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

Seyednasrollah F, Wang T, Piccolo SR, Vega R, Greiner R, Fuchs C, Gofer E, Kumar L, Winner KK, Yu T, Shen L, Stolovitzky G, Sweeney CJ, Ryan CJ, Scher HI, Sartor O, Elo LL, Zhou FL, Costello JC, Abdallah K, Airola A, Aittokallio T, Anghel C, Ankerst DP, Azima H, Baertsch R, Ballester PJ, Bare C, Bhandari V, Bot BM, Buchardt AS, Buturovic L, Cao D, Chalise P, Chang BH, Cho J, Chu TM, Yates Coley R, Conjeti S, Correia S, Dai Z, Dai J, Dang CC, Dargatz P, Delavarkhan S, Deng D, Dhanik A, Du Y, Elangovan A, Ellis S, Espiritu SM, Fan F, Farshi AB, Freitas A, Fridley B, Golińska AK, Graw S, Guinney J, Guo J, Gupta P, Guyer AI, Han J, Hansen NR, Hirvonen O, Huang B, Huang C, Hwang J, Ibrahim JG, Jayaswal V, Jeon J, Ji Z, Juvvadi D, Jyrkkiö S, Kanigel-Winner K, Katouzian A, Kazanov MD, Khan SA, Khayyer S, Kim D, Koestler D, Kokowicz F, Kondofersky I, Krstajic D, Persona C, Kurz C, Kyan M, Laajala TD, Laimighofer M, Lee E, Lesiński W, Li M, Li Y, Lian Q, Liang X, Lim M, Lin H, Lin X, Lu J, Mahmoudian M, Manshaei R, Meier R, Miljkovic D, Mirtti T, Mnich K, Navab N, Neto EC, Newton Y, Norman T, Pahikkala T, Pal S, Park B, Patel J, Pathak S, Pattin A, Peddinti G, Peng J, Petersen AH, Philip R, Pölsterl S, Polewko-Klim A, Rao K, Ren X, Rocha M, Rudnicki WR, Ryu H, Scherb H, Sehgal R, Nasrollah FS, Shang J, Shao B, Sher H, Shiga M, Sokolov A, Söllner JF, Song L, Soule H, Stuart J, Sun R, Tahmasebi N, Tan KT, Tomaziu L, Usset J, Vang YS, Vieira V, Wang D, Wang D, Wang J, Wang L, Wang S, Wang Y, Wolfinger R, Wong C, Wu Z, Xiao J, Xie X, Xin D, Yang H, Yu N, Yu X, Zahedi S, Zanin M, Zhang C, Zhang J, Zhang S, Zhang Y, Zhu H, Zhu S, Zhu Y (2017)

Publication Type: Journal article

Publication year: 2017

Journal

Book Volume: 2017

Pages Range: 1-15

Journal Issue: 1

DOI: 10.1200/CCI.17.00018

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.

Involved external institutions

University of Copenhagen Denmark (DK) Turku University Hospital / Turun yliopistollinen keskussairaala (TYKS) Finland (FI) Turku Bioscience Finland (FI) Ontario Institute for Cancer Research Canada (CA) University of Texas Southwestern Medical Center (UT Southwestern) United States (USA) (US) Brigham Young University United States (USA) (US) University of Alberta Canada (CA) Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (HMGU) / Helmholtz Munich Germany (DE) Bristol-Myers Squibb United States (USA) (US) Hebrew University of Jerusalem Israel (IL) Technische Universität München (TUM) Germany (DE) Toronto Metropolitan University / Ryerson University Canada (CA) University of California Santa Cruz United States (USA) (US) Sage Bionetworks United States (USA) (US) Johns Hopkins University (JHU) United States (USA) (US) Jeevomics Private Limited India (IN) University of Colorado Anschutz Medical Campus United States (USA) (US) University of Pennsylvania (UPenn) United States (USA) (US) University of North Carolina at Chapel Hill United States (USA) (US) University of Białystok Poland (PL) University of Kansas Medical Center United States (USA) (US) The Chinese University of Hong Kong (CUHK) China (CN) Institute for Information Transmission Problems of Russian Academy of Sciences (Kharkevich Institute, IITP RAS) / Институт проблем передачи информации имени А. А. Харкевича (ИППИ) РАН Russian Federation (RU) Kyungpook National University Korea, Republic of (KR) Duke University United States (USA) (US) Fudan University / 复旦大学 China (CN) Helsingin yliopisto / University of Helsinki Finland (FI) Tsinghua University China (CN) Universidade do Minho Portugal (PT) Peking University (PKU) / 北京大学 China (CN) University of Illinois at Urbana-Champaign United States (USA) (US) Daegu University / 대구대학교 Korea, Republic of (KR) Johannes Wesling Klinikum Minden Germany (DE) Åbo Akademi University Finland (FI) CRCM Centre de Recherche en Cancérologie de Marseille France (FR) Sanofi-Aventis Groupe France (FR) Regeneron Pharmaceuticals, Inc. United States (USA) (US) IBM Thomas J. Watson Research Center United States (USA) (US) The University of Melbourne Australia (AU) Johns Hopkins Hospital United States (USA) (US) Harvard University United States (USA) (US) University of California San Francisco (UCSF) United States (USA) (US) Weill Cornell Medicine United States (USA) (US) Tulane University United States (USA) (US) National University of Singapore (NUS) Singapore (SG) University of Cambridge United Kingdom (GB) SAS Institute United States (USA) (US) Federal University of Santa Catarina / Universidade Federal de Santa Catarina (UFSC) Brazil (BR) Gifu University / 岐阜大学 Japan (JP) University of Michigan United States (USA) (US) National Cancer Institute (NCI) United States (USA) (US) Prostate Cancer Foundation (PCF) United States (USA) (US) Georgetown University Medical Center (GUMC) United States (USA) (US) York University Canada (CA) University of Toronto Canada (CA) The Innaxis Foundation and Research Institute Spain (ES) National Center for Mathematics and Interdisciplinary Sciences (NCMIS) / 中国科学院国家数学与交叉科学中心 China (CN)

How to cite

APA:

Seyednasrollah, F., Wang, T., Piccolo, S.R., Vega, R., Greiner, R., Fuchs, C.,... Zhu, Y. (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

MLA:

Seyednasrollah, Fatemeh, et al. "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 (2017): 1-15.

BibTeX: Download