Information Warehouse for Medical Research

Abstract

Data warehousing imposes itself as an attractive solution for centralizing and analyzing high quality data. In the medical research field, this technology can be used to validate assumptions and to discover trends on large amount of patient data. However, like other scientific complex data, medical data and especially raw sensor data need to be processed before becoming interpretable. The selection of the process mode is a key issue in the physician’s reasoning. In our study, we propose a solution to gather data and processes into a single information warehouse. Our solution provides features for loading, modeling and querying the information warehouse. Stored data are multidimensional data (patient identity, therapeutic data...), raw sensor data (electrocardiogram, X-ray...) and processes. A prototype has been implemented and is illustrated in the cardiology domain to finalise processes in order to detect heart arrhythmia and acute myocardial ischemia that may lead to sudden cardiac death.