A retrieval system for the selection and statistical analysis of clinical data

Within the last years computer-aided clinical documentation has provided re searchers and administrators with very large volumes of data for research. User-friendly retrieval tools are needed when processing these clinical dat abases. Clinical researchers require applications by means of which steps i n selection and analysis can be performed in an iterative process. During t he deduction of statistical parameters from routinely collected data a numb er of problems occur that do not appear in the analysis of data gathered wi thin clinical studies. Unlike clinical studies, routine data have complex s tructures and must first be formatted and above all temporally synchronized . In this paper we will describe the medical retrieval system ArchiMed deve loped at the Vienna General Hospital. A main objective in the design of thi s system was to support a joint evaluation of data from clinical studies an d routinely collected data. The retrieval system comprises the main functio ns: Selection of Patients; Selection and Joining of Variables; and Statisti cal Analysis.