Automatic Acquisition of medical Knowledge from Data

Knowledge acquisition is a bottleneck in AI applications. Neural learning is a new perspective in knowledge acquisition. In our approach we have extended Kohonen's self-organizing feature maps (SOFM) by the U-matrix method for the discovery of structures resp. classes. We have developed a machine learning algorithm, called sig*, which automated extracts rules out of SOFM which are trained to classify high-dimensional data. sig * selects significant attributes and constructs appropriate conditions for them in order to characterize each class. sig * generates also differentiating rules, which distinguish classes from each other. The algorithm has been tested on many different data sets with promising results. The framework of using sig * integrated in a system which automated acquires knowledge from learned SOFM is also presented. 1