An Incremental EM-based Learning Approach for On-Line Prediction of Hospital Resource Utilization

Ng, S. K., McLachlan, G. J. and Lee, A. H. (2006) An Incremental EM-based Learning Approach for On-Line Prediction of Hospital Resource Utilization. Artificial Intelligence In Medicine, 36 3: 257-267.


Author Ng, S. K.
McLachlan, G. J.
Lee, A. H.
Title An Incremental EM-based Learning Approach for On-Line Prediction of Hospital Resource Utilization
Journal name Artificial Intelligence In Medicine   Check publisher's open access policy
ISSN 0933-3657
0933-3657
Publication date 2006
Sub-type Article (original research)
DOI 10.1016/j.artmed.2005.07.003
Volume 36
Issue 3
Start page 257
End page 267
Total pages 11
Editor K. P. Adlassnig
Place of publication Amsterdam
Publisher Elsevier Science Bv
Collection year 2006
Language eng
Subject C1
230204 Applied Statistics
270201 Gene Expression
321011 Medical Genetics
780101 Mathematical sciences
780105 Biological sciences
730305 Diagnostic methods
010401 Applied Statistics
Abstract Objective: Inpatient length of stay (LOS) is an important measure of hospital activity, health care resource consumption, and patient acuity. This research work aims at developing an incremental expectation maximization (EM) based learning approach on mixture of experts (ME) system for on-line prediction of LOS. The use of a batchmode learning process in most existing artificial neural networks to predict LOS is unrealistic, as the data become available over time and their pattern change dynamically. In contrast, an on-line process is capable of providing an output whenever a new datum becomes available. This on-the-spot information is therefore more useful and practical for making decisions, especially when one deals with a tremendous amount of data. Methods and material: The proposed approach is illustrated using a real example of gastroenteritis LOS data. The data set was extracted from a retrospective cohort study on all infants born in 1995-1997 and their subsequent admissions for gastroenteritis. The total number of admissions in this data set was n = 692. Linked hospitalization records of the cohort were retrieved retrospectively to derive the outcome measure, patient demographics, and associated co-morbidities information. A comparative study of the incremental learning and the batch-mode learning algorithms is considered. The performances of the learning algorithms are compared based on the mean absolute difference (MAD) between the predictions and the actual LOS, and the proportion of predictions with MAD < 1 day (Prop(MAD < 1)). The significance of the comparison is assessed through a regression analysis. Results: The incremental learning algorithm provides better on-line prediction of LOS when the system has gained sufficient training from more examples (MAD = 1.77 days and Prop(MAD < 1) = 54.3%), compared to that using the batch-mode learning. The regression analysis indicates a significant decrease of MAD (p-value = 0.063) and a significant (p-value = 0.044) increase of Prop(MAD <= 1) with the incremental learning algorithm. Conclusions: The incrementat learning feature and the self-adaptive model-selection ability of the ME network enhance its effective adaptation to non-stationary LOS data. It is demonstrated that the incremental learning algorithm outperforms the batchmode algorithm in the on-tine prediction of LOS. (c) 2005 Elsevier B.V. All rights reserved.
Keyword Computer Science, Artificial Intelligence
Engineering, Biomedical
Medical Informatics
Em Algorithm
Mixture Of Experts
Incremental Update
Length Of Stay
Machine Learning Algorithm
On-line Prediction
Artificial Neural-network
Mixtures-of-experts
Recurrent Gastroenteritis
Hierarchical Mixtures
Maximum-likelihood
Western-australia
Incomplete Data
Ecm Algorithm
Model
Length
Q-Index Code C1

Document type: Journal Article
Sub-type: Article (original research)
Collections: Excellence in Research Australia (ERA) - Collection
2007 Higher Education Research Data Collection
School of Medicine Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 8 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 10 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Access Statistics: 100 Abstract Views  -  Detailed Statistics
Created: Wed, 15 Aug 2007, 08:24:48 EST