Diagnosis of Ovarian Cancer Using Decision Tree Classificationof Mass Spectral Data

[摘要] Recent reports from our laboratory and others support the SELDIProteinChip technology as a potential clinical diagnostic toolwhen combined withn-dimensional analyses algorithms. Theobjective of this study was to determine ifthe commerciallyavailable classification algorithm biomarker patterns software(BPS), which is based on a classification and regression tree(CART), would be effective in discriminating ovarian cancer frombenign diseases and healthy controls.Serum protein massspectrum profiles from 139 patients with either ovarian cancer,benign pelvic diseases, or healthy women were analyzed usingthe BPS software. A decision tree, using five protein peaksresulted inan accuracy of 81.5% in the cross-validationanalysis and 80%in a blinded set of samples indifferentiating the ovarian cancer from the control groups. Thepotential, advantages, and drawbacks of the BPS system as abioinformatic tool for the analysis of the SELDI high-dimensionalproteomic data are discussed.

[学科分类] 基础医学