An analysis of thyroid function diagnosis using Bayesian-type and SOM-type neural networks.

Thyroid function diagnosis is an important classification problem, and we made reanalysis of the human thyroid data, which had been analyzed by the multivariate analysis, by the two notable neural networks. One is the self-organizing map approach which clusters the patients and displays visually a characteristic of the distribution according to laboratory tests. We found that self-organizing map (SOM) consists of three well separated clusters corresponding to hyperthyroid, hypothyroid and normal, and more detailed information for patients is obtained from the position in the map. Besides, the missing value SOM which we had introduced to investigate QSAR problem turned out to be also useful in treating such classification problem. We estimated the classification rates of thyroid disease using Bayesian regularized neural network (BRNN) and found that its prediction accuracy is better than multivariate analysis. Automatic relevance determination (ARD) method of BRNN was surely verified to be effective by the direct calculation of classification rates using BRNN without ARD for all possible combinations of laboratory tests.

[1]  D. Coomans,et al.  The application of linear discriminant analysis in the diagnosis of thyroid diseases , 1978 .

[2]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[3]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[4]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[5]  M. Karplus,et al.  Genetic neural networks for quantitative structure-activity relationships: improvements and application of benzodiazepine affinity for benzodiazepine/GABAA receptors. , 1996, Journal of medicinal chemistry.

[6]  K. Sato,et al.  An improvement of neural networks applied to pharmaceutical problems. , 1997, Chemical & pharmaceutical bulletin.

[7]  S. Anzali,et al.  Endothelin antagonists: search for surrogates of methylendioxyphenyl by means of a Kohonen neural network. , 1998, Bioorganic & medicinal chemistry letters.

[8]  Victor L. Berardi,et al.  An investigation of neural networks in thyroid function diagnosis , 1998, Health care management science.

[9]  Frank R. Burden,et al.  Atomistic topological indices applied to benzodiazepines using various regression methods , 1998 .

[10]  William D. Penny,et al.  An empirical evaluation of Bayesian sampling with hybrid Monte Carlo for training neural network classifiers , 1999, Neural Networks.

[11]  I V Tetko,et al.  Volume learning algorithm artificial neural networks for 3D QSAR studies. , 2001, Journal of medicinal chemistry.

[12]  Shigehiko Kanaya,et al.  Informatics for unveiling hidden genome signatures. , 2003, Genome research.

[13]  Junko Kawakami,et al.  Application of a self-organizing map to quantitative structure-activity relationship analysis of carboquinone and benzodiazepine. , 2004, Chemical & pharmaceutical bulletin.