Retrieving and inspecting traces that log medical processes execution can be a significant help in exception management, and is the first step towards a thorough analysis of the service provided by an health care organization. In this work, we report on extensive retrieval experiments, conducted on a database of 2000 real patient traces, collected at different stroke management units in the Lombardia region, Italy. In our approach, retrieval exploits a K-Nearest Neighbor technique, and relies on a distance definition able to explicitly take into account temporal information in traces-since in emergency medicine the role of time is central. Retrieval is also made faster by the application of non-exhaustive search procedures, that are described in the paper. © 2014 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Montani, S., & Leonardi, G. (2014). Successful Case-based Reasoning Applications-2. Studies in Computational Intelligence (Vol. 494, pp. 29–42). Retrieved from http://www.scopus.com/inward/record.url?eid=2-s2.0-84884196061&partnerID=tZOtx3y1
Mendeley helps you to discover research relevant for your work.