Abstract
In order to provide more ethical and objective measures of the likelihood of Intensive Care Unit (ICU) recovery, hospitals have turned increasingly to decision support system software packages, such as APACHE. However, these packages derive estimates from parametric techniques, such as Binary Logit Regression (BLR) in the APACHE case, and require the developer to specify in advance the functional relationships among variables in the model. Recent rapid advancements in computer software and hardware technology have encouraged researchers to use more computationally intensive, non-parametric techniques such as Neural Networks (NNs), which are purported to be better than parametric models in terms of prediction capabilities. The present study applies both methodologies to a sample of ICU patients and shows that the NN technique predicts mortality rates more correctly than BLR, and offers a promising non-parametric alternative to the parametric methodologies in hospital settings.
| Original language | English |
|---|---|
| Pages (from-to) | 221-227 |
| Number of pages | 7 |
| Journal | Health Care Management Science |
| Volume | 5 |
| Issue number | 3 |
| DOIs | |
| State | Published - 2002 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Business, Management and Accounting(all)
- Health Professions(all)
Cite this
Improving health care organizational management through neural network learning. / Goss, Ernest; Vozikis, George S.
In: Health Care Management Science, Vol. 5, No. 3, 2002, p. 221-227.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Improving health care organizational management through neural network learning
AU - Goss, Ernest
AU - Vozikis, George S.
PY - 2002
Y1 - 2002
N2 - In order to provide more ethical and objective measures of the likelihood of Intensive Care Unit (ICU) recovery, hospitals have turned increasingly to decision support system software packages, such as APACHE. However, these packages derive estimates from parametric techniques, such as Binary Logit Regression (BLR) in the APACHE case, and require the developer to specify in advance the functional relationships among variables in the model. Recent rapid advancements in computer software and hardware technology have encouraged researchers to use more computationally intensive, non-parametric techniques such as Neural Networks (NNs), which are purported to be better than parametric models in terms of prediction capabilities. The present study applies both methodologies to a sample of ICU patients and shows that the NN technique predicts mortality rates more correctly than BLR, and offers a promising non-parametric alternative to the parametric methodologies in hospital settings.
AB - In order to provide more ethical and objective measures of the likelihood of Intensive Care Unit (ICU) recovery, hospitals have turned increasingly to decision support system software packages, such as APACHE. However, these packages derive estimates from parametric techniques, such as Binary Logit Regression (BLR) in the APACHE case, and require the developer to specify in advance the functional relationships among variables in the model. Recent rapid advancements in computer software and hardware technology have encouraged researchers to use more computationally intensive, non-parametric techniques such as Neural Networks (NNs), which are purported to be better than parametric models in terms of prediction capabilities. The present study applies both methodologies to a sample of ICU patients and shows that the NN technique predicts mortality rates more correctly than BLR, and offers a promising non-parametric alternative to the parametric methodologies in hospital settings.
UR - http://www.scopus.com/inward/record.url?scp=0036689146&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0036689146&partnerID=8YFLogxK
U2 - 10.1023/A:1019760901191
DO - 10.1023/A:1019760901191
M3 - Article
C2 - 12363049
AN - SCOPUS:0036689146
VL - 5
SP - 221
EP - 227
JO - Health Care Management Science
JF - Health Care Management Science
SN - 1386-9620
IS - 3
ER -