Decision trees and automatic learning in medical decision making

Decision support systems (DSS) have become increasingly important in medical applications, particularly when important decision must be made effectively and reliably. The best way to design a successful DSS is through the participative design, thereafter conceptual simple decision making models with the possibility of automating learning should be considered in the design phase and then implemented by conceptual simple paradigms. We present a cardiological decision support system, called RO/sup 2/SE (Computerised Prolapse Syndrome Determination, O/sup 2/ stands for object oriented implementation), based on decision tree approach and automatic learning, supporting the process of mitral valve prolapse determination. RO/sup 2/SE is implemented using object oriented visual programming language.