Identification of patients with low-risk for aneuploidy: Comparative discriminatory models using linear and machine-learning classifiers in prostate cancer

• Published in: The Prostate Vol. 67; no. 14; pp. 1524 - 1536
• Main Authors: Venkataraman, Girish, Heinze, Georg, Holmes, Earle W., Ananthanarayanan, Vijayalakshmi, Bostwick, David G., Paner, Gladell P., Bradford-De La garza, Carrie M., Brown, Henry G., Flanigan, Robert C., Wojcik, Eva M.
• Format: Journal Article
• Language: English
• Published: Hoboken Wiley Subscription Services, Inc., A Wiley Company 01.10.2007; Wiley-Liss
• Subjects: Adenocarcinoma - blood; Adenocarcinoma - classification; Adenocarcinoma - diagnosis; Adenocarcinoma - genetics; Adult; Aged; Aged, 80 and over; Aneuploidy; Biological and medical sciences; biopsy; Biopsy, Needle; Cohort Studies; Discriminant Analysis; DNA, Neoplasm - genetics; Gynecology. Andrology. Obstetrics; Humans; Image Cytometry; Logistic Models; logistic regression; Male; Male genital diseases; Medical sciences; Middle Aged; Models, Statistical; morphometry; Nephrology. Urinary tract diseases; Neural Networks (Computer); ploidy; Predictive Value of Tests; prostate; Prostate-Specific Antigen - blood; Prostatic Neoplasms - blood; Prostatic Neoplasms - classification; Prostatic Neoplasms - diagnosis; Prostatic Neoplasms - genetics; Risk Assessment; Tumors; Tumors of the urinary system; Urinary tract. Prostate gland; validation machine learning; Chromosomal aberration; Andrology; Nephrology; Prostate disease; Aneuploidy; Identification; Low risk; Linear model; Learning; Acquisition process; Male genital diseases; Human; Validation; Ploidy; Urinary system disease; Statistical analysis; validation machine learning; Gynecology; Malignant tumor; Logistic regression; Anatomic pathology; Biopsy; Cytogenetics; prostate; Morphometry; Prostate cancer; Comparative study

BACKGROUND Prostate needle biopsy (PNB) ploidy status has proven utility to predict adverse outcomes after prostatectomy. We sought to develop models to predict ploidy status using clinicopathologic variables. METHODS We identified a cohort of 169 patients with a diagnosis of prostatic adenocarcinom...