Non-exhaustive trace retrieval for managing stroke patients

Risultato della ricerca: Capitolo in libro/report/atti di convegnoContributo in volume (Capitolo o Saggio)peer review

Abstract

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.

Lingua originaleInglese
Titolo della pubblicazione ospiteSuccessful Case-Based Reasoning Applications-2
EditorStefania Montani, Lakhmi Jain
Pagine29-42
Numero di pagine14
DOI
Stato di pubblicazionePubblicato - 2014

Serie di pubblicazioni

NomeStudies in Computational Intelligence
Volume494
ISSN (stampa)1860-949X

Fingerprint

Entra nei temi di ricerca di 'Non-exhaustive trace retrieval for managing stroke patients'. Insieme formano una fingerprint unica.

Cita questo