Document Detail


Predicting prostate biopsy outcome: artificial neural networks and polychotomous regression are equivalent models.
MedLine Citation:
PMID:  20464485     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
INTRODUCTION: Complex statistical models utilizing multiple inputs to derive a risk assessment may benefit prostate cancer (PC) detection where focus has been on prostate-specific antigen (PSA). This study develops a polychotomous logistic regression (PR) model and an artificial neural network (ANN) for predicting biopsy results, particularly for clinically significant PC.
METHODS: There were 3,025 men undergoing TRUS-guided biopsy (BX) with PSA <10 ng/ml selected. BX outcome classified as benign, atypical small acinar proliferation or high-grade prostatic intraepithelial neoplasia (ASAP/PIN), non-significant (NSPC) or clinically significant PC (CSPC). PR and ANN models were developed to distinguish between BX categories. Predictors were age, PSA, abnormal digital rectal examination (DRE), positive transrectal ultrasound (TRUS) and prostate volume.
RESULTS: Among the BXs, 44% were benign, 14% ASAP/PIN, 16% NSPC and 25% CSPC. Median age, PSA and volume were 64 years, 5.7 ng/ml and 50 cc. TRUS lesion was present in 47%, and DRE was abnormal in 39%. PR and ANN models did not differ on percentage BX outcomes correctly predicted (55, 57%, respectively) and were equally poor for both ASAP/PIN (0%) and NSPC (2%). For PR and ANN, 74-78% ASAP/PIN predicted benign, 2% NSPC and 20-24% CSPC. For NSPC, 69-71% predicted benign, 27-29% CSPC. Benign outcomes were well identified (86-88%), although 12-13% classified CSPC. CSPC was correctly identified in 65-66% with misclassifications largely benign (33% for PR and ANN).
CONCLUSIONS: Neither PR nor ANN was able to distinguish between the four biopsy outcomes: ASAP/PIN and NSPC were not distinguished from benign or CSPC. ANN did not perform better than PR. Inclusion of additional predictors may increase the performance of statistical models in predicting BX outcome.
Authors:
Nathan Lawrentschuk; Gina Lockwood; Peter Davies; Andy Evans; Joan Sweet; Ants Toi; Neil E Fleshner
Related Documents :
16441375 - Fast identification of ten clinically important micro-organisms using an electronic nose.
16962295 - Comparison between neural networks and multiple logistic regression to predict acute co...
10430425 - Artificial neural networks improve the prediction of mortality in intracerebral hemorrh...
17357985 - Modeling of acrylamide formation and browning ratio in potato chips by artificial neura...
24682735 - The egenvar data management system--cataloguing and sharing sensitive data and metadata...
20064235 - Effect of training-sample size and classification difficulty on the accuracy of genomic...
Publication Detail:
Type:  Journal Article     Date:  2010-05-13
Journal Detail:
Title:  International urology and nephrology     Volume:  43     ISSN:  1573-2584     ISO Abbreviation:  Int Urol Nephrol     Publication Date:  2011 Mar 
Date Detail:
Created Date:  2011-03-22     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  0262521     Medline TA:  Int Urol Nephrol     Country:  Netherlands    
Other Details:
Languages:  eng     Pagination:  23-30     Citation Subset:  IM    
Affiliation:
Department of Urology, University of Toronto, University Health Network, Toronto, ON, Canada, Lawrentschuk@gmail.com.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Electron spin resonance (ESR) detection of irradiated fish containing bone (gilthead sea bream, cod,...
Next Document:  Effects of anesthetics on cystometric parameters in female rats.