Mining administrative data to predict falls in the elderly population

Authors:
Arian Hosseinzadeh;Masoumeh Izadi;Doina Precup;David Buckeridge
Affiliations:
School of Computer Science, McGill University, Canada;Health Informatics Research Group, McGill University, Canada;School of Computer Science, McGill University, Canada;Health Informatics Research Group, McGill University, Canada
Venue:
Canadian AI'12 Proceedings of the 25th Canadian conference on Advances in Artificial Intelligence
Year:
2012

Citing 1
Cited 0

A decision-theoretic generalization of on-line learning and an application to boosting

Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995

Quantified Score

Hi-index	0.00

Visualization

Abstract

Falls among the elderly are very common and have a great impact on the health services and the community, as well as on individuals. Many medical studies have focused on the possible risk factors associated with falling in the elderly population, but predicting who is at risk for falling is still an open research question. In this paper, we investigate the use of supervised learning methods for predicting falls in individuals based on the administrative data on their medication use. The data is obtained from a cohort of elderly people in the province of Quebec, and our preliminary empirical investigation yields promising results.