Interoperability of Data and Knowledge in Distributed Health Care Systems

In this paper we propose a knowledge management framework for distributed health care systems consisting of data- and knowledge-bases that contain patient data and mined knowledge from health care institutions. The framework takes advantage of data mining techniques, enabling technologies and standards to provide decision making support for the health care personnel. The application areas of the new framework range from clinical care to administrative decision support. With the guidance of the health care researchers the available patient data is mined off-line to extract meaningful knowledge from medical data which can be shared with other institutions through XML-based documents (known as PMML) to achieve knowledge interoperability among different heterogeneous health care systems. Data interoperability is achieved through an XML-based clinical data representation standards (HL7 CDA) that is used to encode patient data. A clinical guideline and a logic module will receive inputs form both PMML and CDA documents to enable decision making at a higher level based on patient data and the mined knowledge. We also applied the proposed framework on three clinical case studies.