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
• ISSN: 0270-4137; 1097-0045
• DOI: 10.1002/pros.20629

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 adenocarcinoma on PNB, and estimated ploidy status (determined using Feulgen stained biopsy tissue) using four predictors, including age, prebiopsy PSA, highest Gleason score (GS), and the percentage of involvement by carcinoma at the biopsy site with the highest GS (PCARBX). Logistic regression (LR), Neural Network (NN), and CART classifiers were constructed. RESULTS Univariate analyses revealed all four predictors to be significantly associated with ploidy status. On multivariable analyses, LR identified a 2‐parameter model, including GS and PCARBX that had a significant ability to predict ploidy status with a 74% and 75% correct classification rate (CCR), respectively. Using the same variables, CART and NN yielded similar CCRs of 70.4%. Within GS = 6 cohort, the CART model classified over 90% of biopsies as diploid when patients had a PCARBX < 55% and a log(PSA) < 1.7. CONCLUSIONS Our study demonstrates that models using GS and PCARBX are able to predict PNB ploidy status with acceptable accuracy. While machine learning classifier‐derived models yield similar accuracy as LR‐derived models, the latter methodology has the distinct advantage of being applicable in future datasets to estimate case‐specific predictions. This information may be useful in identifying potentially aneuploid patients, who can then be targeted for more aggressive therapy. Prostate 67: 1524–1536, 2007. © 2007 Wiley‐Liss, Inc.