Feed Forward Artificial Neural Network: Tool for Early Detection of Ovarian Cancer
Open Access
- 1 January 2011
- journal article
- Published by MDPI AG in Scientia Pharmaceutica
- Vol. 79 (3) , 493-505
Abstract
Pathological changes in an organ or tissue may be reflected in proteomic patterns in serum. The early detection of cancer is crucial for successful treatment. Some cancers affect the concentration of certain molecules in the blood, which allows early diagnosis by analyzing the blood mass spectrum. It is possible that exclusive serum proteomic patterns could be used to differentiate cancer samples from non-cancer ones. Several techniques have been developed for the analysis of mass-spectrum curve, and use them for the detection of prostate, ovarian, breast, bladder, pancreatic, kidney, liver, and colon cancers. In present study, we applied data mining to the diagnosis of ovarian cancer and identified the most informative points of the mass-spectrum curve, then used student t-test and neural networks to determine the differences between the curves of cancer patients and healthy people. Two serum SELDI MS data sets were used in this research to identify serum proteomic patterns that distinguish the serum of ovarian cancer cases from non-cancer controls. Statistical testing and genetic algorithm-based methods are used for feature selection respectively. The results showed that (1) data mining techniques can be successfully applied to ovarian cancer detection with a reasonably high performance; (2) the discriminatory features (proteomic patterns) can be very different from one selection method to another.Keywords
This publication has 22 references indexed in Scilit:
- Symptoms and diagnostic delay in ovarian cancer: A summary of the literatureContemporary Nurse, 2010
- Early Detection of Ovarian CancerBiomarkers in Medicine, 2008
- Pharmaceutical Management of Ovarian CancerDrugs, 2008
- Characterization of serum biomarkers for detection of early stage ovarian cancerProteomics, 2005
- An integrated approach utilizing proteomics and bioinformatics to detect ovarian cancerJournal of Zhejiang University SCIENCE, 2005
- Probabilistic Disease Classification of Expression-Dependent Proteomic Data from Mass Spectrometry of Human SerumJournal of Computational Biology, 2003
- Comparison of statistical methods for classification of ovarian cancer using mass spectrometry dataBioinformatics, 2003
- A data review and re-assessment of ovarian cancer serum proteomic profilingBMC Bioinformatics, 2003
- Ovarian Surface Epithelium: Biology, Endocrinology, and Pathology*Endocrine Reviews, 2001
- A Radioimmunoassay Using a Monoclonal Antibody to Monitor the Course of Epithelial Ovarian CancerNew England Journal of Medicine, 1983