Your browser version may not work well with NCBI's Web applications. More information here...
1: Crit Care. 2005 Apr;9(2):153-4. Epub 2005 Mar 3.Click here to read Click here to read Links
Comment on:
Crit Care. 2005 Apr;9(2):R150-6.

Artificial neural networks as prediction tools in the critically ill.

Clermont G.

The CRISMA Laboratory, Department of Critical Care Medicine, The Center for Inflammatory and Regenerative Modeling, University of Pittsburgh, Pittsburgh, Pennsylvania, USA. clermontg@upmc.edu

The past 25 years have witnessed the development of improved tools with which to predict short-term and long-term outcomes after critical illness. The general paradigm for constructing the best known tools has been the logistic regression model. Recently, a variety of alternative tools, such as artificial neural networks, have been proposed, with claims of improved performance over more traditional models in particular settings. However, these newer methods have yet to demonstrate their practicality and usefulness within the context of predicting outcomes in the critically ill.

PMID: 15774070 [PubMed - indexed for MEDLINE]

PMCID: PMC1175945