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

Lalit Garg, Sally McClean, BJ Meenan, Elia El-Darzi, Peter Millard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

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.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages1-7
Number of pages7
DOIs
Publication statusPublished - 2009
Event22nd IEEE International Symposium on Computer-Based Medical Systems, 2009. CBMS 2009. - Albuquerque, NM, USA
Duration: 1 Jan 2009 → …

Conference

Conference22nd IEEE International Symposium on Computer-Based Medical Systems, 2009. CBMS 2009.
Period1/01/09 → …

Fingerprint

Statistics

Cite this

Garg, Lalit ; McClean, Sally ; Meenan, BJ ; El-Darzi, Elia ; Millard, Peter. / Clustering patient length of stay using mixtures of Gaussian models and phase type distributions. Unknown Host Publication. 2009. pp. 1-7
@inproceedings{a9b4dcc68acd409280a97d4a260fb678,
title = "Clustering patient length of stay using mixtures of Gaussian models and phase type distributions",
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.",
author = "Lalit Garg and Sally McClean and BJ Meenan and Elia El-Darzi and Peter Millard",
year = "2009",
doi = "10.1109/CBMS.2009.5255245",
language = "English",
isbn = "978-1-4244-4879-1",
pages = "1--7",
booktitle = "Unknown Host Publication",

}

Garg, L, McClean, S, Meenan, BJ, El-Darzi, E & Millard, P 2009, Clustering patient length of stay using mixtures of Gaussian models and phase type distributions. in Unknown Host Publication. pp. 1-7, 22nd IEEE International Symposium on Computer-Based Medical Systems, 2009. CBMS 2009., 1/01/09. https://doi.org/10.1109/CBMS.2009.5255245

Clustering patient length of stay using mixtures of Gaussian models and phase type distributions. / Garg, Lalit; McClean, Sally; Meenan, BJ; El-Darzi, Elia; Millard, Peter.

Unknown Host Publication. 2009. p. 1-7.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Clustering patient length of stay using mixtures of Gaussian models and phase type distributions

AU - Garg, Lalit

AU - McClean, Sally

AU - Meenan, BJ

AU - El-Darzi, Elia

AU - Millard, Peter

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

U2 - 10.1109/CBMS.2009.5255245

DO - 10.1109/CBMS.2009.5255245

M3 - Conference contribution

SN - 978-1-4244-4879-1

SP - 1

EP - 7

BT - Unknown Host Publication

ER -