By Topic

Data mining in healthcare information systems: case study of a veterans' administration spinal cord injury population

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

3 Author(s)
Kraft, M.R. ; Decision Support Clinical Coordinator, VA Hines Hosp., IL, USA ; Desouza, K. ; Androwich, I.

In the following paper the process of knowledge generation from the Veterans Administration healthcare information system is explored. This inquiry is concerned with predicting length of stay of a subset of the total patient population, specifically those with spinal cord injuries (SCI). Although SCI patients do not present large numbers, they are outliers in the healthcare system due to extended hospital stays and high costs for treatment. Predicting length of stay can increase efficiencies and effectiveness in resource allocation thus lowering cost. The following research is the first of its kind to use nursing diagnosis and neural networks to predict length of stay. Background material on SCI and the knowledge discovery process is introduced. The entire data mining process is described beginning with data gathering followed by cleaning, aggregation, and integration. Issues faced while conducting the research are discussed. Results of artificial neural networks used to predict length of stay are presented.

Published in:

System Sciences, 2003. Proceedings of the 36th Annual Hawaii International Conference on

Date of Conference:

6-9 Jan. 2003