Skip to main content
Proceedings of the National Academy of Sciences of the United States of America logoLink to Proceedings of the National Academy of Sciences of the United States of America
. 1991 Dec 15;88(24):11426–11430. doi: 10.1073/pnas.88.24.11426

Neural networks as a tool for utilizing laboratory information: comparison with linear discriminant analysis and with classification and regression trees.

G Reibnegger 1, G Weiss 1, G Werner-Felmayer 1, G Judmaier 1, H Wachter 1
PMCID: PMC53148  PMID: 1763057

Abstract

Successful applications of neural network architecture have been described in various fields of science and technology. We have applied one such technique, error back-propagation, to a medical classification problem stemming from clinical chemistry, and we have compared the performance of two different neural networks with results obtained by conventional linear discriminant analysis or by the technique of classification and regression trees. The results obtained by the various models were tested for robustness by jackknife validation ("leave n out" method). Compared with the two other techniques, neural networks show a unique ability to detect features hidden in the input data which are not explicitly formulated as input. Thus, neural network techniques appear promising in the field of clinical chemistry, and their application, particularly in situations with complex data structures, should be investigated with more emphasis.

Full text

PDF
11426

Images in this article

Selected References

These references are in PubMed. This may not be the complete list of references from this article.

  1. Boone J. M., Sigillito V. G., Shaber G. S. Neural networks in radiology: an introduction and evaluation in a signal detection task. Med Phys. 1990 Mar-Apr;17(2):234–241. doi: 10.1118/1.596501. [DOI] [PubMed] [Google Scholar]
  2. Brain S. D., Tippins J. R., Morris H. R., MacIntyre I., Williams T. J. Potent vasodilator activity of calcitonin gene-related peptide in human skin. J Invest Dermatol. 1986 Oct;87(4):533–536. doi: 10.1111/1523-1747.ep12455620. [DOI] [PubMed] [Google Scholar]
  3. Büttner J. Grundlagen der Anwendung der Informationstheorie auf qualitative klinisch-chemische Untersuchungen. J Clin Chem Clin Biochem. 1982 Jul;20(7):477–490. [PubMed] [Google Scholar]
  4. Holley L. H., Karplus M. Protein secondary structure prediction with a neural network. Proc Natl Acad Sci U S A. 1989 Jan;86(1):152–156. doi: 10.1073/pnas.86.1.152. [DOI] [PMC free article] [PubMed] [Google Scholar]
  5. Hopfield J. J. Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci U S A. 1982 Apr;79(8):2554–2558. doi: 10.1073/pnas.79.8.2554. [DOI] [PMC free article] [PubMed] [Google Scholar]
  6. Hopfield J. J., Tank D. W. Computing with neural circuits: a model. Science. 1986 Aug 8;233(4764):625–633. doi: 10.1126/science.3755256. [DOI] [PubMed] [Google Scholar]
  7. Prior C., Fuchs D., Hausen A., Judmaier G., Reibnegger G., Werner E. R., Vogel W., Wachter H. Potential of urinary neopterin excretion in differentiating chronic non-A, non-B hepatitis from fatty liver. Lancet. 1987 Nov 28;2(8570):1235–1237. doi: 10.1016/s0140-6736(87)91852-6. [DOI] [PubMed] [Google Scholar]
  8. Sejnowski T. J., Koch C., Churchland P. S. Computational neuroscience. Science. 1988 Sep 9;241(4871):1299–1306. doi: 10.1126/science.3045969. [DOI] [PubMed] [Google Scholar]

Articles from Proceedings of the National Academy of Sciences of the United States of America are provided here courtesy of National Academy of Sciences

RESOURCES