AN ACTIVE MEDICAL INFORMATION SYSTEM
FOR INFORMATION RETRIEVAL, DISCOVERY AND FUSION
Shi-Kuo Chang+, Daniel Graupe*, Keiko Hasegawa+ and Hubert Kordylewski*
+Visual Computer Laboratory, Department of Computer Science
University of Pittsburgh, Pittsburgh, PA 15260 USA
Email: [chang, keiko]@cs.pitt.edu
and
* Department of Electrical Engineering and Computer Science
University of Illinois, Chicago, IL 60680 USA
Email: [graupe, hkordyle]@eecs.uic.edu
Abstract
To accomplish the retrieval, discovery and fusion of medical information from diverse sources,
an active medical information system capable of
retrieving, processing and filtering medical information, checking for
semantic consistency, and structuring the relevant information for distribution is needed.
We describe a framework for the human- and
system-directed retrieval, discovery and fusion of medical information, which
is based upon the observation that a significant
event often manifests itself in different media over time.
Therefore if we can index such manifestations and dynamically
link them, then we can check for consistency and discover important and relevant medical information.
This dynamic indexing technique is based upon
the theory of active index.
A powerful newly developed artificial neural network is used for
the discovery of significant events.
An experimental systemis implemented for further empirical research. A
prototyping
environment is available to prototype similar systems.
