Improving Medical Decision Making by Self Organizing Intelligent Systems

Early and accurate diagnosing of various diseases has proved to be of vital importance in many health care processes. In recent years intelligent systems have been often used for decision support and classification in many scientific and engineering disciplines including health care. However, in many cases the proposed treatment, prediction or diagnose can differ from one intelligent system to another, similar to the real world where different medical specialists may have different opinions. Indeed, in real world specialists' opinions complement one another and when integrated they usually form a better solution. Our novel idea presented in this paper is to mimic this real world situation in the manner to merge different opinions generated by different intelligent systems using the self organizing abilities of cellular automata. We empirically show that classification cellular automata combining many various methods for classifier construction eventually outperforms single classifiers and conventional integration methods in terms of accuracy and class accuracy.