Don't care values in induction.

Inductive learning algorithms are powerful tools for the extraction of knowledge from data. Their success in medical domains is well-known. In medical diagnosis domains and generally in real-world applications among other problems, inductive learning algorithms have to deal with unknown values. In most cases unknown values are treated as missing ones, i.e. unknown values which are related to the class of training examples, but are missing due to lack of measurements. In this paper we address the problem of don't care values, which are unknown, because they are irrelevant to the class of the examples. The distinction of don't care values and missing ones is important in medical domains. With this distinction the experts are able to relate each diagnosis to the appropriate subset of attributes. We present techniques for dealing efficiently with don't care values in the induction of decision trees. Furthermore, we examine the importance of the distinction between missing and don't care values and we investigate the existence of don't care values instead of missing ones, in medical and non-medical real-world datasets.

The CARDIO-LOGOS system for ECG training and diagnosis.

A new approach in ECG training is presented. The overall approach is based on a combination of the "page-turning architecture", the "reference model" and AI techniques. A thorough analysis of the training requirements in this field has been carried out; the results determined the educational scenarios and the associated evaluation sessions. The system (CARDIO-LOGOS) is intended to be used mainly by internal medicine physicians and general practitioners, as well as by medical students. The layered structure of the whole CBT application together with the advanced learning strategies and the interactive multimedia technology offer a flexible environment that encourages experimentation and supports individualised training for a wide variety of users.