Send to

Choose Destination
JCO Clin Cancer Inform. 2017 Nov;1:1-15. doi: 10.1200/CCI.17.00018.

A DREAM Challenge to Build Prediction Models for Short-Term Discontinuation of Docetaxel in Metastatic Castration-Resistant Prostate Cancer.

Author information

Fatemeh Seyednasrollah and Laura L. Elo, Turku Centre for Biotechnology; University of Turku; Åbo Akademi University, Turku, Finland; Devin C. Koestler, University of Kansas Medical Center, Kansas City, KS; Tao Wang, University of Texas Southwestern Medical Center, Dallas, TX; Stephen R. Piccolo, Brigham Young University, Provo; University of Utah, Salt Lake City, Utah, UT; Roberto Vega, Russell Greiner, and Luke Kumar, University of Alberta; Alberta Innovates Centre for Machine Learning, Edmonton, Alberta, Canada; Christiane Fuchs, Helmholtz Zentrum München, Neuherberg; Technische Universität München, Garching, Germany; Eyal Gofer, The Hebrew University, Jerusalem, Israel; Russell D. Wolfinger, SAS Institute, Cary, NC; Kimberly Kanigel Winner and James C. Costello, University of Colorado, Anschutz Medical Campus, Aurora, CO; Chris Bare, Elias Chaibub Neto, Thomas Yu, Thea Norman, and Justin Guinney, Sage Bionetworks, Seattle, WA; Liji Shen and Fang Liz Zhou, Sanofi, Bridgewater, NJ; Kald Abdallah, AstraZeneca, Gaithersburg, MD; Gustavo Stolovitzky, IBM Research, Yorktown Heights; Howard I. Scher, Memorial Sloan Kettering Cancer Center and Weill Cornell Medical College, New York, NY; Howard R. Soule, Prostate Cancer Foundation, Santa Monica; Charles J. Ryan, University of California, San Francisco, CA; Christopher J. Sweeney, Dana-Farber Cancer Institute and Brigham and Women's Hospital, Harvard Medical School, Boston, MA; and Oliver Sartor, Tulane University, New Orleans, LA.



Docetaxel has a demonstrated survival benefit for patients with metastatic castration-resistant prostate cancer (mCRPC); however, 10% to 20% of patients discontinue docetaxel prematurely because of toxicity-induced adverse events, and the management of risk factors for toxicity remains a challenge.


The comparator arms of four phase III clinical trials in first-line mCRPC were collected, annotated, and compiled, with a total of 2,070 patients. Early discontinuation was defined as treatment stoppage within 3 months as a result of adverse treatment effects; 10% of patients discontinued treatment. We designed an open-data, crowd-sourced DREAM Challenge for developing models with which to predict early discontinuation of docetaxel treatment. Clinical features for all four trials and outcomes for three of the four trials were made publicly available, with the outcomes of the fourth trial held back for unbiased model evaluation. Challenge participants from around the world trained models and submitted their predictions. Area under the precision-recall curve was the primary metric used for performance assessment.


In total, 34 separate teams submitted predictions. Seven models with statistically similar area under precision-recall curves (Bayes factor ≤ 3) outperformed all other models. A postchallenge analysis of risk prediction using these seven models revealed three patient subgroups: high risk, low risk, or discordant risk. Early discontinuation events were two times higher in the high-risk subgroup compared with the low-risk subgroup. Simulation studies demonstrated that use of patient discontinuation prediction models could reduce patient enrollment in clinical trials without the loss of statistical power.


This work represents a successful collaboration between 34 international teams that leveraged open clinical trial data. Our results demonstrate that routinely collected clinical features can be used to identify patients with mCRPC who are likely to discontinue treatment because of adverse events and establishes a robust benchmark with implications for clinical trial design.

[Indexed for MEDLINE]
Free full text

Supplemental Content

Full text links

Icon for Atypon
Loading ...
Support Center