Artificial neural network classification based on capillary electrophoresis of urinary nucleosides for the clinical diagnosis of tumors

Nucleosides in human urine have been studied frequently as a possible biomedical marker for cancers, acquired immune deficiency syndrome (AIDS) and the whole-body turnover of RNAs. A capillary electrophoretic method that can quantitatively analyze urinary normal and modified nucleosides in less than...

Full description

Saved in:
Bibliographic Details
Published in:Journal of Chromatography A 1998-12, Vol.828 (1), p.489-496
Main Authors: Zhao, Ruihuan, Xu, Guowang, Yue, Bingfang, Liebich, H.M., Zhang, Yukui
Format: Article
Language:English
Subjects:
Biological and medical sciences
Biomarkers, Tumor - urine
Discriminant Analysis
Electrophoresis, Capillary - methods
Host-tumor relations. Immunology. Biological markers
Humans
Medical sciences
Neoplasms - diagnosis
Neural Networks (Computer)
Nucleosides
Nucleosides - urine
Tumors
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:Nucleosides in human urine have been studied frequently as a possible biomedical marker for cancers, acquired immune deficiency syndrome (AIDS) and the whole-body turnover of RNAs. A capillary electrophoretic method that can quantitatively analyze urinary normal and modified nucleosides in less than 40 min with a good resolution and sufficient sensitivity has been developed. Twelve kinds of normal and modified nucleosides were determined in urine samples from 25 healthy persons and 25 cancer patients of 14 kinds of cancers. Artificial neural networks have been used as a powerful pattern recognition tool to distinguish cancer patients from healthy persons. The recognition rate for the training set reached to 100% and above 85% of the members in the predicting set were correctly classified. In addition, the neural network technique was compared with methods of the principal component analysis and the canonical discriminant analysis. The results demonstrate that the predictive ability of the artificial neural network is stronger than the others in this study.
ISSN:0021-9673
DOI:10.1016/S0021-9673(98)00589-5