Sequential pattern mining and classification of patient path
Nicolas Jay, Gilles Herengt, Éliane Albuisson, François Kohler, Amedeo Napoli · 2004
The purpose of the French DRG’s information system is to describe hospital activity by focusing on hospital stays. However, certain types of healthcare should be analysed as a temporal process covering multiple hospital stays. We propose two data-mining methods for patient path analysis across multiple healthcare institution : sequential pattern mining and formal concept analysis. Our objective is to discover, to classify and to visualize frequent patterns among patient path. Results: Our work shows the feasibility of a new approach to analyse temporal symbolic data in the field of health information systems.