A DREAM challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration- resistant prostate cancer

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Standard

A DREAM challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration- resistant prostate cancer. / Prostate Cancer DREAM Challenge Community.

I: JCO clinical cancer informatics, Bind 2017, Nr. 1, 2017, s. 1-15.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Harvard

Prostate Cancer DREAM Challenge Community 2017, 'A DREAM challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration- resistant prostate cancer', JCO clinical cancer informatics, bind 2017, nr. 1, s. 1-15. https://doi.org/10.1200/CCI.17.00018

APA

Prostate Cancer DREAM Challenge Community (2017). A DREAM challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration- resistant prostate cancer. JCO clinical cancer informatics, 2017(1), 1-15. https://doi.org/10.1200/CCI.17.00018

Vancouver

Prostate Cancer DREAM Challenge Community. A DREAM challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration- resistant prostate cancer. JCO clinical cancer informatics. 2017;2017(1):1-15. https://doi.org/10.1200/CCI.17.00018

Author

Prostate Cancer DREAM Challenge Community. / A DREAM challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration- resistant prostate cancer. I: JCO clinical cancer informatics. 2017 ; Bind 2017, Nr. 1. s. 1-15.

Bibtex

@article{866839c66a1b4fa9b573f730a7fe9d08,
title = "A DREAM challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration- resistant prostate cancer",
abstract = "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.",
author = "Fatemeh Seyednasrollah and Koestler, {Devin C.} and Tao Wang and Piccolo, {Stephen R.} and Roberto Vega and Russell Greiner and Christiane Fuchs and Eyal Gofer and Luke Kumar and Wolfinger, {Russell D.} and Winner, {Kimberly Kanigel} and Neto, {Elias Chaibub} and Thomas Yu and Liji Shen and Gustavo Stolovitzky and Soule, {Howard R.} and Sweeney, {Christopher J.} and Ryan, {Charles J.} and Scher, {Howard I.} and Oliver Sartor and Elo, {Laura L.} and Zhou, {Fang Liz} and Costello, {James C.} and Kald Abdallah and Antti Airola and Tero Aittokallio and Catalina Anghel and Ankerst, {Donna P.} and Helia Azima and Robert Baertsch and Ballester, {Pedro J.} and Chris Bare and Vinayak Bhandari and Bot, {Brian M.} and Buchardt, {Ann Sophie} and Ljubomir Buturovic and Da Cao and Prabhakar Chalise and Chang, {Billy H.W.} and Junwoo Cho and Chu, {Tzu Ming} and {Yates Coley}, R. and Sailesh Conjeti and Sara Correia and Ziwei Dai and Junqiang Dai and Dang, {Cuong C.} and Fan Fan and Hansen, {Niels R.} and Petersen, {Anne H.} and {Prostate Cancer DREAM Challenge Community}",
year = "2017",
doi = "10.1200/CCI.17.00018",
language = "English",
volume = "2017",
pages = "1--15",
journal = "JCO clinical cancer informatics",
issn = "2473-4276",
publisher = "American Society of Clinical Oncology",
number = "1",

}

RIS

TY - JOUR

T1 - A DREAM challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration- resistant prostate cancer

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 - Fan, Fan

AU - Hansen, Niels R.

AU - Petersen, Anne H.

AU - Prostate Cancer DREAM Challenge Community

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.

U2 - 10.1200/CCI.17.00018

DO - 10.1200/CCI.17.00018

M3 - Journal article

C2 - 30657384

VL - 2017

SP - 1

EP - 15

JO - JCO clinical cancer informatics

JF - JCO clinical cancer informatics

SN - 2473-4276

IS - 1

ER -

ID: 238449441