Knowledge discovery from distributed clinical data sources: the era for internet-based epidemiology

A methodology and the operational framework for knowledge discovery from distributed and heterogeneous clinical data sources are presented. The methodology follows a multi-phase process for the integration, homogenization and intelligent processing of the distributed and heterogeneous data. Its realization is based on the coupling of multidisciplinary technologies ranging from, CORBA-based seamless access to distributed data, to semantic data homogenization operations, and to advanced DTD/XML operations. These operations, coupled with advanced and effective data representation models forms a framework in which effective knowledge discovery (KDD) operations are performed. The fundamental contribution of our work is the incorporation and customization of association rule mining (ARM) operations on top of appropriately generated XML documents. Based on the argument that future databases will use XML-like structures in order to store and retrieve data then, our work presents a promising direction towards internet-based epidemiology as realized by the respective knowledge-discovery from distributed clinical data sources operations.