Clustering patient length of stay using mixtures of Gaussian models and phase type distributions

Author

Garg, Lalit ; Mcclean, Sally ; Meenan, Brian ; El-Darzi, Elia ; Millard, Peter

Author_Institution

Sch. of Comput. & Inf. Eng., Univ. of Ulster, Coleraine, UK

fYear

2009

fDate

2-5 Aug. 2009

Firstpage

1

Lastpage

7

Abstract

Gaussian mixture distributions and Coxian phase type distributions have been popular choices model based clustering of patients´ length of stay data. This paper compares these models and presents an idea for a mixture distribution comprising of components of both of the above distributions. Also a mixed distribution survival tree is presented. A stroke dataset available from the English Hospital Episode Statistics database is used as a running example.

Keywords

Gaussian distribution; medical administrative data processing; medical computing; Coxian phase type distributions; English Hospital Episode Statistics database; Gaussian mixture distributions; Gaussian models; mixed distribution survival tree; patient stay length clustering; phase type distributions; stroke dataset; Aging; Computer science; Data engineering; Databases; Distributed computing; Hospitals; Probability density function; Probability distribution; Statistical distributions; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 2009. CBMS 2009. 22nd IEEE International Symposium on

Conference_Location

Albuquerque, NM

ISSN

1063-7125

Print_ISBN

978-1-4244-4879-1

Electronic_ISBN

1063-7125

Type

conf

DOI

10.1109/CBMS.2009.5255245

Filename

5255245