Publications

Mining large clinical databases often includes exploration of temporal data. For example, in liver transplantation, where parameters are obtained from continuously monitored patients, a researcher might be interested in patients that exhibit an unusual pattern of potential complications of the transplanted organ, each following a typical pattern in time. Standard query languages like SQL are not well suited for this kind of research because of an insufficient time model. A very flexible approach is Knowledge-based Temporal Abstraction, which has been implemented in a number of proprietary systems. Here time-stamped data points are transformed into an interval-based representation that can utilize, e.g., Allen’s temporal relationships. For increased availability in clinical research, we extended the knowledge-based temporal abstraction framework by creating an open-source platform, SPOT. It supports the R statistical packages and knowledge representation standards (OWL, SWRL) using the open source Semantic Web tool Protégé-OWL.