TY - JOUR
T1 - A DREAM challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration- resistant prostate cancer
AU - Prostate Cancer DREAM Challenge Community
AU - Seyednasrollah, Fatemeh
AU - Koestler, Devin C.
AU - Wang, Tao
AU - Piccolo, Stephen R.
AU - Vega, Roberto
AU - Greiner, Russell
AU - Fuchs, Christiane
AU - Gofer, Eyal
AU - Kumar, Luke
AU - Wolfinger, Russell D.
AU - Winner, Kimberly Kanigel
AU - Neto, Elias Chaibub
AU - Yu, Thomas
AU - Shen, Liji
AU - Stolovitzky, Gustavo
AU - Soule, Howard R.
AU - Sweeney, Christopher J.
AU - Ryan, Charles J.
AU - Scher, Howard I.
AU - Sartor, Oliver
AU - Elo, Laura L.
AU - Zhou, Fang Liz
AU - Costello, James C.
AU - Abdallah, Kald
AU - Airola, Antti
AU - Aittokallio, Tero
AU - Anghel, Catalina
AU - Ankerst, Donna P.
AU - Azima, Helia
AU - Baertsch, Robert
AU - Ballester, Pedro J.
AU - Bare, Chris
AU - Bhandari, Vinayak
AU - Bot, Brian M.
AU - Buchardt, Ann Sophie
AU - Buturovic, Ljubomir
AU - Cao, Da
AU - Chalise, Prabhakar
AU - Chang, Billy H.W.
AU - Cho, Junwoo
AU - Chu, Tzu Ming
AU - Yates Coley, R.
AU - Conjeti, Sailesh
AU - Correia, Sara
AU - Dai, Ziwei
AU - Dai, Junqiang
AU - Dang, Cuong C.
AU - Dargatz, Philip
AU - Delavarkhan, Sam
AU - Zhu, Yuxin
N1 - Publisher Copyright:
© 2018 American Society of Clinical Oncology.
PY - 2017
Y1 - 2017
N2 - Purpose 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. Patients and Methods The comparator arms of four phase III clinical trials in first-linem CRPC 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 adversetreatment 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. Results In total, 34 separate teams submitted predictions. Seven models with statistically similar area under precision-recall curves (Bayes factor≤3) outperformed all other models. Apostchallenge 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. Conclusion This work represents a successful collaboration between 34international 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.
AB - Purpose 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. Patients and Methods The comparator arms of four phase III clinical trials in first-linem CRPC 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 adversetreatment 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. Results In total, 34 separate teams submitted predictions. Seven models with statistically similar area under precision-recall curves (Bayes factor≤3) outperformed all other models. Apostchallenge 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. Conclusion This work represents a successful collaboration between 34international 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.
UR - http://www.scopus.com/inward/record.url?scp=85030873091&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85030873091&partnerID=8YFLogxK
U2 - 10.1200/CCI.17.00018
DO - 10.1200/CCI.17.00018
M3 - Article
C2 - 30657384
AN - SCOPUS:85030873091
SN - 2473-4276
VL - 2017
SP - 1
EP - 15
JO - JCO Clinical Cancer Informatics
JF - JCO Clinical Cancer Informatics
IS - 1
ER -