A Sequence Building Approach to Pattern Discovery in Medical Data

May 1998

Proceedings of the Eleventh International Florida Artificial Intelligence Research Society Conference (FLAIRS 1998)

Volume

Proceedings of the Eleventh International Florida Artificial Intelligence Research Society Conference (FLAIRS 1998)

All Papers

The goal of the research being reported is the discovery of useful concepts in temporal medical databses. In this paper, we present a sequence building approach, based on the Generalized Sequential Patterns (GSP) Algorithm (Srikant and Agrawal 1996), to discover temporal patterns in this type of data. We show that this pattern discovery is possible by normalizing continuous features in a way that allows meaningful comparisons between patients.