Dataset Information

Predicting survival time for metastatic castration resistant prostate cancer: An iterative imputation approach.

ABSTRACT: In this paper, we present our winning method for survival time prediction in the 2015 Prostate Cancer DREAM Challenge, a recent crowdsourced competition focused on risk and survival time predictions for patients with metastatic castration-resistant prostate cancer (mCRPC). We are interested in using a patient's covariates to predict his or her time until death after initiating standard therapy. We propose an iterative algorithm to multiply impute right-censored survival times and use ensemble learning methods to characterize the dependence of these imputed survival times on possibly many covariates. We show that by iterating over imputation and ensemble learning steps, we guide imputation with patient covariates and, subsequently, optimize the accuracy of survival time prediction. This method is generally applicable to time-to-event prediction problems in the presence of right-censoring. We demonstrate the proposed method's performance with training and validation results from the DREAM Challenge and compare its accuracy with existing methods.

SUBMITTER: Deng D

PROVIDER: S-EPMC5321124 | biostudies-other | 2016

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Predicting survival time for metastatic castration resistant prostate cancer: An iterative imputation approach.

Deng Detian D Du Yu Y Ji Zhicheng Z Rao Karthik K Wu Zhenke Z Zhu Yuxin Y Coley R Yates RY

F1000Research 20161116

In this paper, we present our winning method for survival time prediction in the 2015 Prostate Cancer DREAM Challenge, a recent crowdsourced competition focused on risk and survival time predictions for patients with metastatic castration-resistant prostate cancer (mCRPC). We are interested in using a patient's covariates to predict his or her time until death after initiating standard therapy. We propose an iterative algorithm to multiply impute right-censored survival times and use ensemble le ...[more]

PMID: 28299176

Similar Datasets

Project description:From March through August 2015, nearly 60 teams from around the world participated in the Prostate Cancer Dream Challenge (PCDC). Participating teams were faced with the task of developing prediction models for patient survival and treatment discontinuation using baseline clinical variables collected on metastatic castrate-resistant prostate cancer (mCRPC) patients in the comparator arm of four phase III clinical trials. In total, over 2,000 mCRPC patients treated with first-line docetaxel comprised the training and testing data sets used in this challenge. In this paper we describe: (a) the sub-challenges comprising the PCDC, (b) the statistical metrics used to benchmark prediction performance, (c) our analytical approach, and finally (d) our team's overall performance in this challenge. Specifically, we discuss our curated, ad-hoc, feature selection (CAFS) strategy for identifying clinically important risk-predictors, the ensemble-based Cox proportional hazards regression framework used in our final submission, and the adaptation of our modeling framework based on the results from the intermittent leaderboard rounds. Strong predictors of patient survival were successfully identified utilizing our model building approach. Several of the identified predictors were new features created by our team via strategically merging collections of weak predictors. In each of the three intermittent leaderboard rounds, our prediction models scored among the top four models across all participating teams and our final submission ranked 9 th place overall with an integrated area under the curve (iAUC) of 0.7711 computed in an independent test set. While the prediction performance of teams placing between 2 nd- 10 th (iAUC: 0.7710-0.7789) was better than the current gold-standard prediction model for prostate cancer survival, the top-performing team, FIMM-UTU significantly outperformed all other contestants with an iAUC of 0.7915. In summary, our ensemble-based Cox regression framework with CAFS resulted in strong overall performance for predicting prostate cancer survival and represents a promising approach for future prediction problems.

Project description:BACKGROUND:Multiple androgens drive prostate cancer progression and higher pre-treatment levels of androgens, even within the castrate range, have been previously shown to be associated with an improved overall survival (OS) in mCRPC. Docetaxel impairs microtubules, has androgen receptor (AR) inhibitory effects and is used in both the castration resistant and sensitive settings, where androgen dynamics may impact outcome. The present analysis evaluates the association of decline in serum androgen levels (Testosterone (T), Androstenedione (A) and DHEA in docetaxel-treated mCRPC patients with OS. METHODS:Data from 1050 men treated on CALGB 90401 with docetaxel, prednisone and either bevacizumab or placebo were evaluated. Eligibility required progressive mCRPC and no prior chemotherapy. Pre-treatment, 6 week and progression serum assays for T, A and DHEA were performed via tandem Liquid Chromatography-Mass Spectrometry (LC-MS/MS). Changes in T, A and DHEA levels from baseline to 6 weeks were calculated as the ratio of 6-week over baseline. The proportional hazards model was used to assess the prognostic significance of changes in T, A, and DHEA from baseline to 6 weeks in predicting OS adjusting for known prognostic factors. RESULTS:Median baseline values for T, A, and, DHEA were 1.0, 13.5, and 8.1?ng/dL respectively while 6 week levels were 0.64, 7.0, and 6.8?ng/dL respectively. Median OS for low testosterone decline is 20.9 months vs 26.3 months for high testosterone decline. In multivariable analysis including known prognostic variables, change in testosterone levels was independently associated with greater OS; the hazard ratio for death with each unit increase in the 6-week/baseline ratio is 1.02 (95% CI?=?1.01-1.03, p?=?0.001). Decline in A and DHEA were not significant predictors of OS. In multivariable analysis change in the serum changes did not predict PFS however the ratio of T at 6-weeks over baseline was prognostic of ?50% decline in PSA with an odds ratio of 0.93 (95% CI?=?0.85-0.98, p-value?=?0.039). CONCLUSIONS:Declines in testosterone during docetaxel treatment is associated with a longer survival, consistent with a favorable prognostic significance of higher serum androgens in the CRPC.

Dataset Information

Predicting survival time for metastatic castration resistant prostate cancer: An iterative imputation approach.

Publications

Predicting survival time for metastatic castration resistant prostate cancer: An iterative imputation approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets