Document Detail


Use of a neural network as a predictive instrument for length of stay in the intensive care unit following cardiac surgery.
MedLine Citation:
PMID:  1482955     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
A patient's intensive care unit (ICU) length of stay following cardiac surgery is an important issue in Canada, where cardiovascular intensive care resources are limited and waiting lists for cardiac surgery exist. A predictive instrument for ICU length of stay could lead to improved utilization of existing ICU and operating room resources through better scheduling of patients and staff. We trained a neural network with a database of 713 patients and 15 input variables to predict patients who would have a prolonged ICU length of stay, which we defined as a stay greater than 2 days. In an independent test set of 696 patients, the network was able to stratify patients into three risk groups for prolonged stay (low, intermediate, and high), corresponding to frequencies of prolonged stay of 16.3%, 35.3%, and 60.8% respectively. The performance of the network was also evaluated by calculating the area under the Receiver Operating Characteristic (ROC) curve in the training set, 0.7094 (SE 0.0224), and in the test set, 0.6960 (SE 0.0227). We believe the trained network would be a useful predictive instrument for optimizing the scheduling of cardiac surgery patients in times of limited ICU resources. Neural networks are a new alternative method for developing predictive instruments that offer both advantages and disadvantages when compared to other more widely used statistical techniques.
Authors:
J V Tu; M R Guerriere
Related Documents :
7802555 - The neuropathology of cardiac allograft transplantation. an autopsy series of 18 patients.
11198785 - Epidemic dropsy--a clinical study of the delhi outbreak.
235375 - Cardiac performance and mortality early after intracardiac surgery in infants and young...
2869715 - Clinical observations on the pathophysiology and treatment of anaphylactic cardiovascul...
8340585 - Reevaluation of plain radiographic findings in the diagnosis of aortic rupture: the rol...
9109885 - Corticobasal degeneration: neuropathologic and clinical heterogeneity.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  Proceedings / the ... Annual Symposium on Computer Application [sic] in Medical Care. Symposium on Computer Applications in Medical Care     Volume:  -     ISSN:  0195-4210     ISO Abbreviation:  Proc Annu Symp Comput Appl Med Care     Publication Date:  1992  
Date Detail:
Created Date:  1993-02-12     Completed Date:  1993-02-12     Revised Date:  2010-09-07    
Medline Journal Info:
Nlm Unique ID:  8113685     Medline TA:  Proc Annu Symp Comput Appl Med Care     Country:  UNITED STATES    
Other Details:
Languages:  eng     Pagination:  666-72     Citation Subset:  IM    
Affiliation:
Information Systems Department, St. Michael's Hospital, University of Toronto, Ontario.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Cardiac Surgical Procedures*
Humans
Intensive Care Units*
Length of Stay*
Neural Networks (Computer)*
Predictive Value of Tests
Comments/Corrections

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Collaboration between unlikely disciplines in the creation of a conceptual framework for nurse-compu...
Next Document:  Automated acuity scoring within a computer based medical record.