The Natural Induction System AQ21 and its Application to Data Describing Patients with Metabolic Syndrome: Initial Results

This paper briefly describes the AQ21 learning system that implements a simple form of natural induction, an approach to learning that generates hypotheses in forms resembling natural language descriptions, and by that easy to understand and interpret. The system was applied to the analysis of aggregated data obtained from non-invasive tests performed on different groups of patients with metabolic syndrome. The discovered patterns were very simple and were evaluated by an expert as potentially medically significant.