By Topic

A clinical description of the IMPROVE data library

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Nieminen, K. ; Dept. of Anaesthesiology & Intensive Care, Kuopio Univ. Hosp., Finland ; Langford, R.M. ; Morgan, C.J. ; Takala, J.
more authors

IMPROVE (IMPROVing control of patient status in critical carE) was a concerted action project of the Biomed-1 programme of the European Union. Its main goal was to develop methods of biosignal processing and interpretation in order to detect disorders of oxygen delivery to vital tissues early enough for effective treatment to improve patient outcome. As the first step, a prospective survey of the incidence of potentially dangerous disorders of oxygen delivery was carried out in the intensive-care units (ICUs) of three of the participating hospitals. The four most common and significant types of disorders were defined (hypovolaemia, cardiac failure, high blood-flow state and oxygen-content-related problems) and their incidence measured and compared among the three sites. In the second phase, a data library (DL) was obtained from episodes of 24 hours of intensive observation in patients at risk of developing one of the four most frequent disorders observed in the first survey. This data collection was performed in the Department of Intensive Care, Kuopio University Hospital, Finland. The objective of the IMPROVE project was that the DL should include data from 60 patient days, that it should include evidence of the evolution and resolution of the disorders, and that it should be unique in as much as the physiological data trends would be put in clear clinical context by a comprehensive process of clinical annotation. This annotation was seen as the key to making the DL suitable for biosignal processing and interpretation tasks, and to facilitate the development of diagnostic trend analysis tools.

Published in:

Engineering in Medicine and Biology Magazine, IEEE  (Volume:16 ,  Issue: 6 )