Heuristic modeler: A multi-purpose evolutionary machine learning algorithm and its applications in medical data analysis

The application of machine learning techniques for discovering patterns in data is becoming more and more important not only in computer science in general, but also especially in medical data mining. Regression modeling problems are to be solved in this context as well as classification problems, and also time series analysis methods are expected to become more and more important. In this paper we describe a multi-purpose machine learning approach based on various evolutionary computation concepts that is applicable for several medical data mining aspects in evidence based medicine. We show how regression, classification and time series problems can be attacked using this algorithm, and we also propose a hybrid approach combining time series analysis with regression and classification aspects.