Dataset Information

External validation of the ProCaRS nomograms and comparison of existing risk-stratification tools for localized prostate cancer.

ABSTRACT: INTRODUCTION:The purpose of this study was to perform a direct comparison of several existing risk-stratification tools for localized prostate cancer in terms of their ability to predict for biochemical failure-free survival (BFFS). Two large databases were used and an external validation of two recently developed nomograms on an independent cohort was also performed in this analysis. METHODS:Patients who were treated with external beam radiotherapy (EBRT) and/or brachytherapy for localized prostate cancer were selected from the multi-institutional Genitourinary Radiation Oncologists of Canada (GUROC) Prostate Cancer Risk Stratification (ProCaRS) database (n=7974) and the Centre Hospitalier de l'Université de Montréal (CHUM) validation database (n=2266). The primary outcome was BFFS using the Phoenix definition. Concordance index (C-index) reported from Cox proportional hazards regression using 10-fold cross validation and decision curve analysis (DCA) were used to predict BFFS. RESULTS:C-index identified Cancer of the Prostate Risk Assessment (CAPRA) score and ProCaRS as superior to the historical GUROC and National Comprehensive Cancer Network (NCCN) risk-stratification systems. CAPRA modeled as five and three categories were superior to GUROC and NCCN only for the CHUM database. C-indices for CAPRA score, ProCaRS, GUROC, and NCCN were 0.72, 0.72, 0.71, and 0.72, respectively, for the ProCaRS database, and 0.66, 0.63, 0.57, and 0.60, respectively, for the CHUM database. However, many of these comparisons did not demonstrate a clinically meaningful difference. DCA identified minimal differences across the different risk-stratification systems, with no system emerging with optimal net benefit. External validation of the ProCaRS nomograms yielded favourable calibrations of R2=0.778 (low-dose rate [LDR]-brachytherapy) and R2=0.868 (EBRT). CONCLUSIONS:This study externally validated two ProCaRS nomograms for BFFS that may help clinicians in treatment selection and outcome prediction. A direct comparison between existing risk-stratification tools demonstrated minimal clinically significant differences in discriminative ability between the systems, favouring the CAPRA and ProCaRS systems. The incorporation of novel prognostic variables, such as genomic markers, is needed.

SUBMITTER: Tiberi D

PROVIDER: S-EPMC5434512 | biostudies-literature | 2017 Mar-Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

External validation of the ProCaRS nomograms and comparison of existing risk-stratification tools for localized prostate cancer.

Tiberi David D Rodrigues George G Pickles Tom T Morris Jim J Crook Juanita J Martin Andre-Guy AG Cury Fabio F Catton Charles C Lukka Himu H Warner Andrew A Taussky Daniel D

Canadian Urological Association journal = Journal de l'Association des urologues du Canada 20170301 3-4

<h4>Introduction</h4>The purpose of this study was to perform a direct comparison of several existing risk-stratification tools for localized prostate cancer in terms of their ability to predict for biochemical failure-free survival (BFFS). Two large databases were used and an external validation of two recently developed nomograms on an independent cohort was also performed in this analysis.<h4>Methods</h4>Patients who were treated with external beam radiotherapy (EBRT) and/or brachytherapy for ...[more]

PMID: 28515807

Similar Datasets

Project description:IntroductionAmong industrialized countries, endometrial cancer is a common malignancy with generally an excellent outcome. To personalize medicine, we ideally compile as much information as possible concerning patient prognosis prior to effecting an appropriate treatment decision. Endometrial cancer preoperative risk stratification (ENDORISK) is a machine learning-based computational Bayesian networks model that predicts lymph node metastasis and 5-year disease-specific survival potential with percentual probability. Our objective included validating ENDORISK effectiveness in our patient cohort, assessing its application in the current use of sentinel node biopsy, and verifying its accuracy in advanced stages.MethodsThe ENDORISK model was evaluated with a retrospective cohort of 425 patients from the University Hospital Brno, Czech Republic. Two hundred ninety-nine patients were involved in our disease-specific survival analysis; 226 cases with known lymph node status were available for lymph node metastasis analysis. Patients were included undergoing either pelvic lymph node dissection (N = 84) or sentinel node biopsy (N =70) to explore the accuracy of both staging procedures.ResultsThe area under the curve was 0.84 (95% confidence interval [CI], 0.77-0.9) for lymph node metastasis analysis and 0.86 (95% CI, 0.79-0.93) for 5-year disease-specific survival evaluation, indicating quite positive concordance between prediction and reality. Calibration plots to visualize results demonstrated an outstanding predictive value for low-risk cancers (grades 1-2), whereas outcomes were underestimated among high-risk patients (grade 3), especially in disease-specific survival. This phenomenon was even more obvious when patients were subclassified according to FIGO clinical stages.ConclusionsOur data confirmed ENDORISK model's laudable predictive ability, particularly among patients with a low risk of lymph node metastasis and expected favorable survival. For high-risk and/or advanced stages, the ENDORISK network needs to be additionally trained/improved.

Project description:While the 10-year survival rate for localized prostate cancer patients is very good (>98%), side effects of treatment may limit quality of life significantly. Erectile dysfunction (ED) is a common burden associated with increasing age as well as prostate cancer treatment. Although many studies have investigated the factors affecting erectile dysfunction (ED) after prostate cancer treatment, only limited studies have investigated whether ED can be predicted before the start of treatment. The advent of machine learning (ML) based prediction tools in oncology offers a promising approach to improve the accuracy of prediction and quality of care. Predicting ED may help aid shared decision-making by making the advantages and disadvantages of certain treatments clear, so that a tailored treatment for an individual patient can be chosen. This study aimed to predict ED at 1-year and 2-year post-diagnosis based on patient demographics, clinical data and patient-reported outcomes (PROMs) measured at diagnosis. We used a subset of the ProZIB dataset collected by the Netherlands Comprehensive Cancer Organization (Integraal Kankercentrum Nederland; IKNL) that contained information on 964 localized prostate cancer cases from 69 Dutch hospitals for model training and external validation. Two models were generated using a logistic regression algorithm coupled with Recursive Feature Elimination (RFE). The first predicted ED 1 year post-diagnosis and required 10 pre-treatment variables; the second predicted ED 2 years post-diagnosis with 9 pre-treatment variables. The validation AUCs were 0.84 and 0.81 for 1 year and 2 years post-diagnosis respectively. To immediately allow patients and clinicians to use these models in the clinical decision-making process, nomograms were generated. In conclusion, we successfully developed and validated two models that predicted ED in patients with localized prostate cancer. These models will allow physicians and patients alike to make informed evidence-based decisions about the most suitable treatment with quality of life in mind.

Project description:PurposeWe developed the Korean Prostate Cancer Risk Calculator for High-Grade Prostate Cancer (KPCRC-HG) that predicts the probability of prostate cancer (PC) of Gleason score 7 or higher at the initial prostate biopsy in a Korean cohort (http://acl.snu.ac.kr/PCRC/RISC/). In addition, KPCRC-HG was validated and compared with internet-based Western risk calculators in a validation cohort.Materials and methodsUsing a logistic regression model, KPCRC-HG was developed based on the data from 602 previously unscreened Korean men who underwent initial prostate biopsies. Using 2,313 cases in a validation cohort, KPCRC-HG was compared with the European Randomized Study of Screening for PC Risk Calculator for high-grade cancer (ERSPCRC-HG) and the Prostate Cancer Prevention Trial Risk Calculator 2.0 for high-grade cancer (PCPTRC-HG). The predictive accuracy was assessed using the area under the receiver operating characteristic curve (AUC) and calibration plots.ResultsPC was detected in 172 (28.6%) men, 120 (19.9%) of whom had PC of Gleason score 7 or higher. Independent predictors included prostate-specific antigen levels, digital rectal examination findings, transrectal ultrasound findings, and prostate volume. The AUC of the KPCRC-HG (0.84) was higher than that of the PCPTRC-HG (0.79, p<0.001) but not different from that of the ERSPCRC-HG (0.83) on external validation. Calibration plots also revealed better performance of KPCRC-HG and ERSPCRC-HG than that of PCPTRC-HG on external validation. At a cut-off of 5% for KPCRC-HG, 253 of the 2,313 men (11%) would not have been biopsied, and 14 of the 614 PC cases with Gleason score 7 or higher (2%) would not have been diagnosed.ConclusionsKPCRC-HG is the first web-based high-grade prostate cancer prediction model in Korea. It had higher predictive accuracy than PCPTRC-HG in a Korean population and showed similar performance with ERSPCRC-HG in a Korean population. This prediction model could help avoid unnecessary biopsy and reduce overdiagnosis and overtreatment in clinical settings.

Dataset Information

External validation of the ProCaRS nomograms and comparison of existing risk-stratification tools for localized prostate cancer.

Publications

External validation of the ProCaRS nomograms and comparison of existing risk-stratification tools for localized prostate cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets