer-aided diagnosis of human acid-base balance states and results of classification accuracies are given