Document Detail

Use of genetic algorithms for neural networks to predict community-acquired pneumonia.
MedLine Citation:
PMID:  14684266     Owner:  NLM     Status:  MEDLINE    
BACKGROUND: Genetic algorithms have been used to solve optimization problems for artificial neural networks (ANN) in several domains. We used genetic algorithms to search for optimal hidden-layer architectures, connectivity, and training parameters for ANN for predicting community-acquired pneumonia among patients with respiratory complaints. METHODS: Feed-forward back-propagation ANN were trained on sociodemographic, symptom, sign, comorbidity, and radiographic outcome data among 1044 patients from the University of Illinois (the training cohort), and were applied to 116 patients from the University of Nebraska (the testing cohort). Binary chromosomes with genes representing network attributes, including the number of nodes in the hidden layers, learning rate and momentum parameters, and the presence or absence of implicit within-layer connectivity using a competition algorithm, were operated on by various combinations of crossover, mutation, and probabilistic selection based on network mean-square error (MSE), and separately on average cross entropy (ENT). Predictive accuracy was measured as the area under a receiver-operating characteristic (ROC) curve. RESULTS: Over 50 generations, the baseline genetic algorithm evolved an optimized ANN with nine nodes in the first hidden layer, zero nodes in the second hidden layer, learning rate and momentum parameters of 0.5, and no within-layer competition connectivity. This ANN had an ROC area in the training cohort of 0.872 and in the testing cohort of 0.934 (P-value for difference, 0.181). Algorithms based on cross-generational selection, Gray coding of genes prior to mutation, and crossover recombination at different genetic levels, evolved optimized ANN identical to the baseline genetic strategy. Algorithms based on other strategies, including elite selection within generations (training ROC area 0.819), and inversions of genetic material during recombination (training ROC area 0.812), evolved less accurate ANN. CONCLUSION: ANN optimized by genetic algorithms accurately discriminated pneumonia within a training cohort, and within a testing cohort consisting of cases on which the networks had not been trained. Genetic algorithms can be used to implement efficient search strategies for optimal ANN to predict pneumonia.
Paul S Heckerling; Ben S Gerber; Thomas G Tape; Robert S Wigton
Related Documents :
18395736 - Combination of artificial neural network technique and linear free energy relationship ...
14635726 - Anvas: artificial neural variables adaptation system for descriptor selection.
12929716 - A study on prediction of the bio-toxicity of substituted benzene based on artificial ne...
18196306 - An informative probability model enhancing real time echobiometry to improve fetal weig...
22373266 - Lasso model selection with post-processing for a genome-wide association study data set.
21274806 - Residential satisfaction as an intervening variable in residential mobility.
Publication Detail:
Type:  Evaluation Studies; Journal Article    
Journal Detail:
Title:  Artificial intelligence in medicine     Volume:  30     ISSN:  0933-3657     ISO Abbreviation:  Artif Intell Med     Publication Date:  2004 Jan 
Date Detail:
Created Date:  2003-12-19     Completed Date:  2004-04-02     Revised Date:  2004-11-17    
Medline Journal Info:
Nlm Unique ID:  8915031     Medline TA:  Artif Intell Med     Country:  Netherlands    
Other Details:
Languages:  eng     Pagination:  71-84     Citation Subset:  IM    
Department of Medicine (M/C 787), University of Illinois, 840 South Wood Street, Chicago, IL 60612, USA.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Child, Preschool
Cohort Studies
Community-Acquired Infections
DNA Mutational Analysis
Genetic Predisposition to Disease*
Infant, Newborn
Middle Aged
Pneumonia / epidemiology*,  genetics*
Predictive Value of Tests
Sensitivity and Specificity

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

Previous Document:  Prediction of postoperative morbidity after lung resection using an artificial neural network ensemb...
Next Document:  An overview of current delivery systems in cancer gene therapy.