View Item 

Clustering Patient Medical Records via Sparse Subspace Representation

Access Status
Fulltext not available
Authors
Date
2013
Type
Conference Paper

Metadata
Show full item record
Citation
Budhaditya, Saha and Phung, Dinh and Pham, Duc-Son and Venkatesh, Svetha. 2013. Clustering Patient Medical Records via Sparse Subspace Representation, in Pei, J., Tseng, V.S., Cao, L., Motoda, H., Xu, G. (ed), Proceedings of the 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Apr 14-17 2013, pp. 123-134. Gold Coast, Qld: UTS: Advanced Analytics Institute.
Source Title
Advances in Knowledge Discovery and Data Mining, Lecture Notes on Computer Science Volume 7819
Source Conference
17th Pacific-Asia Conference on Knowledge Discovery and Data Mining
DOI
ISBN
URI
Collection
Abstract

The health industry is facing increasing challenge with “big data” as traditional methods fail to manage the scale and complexity. This paper examines clustering of patient records for chronic diseases to facilitate a better construction of care plans. We solve this problem under the framework of subspace clustering. Our novel contribution lies in the exploitation of sparse representation to discover subspaces automatically and a domain-specific construction of weighting matrices for patient records. We show the new formulation is readily solved by extending existing 1 -regularized optimization algorithms. Using a cohort of both diabetes and stroke data we show that we outperform existing benchmark clustering techniques in the literature.