Use this URL to cite or link to this record in EThOS:
Title: Predicting patient length of stay and outcome using discrete conditional survival methods
Author: Payne, Kieran
ISNI:       0000 0004 2742 5439
Awarding Body: Queen's University Belfast
Current Institution: Queen's University Belfast
Date of Award: 2012
Availability of Full Text:
Full text unavailable from EThOS.
Please contact the current institution’s library for further details.
The health and social care service is increasingly being placed under pressure to facilitate the demands of an ageing population in a difficult economic climate .. The need for better planning and resource management through statistical modelling has never been greater. This thesis adds to the current research on modelling patient length of stay and outcome within hospital by further developing the family of discrete conditional survival models. A statistical technique, consisting of a conditional and process component, is used to model length of stay within hospital based on information known on first day of admission. The approach in this thesis categorises patients into cohorts with similar characteristics and based upon this classification, accurately predicts their length of stay in hospital. Three new techniques, classification trees, ADA boosting and random forests are introduced into the family of discrete conditional survival models. The use of Coxian phase-type distributions for representing length of stay is examined and optimised with the development of more efficient expressions of the probability density function. This is validated in application by modelling length of stay of geriatric patients in Northern Ireland hospitals. The structure of the resulting distributions are discussed and compared to previous research. The advances in the discrete conditional survival model are illustrated in a model developed as a tool for predicting infant length of stay within neonatal care. With the development of late onset sepsis, the model classifies infants as both high or low risk and depending upon the classification accurately models their corresponding length of stay. Performance measures are calculated for each model and the advantages of using the techniques considered and compared against standard methods. The approach not only accurately predicts outcome and length of stay but contributes to knowledge. Development and potential integration within a hospital environment are discussed as further work.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available