A Genomic Classifier Improves Prediction of Metastatic Disease Within 5 Years After Surgery in Node-negative High-risk Prostate Cancer Patients Managed by Radical Prostatectomy Without Adjuvant Therapy

Klein, Eric A.; Yousefi, Kasra; Haddad, Zaid; Choeurng, Voleak; Buerki, Christine; Stephenson, Andrew J.; Li, Jianbo; Kattan, Michael W.; Magi‐Galluzzi, Cristina; Davicioni, Elai

doi:10.1016/j.eururo.2014.10.036

Cited by 159 publications

(123 citation statements)

References 43 publications

Supporting

Mentioning

118

Contrasting

Order By: Relevance

“…Decipher is a genomic test based on RNA expression from routinely processed and stored tissue specimens; its ability to augment risk stratification for men considering adjuvant and salvage therapies after prostatectomy has previously been investigated [3][4][5][6]. While Decipher has been explored in multiple studies as a prognostic tool in the posttreatment setting, previous work involved either populations confounded by appreciable rates of adjuvant and salvage therapies or populations with relatively low event (metastasis) rates [4][5][6][7].…”

Section: Introductionmentioning

confidence: 98%

Tissue-based Genomics Augments Post-prostatectomy Risk Stratification in a Natural History Cohort of Intermediate- and High-Risk Men

et al. 2016

Self Cite

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 98%

Tissue-based Genomics Augments Post-prostatectomy Risk Stratification in a Natural History Cohort of Intermediate- and High-Risk Men

et al. 2016

Self Cite

View full text Add to dashboard Cite

“…Moreover, the predictive value of GC is not limited to post-RP patients but can be utilized in recurrent individuals who underwent RP and have already been treated with secondary salvage RT [74]. Similarly to Prolaris, GC scoring adds a significant predictive value to the clinical scoring (CAPRA-S) as well as to the Eggeners risk model, which constitutes the rationale for genomic-clinical classifier integration [72,73,75]. In a recent prospective study on a large cohort of 2,342 patients, utilization of the GC score in postoperative decision-making changed initial tumour aggressiveness classification based on clinical parameters alone [76], regardless of the positive correlation between Decipher score and GS, T-staging, CAPRA-S, and age.…”

Section: Decipher and Genomic Classifier-know Your Enemy To Change Tamentioning

confidence: 99%

“…GC was developed as a prognostic tool to assess the probability of metastatic disease development after RP and eventually change secondary treatment recommendations including post-RP adjuvant radiation therapy [34,[67][68][69][70][71][72]. Based on the PRO-ACT study from 2014, even 60% of post RP high-risk patients might be reclassified with GC, 30% patients might need additional adjuvant treatment and in 40%, adjuvant therapy might be unnecessary in spite of initial recommendations [73].…”

Section: Decipher and Genomic Classifier-know Your Enemy To Change Tamentioning

confidence: 99%

What Can Be Expected from Prostate Cancer Biomarkers A Clinical Perspective

Zapała

Dybowski²,

Poletajew³

et al. 2017

Urol Int

View full text Add to dashboard Cite

Along with significant advances in prostate cancer biology research, we also observe the rapid development of modern diagnostic tests. New biomarkers are derived to detect disease while it is organ-confined to stratify the risk and to aid clinical decision-making. Majority of these tools have already been validated clinically, but only a few have received premarket clearance and administration approval. Superiority of novel tests is visible not only in improved detection accuracy but predominantly in the assessment of tumour aggressiveness and selection of patients eligible for conservative management. Two factors limiting the clinical implementation of validated biomarker candidates are costs and local availability. For these reasons, currently, their true clinical role starts after routine screening with prostate-specific antigen test. With this review of prostate cancer biomarkers, we attempted to draw general conclusions on clinical perspectives of these novel tools.

show abstract

“…This included expression data from six published retrospective cohorts (n=1,702) with complete treatment and long-term outcomes data (we referred to them as the labelled datasets) and 1 prospective cohort (n = 15,136) with baseline pathological information only (we referred to it as the unlabelled dataset). labelled cohorts are as follows: Mayo I and II (GSE46691 and GSE62116) (Nakagawa et al, 2008;Erho et al, 2013;Karnes et al, 2017); CCF (GSE62667) (Prensner et al, 2014;Klein et al, 2015); JHMI (GSE79957 and GSE79956) (Ross et al, 2016); TJU (GSE72291) (Den et al, 2014); MetaSet (Spratt et al, 2017) 1 . The characteristics of these labelled datasets are brought in Table S1 in the Supplementary Materials.…”

Section: Datasetsmentioning

confidence: 99%

Deep Genomic Signature for early metastasis prediction in prostate cancer

Sharifi-Noghabi

Liu

Erho

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Motivation: For Prostate Cancer (PCa) patients, timing and intensity of the therapy is adjusted based on their prognosis. This can be predicted from clinical/pathological information and, recently, gene expression signatures. One major challenge in developing such signatures is that all of them are based on cohorts which have limited number of patients with complete clinical outcomes (labelled), especially for slow progressing cancers such as PCa. This poses a challenge to the model development in conjunction with high dimensionality of the transcriptomic data. Results: In this study we aim to exploit the previously untapped potential of a large cohort (n=15,136) with genomic data but no clinical outcome (unlabelled), to improve the performance of the genomic classifiers for predicting PCa metastasis. We propose, Deep Genomic Signature (DGS), based on Denoising Auto-Encoder (DAE) for feature extraction and selection. In order to capture information from the unlabelled and labelled data we train two DAEs separately and apply transfer learning to bridge the gap between them. We show that DGS captures information from these cohorts that can be utilized to build a logistic regression model to predict metastasis. Results on five validation cohorts indicate that this classifier, which is based on high weight genes in the DAEs, outperforms state-of-the-art signatures for metastatic PCa in terms of prediction accuracy. Survival analysis demonstrate the clinical utility of our signature which adds information to the well-established clinical factors and state-of-the-art signatures. Furthermore, pathway analysis reveals that the signature discovered by our DGS captures the hallmarks of PCa metastasis. Availability of the implemented codes and supplementary materials: https://github.com/hosseinshn/Deep-Genomic-Signature

show abstract

A Genomic Classifier Improves Prediction of Metastatic Disease Within 5 Years After Surgery in Node-negative High-risk Prostate Cancer Patients Managed by Radical Prostatectomy Without Adjuvant Therapy

Cited by 159 publications

References 43 publications

Tissue-based Genomics Augments Post-prostatectomy Risk Stratification in a Natural History Cohort of Intermediate- and High-Risk Men

Tissue-based Genomics Augments Post-prostatectomy Risk Stratification in a Natural History Cohort of Intermediate- and High-Risk Men

What Can Be Expected from Prostate Cancer Biomarkers A Clinical Perspective

Deep Genomic Signature for early metastasis prediction in prostate cancer

Contact Info

Product

Resources

About