Neural Network Prediction of ICU Length of Stay Following Cardiac Surgery Based on Pre-Incision Variables

Advanced predictive analytical techniques are being increasingly applied to clinical risk assessment. This study compared a neural network model to several other models in predicting the length of stay (LOS) in the cardiac surgical intensive care unit (ICU) based on pre-incision patient characterist...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2015-12, Vol.10 (12), p.e0145395-e0145395
Main Authors: LaFaro, Rocco J, Pothula, Suryanarayana, Kubal, Keshar Paul, Inchiosa, Mario Emil, Pothula, Venu M, Yuan, Stanley C, Maerz, David A, Montes, Lucresia, Oleszkiewicz, Stephen M, Yusupov, Albert, Perline, Richard, Inchiosa, Jr, Mario Anthony
Format: Article
Language:English
Subjects:
Algorithms
Anesthesiology
Aorta
Artificial neural networks
Balloon treatment
Bone surgery
Cardiac Surgical Procedures
Classification
Computer programs
Creatinine
Diabetes
Female
Gene expression
Health risk assessment
Heart
Heart diseases
Heart surgery
Hematocrit
Hospital stays
Humans
Intensive care
Intensive Care Units
Length of Stay
Linear Models
Male
Mathematical models
Medical diagnosis
Medical research
Methods
Model accuracy
Modelling
Morbidity
Neural networks
Neural Networks (Computer)
Odds Ratio
Patient outcomes
Pharmacology
Prediction models
Risk assessment
Risk Assessment - methods
Statistical analysis
Surgery
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Advanced predictive analytical techniques are being increasingly applied to clinical risk assessment. This study compared a neural network model to several other models in predicting the length of stay (LOS) in the cardiac surgical intensive care unit (ICU) based on pre-incision patient characteristics. Thirty six variables collected from 185 cardiac surgical patients were analyzed for contribution to ICU LOS. The Automatic Linear Modeling (ALM) module of IBM-SPSS software identified 8 factors with statistically significant associations with ICU LOS; these factors were also analyzed with the Artificial Neural Network (ANN) module of the same software. The weighted contributions of each factor ("trained" data) were then applied to data for a "new" patient to predict ICU LOS for that individual. Factors identified in the ALM model were: use of an intra-aortic balloon pump; O2 delivery index; age; use of positive cardiac inotropic agents; hematocrit; serum creatinine ≥ 1.3 mg/deciliter; gender; arterial pCO2. The r2 value for ALM prediction of ICU LOS in the initial (training) model was 0.356, p
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0145395