Logo des Repositoriums
 
Konferenzbeitrag

An integrated data management approach to manage health care data

Vorschaubild nicht verfügbar

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2011

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

Surgical Intensive Care Unit data management systems suffer from three problems: data and meta-data are spread out in different systems, there is a high rate of false positives, and data mining predictions are not presented in a timely manner to health care staff. These problems lead to missed opportunities for data analysis, alert fatigue and reactive, instead of proactive analysis. In this demo, and in contrast to current CEP efforts, we present a proof-of-concept, integrated engine that runs entirely within a single database system. The resulting novel and low cost event processing architecture uses features and components commercially available from Oracle Corporation. We demonstrate how multiple data from a realworld surgical intensive care unit (bed-side sensors and all other information available about the patients) are assimilated and queries, alarms, and rules are applied. The system is highly customizable: staff can point and click to create, edit and delete rules, compose personal rules (per patient, per doctor, per patientdoctor), and, while maintaining a hierarchy of rules, create rules that inherit and override previous rules. The system is also integrated with the data mining module, being able to offer predictions of high risk situations in real-time (e.g., predictions of cardiac arrests). Using simulated inputs, we show the complete system working, including writing and editing rules, triggering simple alerts, prediction of cardiac arrests, and visual explanation of predictions.

Beschreibung

Guerra, Diogo; Gawlick, Ute; Bizarro, Pedro; Gawlick, Dieter (2011): An integrated data management approach to manage health care data. Datenbanksysteme für Business, Technologie und Web (BTW). Bonn: Gesellschaft für Informatik e.V.. PISSN: 1617-5468. ISBN: 978-3-88579-274-1. pp. 596-605. Regular Research Papers. Kaiserslautern. 02.-04.03.2011

Schlagwörter

Zitierform

DOI

Tags