Cover Image

Gene expression profiling of breast cancer survivability by pooled cDNA microarray analysis using logistic regression, artificial neural networks and decision trees

Microarray technology can acquire information about thousands of genes simultaneously. We analyzed published breast cancer microarray databases to predict five-year recurrence and compared the performance of three data mining algorithms of artificial neural networks (ANN), decision trees (DT) and lo...

Full description

Saved in:
Bibliographic Details
Main Authors: Chou, Hsiu-Ling (Author) , Yao, Chung-Tay (Author) , Su, Sui-Lun (Author) , Lee, Chia-Yi (Author) , Hu, Kuang-Yu (Author) , Terng, Harn-Jing (Author) , Shih, Yun-Wen (Author) , Chang, Yu-Tien (Author) , Lu, Yu-Fen (Author) , Chang, Chi-Wen (Author) , Wahlqvist, Mark L. (Author) , Wetter, Thomas (Author) , Chu, Chi-Ming (Author)
Format: Article (Journal)
Language:English
Published: 19 March 2013
In: BMC bioinformatics
Year: 2013, Volume: 14, Issue: 1, Pages: 1-11
ISSN:1471-2105
DOI:10.1186/1471-2105-14-100
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1186/1471-2105-14-100
Get full text
Author Notes:Hsiu-Ling Chou, Chung-Tay Yao, Sui-Lun Su, Chia-Yi Lee, Kuang-Yu Hu, Harn-Jing Terng, Yun-Wen Shih, Yu-Tien Chang, Yu-Fen Lu, Chi-Wen Chang, Mark L. Wahlqvist, Thomas Wetter and Chi-Ming Chu
Description
Summary:Microarray technology can acquire information about thousands of genes simultaneously. We analyzed published breast cancer microarray databases to predict five-year recurrence and compared the performance of three data mining algorithms of artificial neural networks (ANN), decision trees (DT) and logistic regression (LR) and two composite models of DT-ANN and DT-LR. The collection of microarray datasets from the Gene Expression Omnibus, four breast cancer datasets were pooled for predicting five-year breast cancer relapse. After data compilation, 757 subjects, 5 clinical variables and 13,452 genetic variables were aggregated. The bootstrap method, Mann-Whitney U test and 20-fold cross-validation were performed to investigate candidate genes with 100 most-significant p-values. The predictive powers of DT, LR and ANN models were assessed using accuracy and the area under ROC curve. The associated genes were evaluated using Cox regression.
Item Description:Gesehen am 16.04.2021
Physical Description:Online Resource
ISSN:1471-2105
DOI:10.1186/1471-2105-14-100

Similar Items