A framework for intelligent visualization of multiple time-oriented medical records.

Management of patients, especially chronic patients, requires presentation and processing of very large amounts of time-oriented clinical data. Using regular means such as text or tables is often ineffective, thus we propose to use the visual presentation of the information in decision support, especially in the medical domain. Displaying only raw data is not sufficient, because it still requires the user to derive meaningful conclusions from large amount of data. In order to support the computation process, we provide automated mechanisms for temporal abstraction. These mechanisms perform derivation of context-specific, interval-based abstract concepts from raw time-stamped clinical data, by using a domain-specific knowledge base. Then, these abstractions can be visualized and explored. In addition, in many cases (e.g. when comparing the effect of new drugs on various groups of patients) a view of multiple records is more effective than a view of each indi-vidual record separately. We have designed and implemented a system called VISITORS (VisualizatIon of Time-Oriented RecordS) which includes several tools for intelligent visualization and exploration of raw data and abstracted concepts for multiple patient records.