"A DREAM Challenge to Build Prediction Models for Short-term Discontinu" by Fatemeh Seyednasrollah, Devin C. Koestler et al.
 

Keywords

Adolescent, Adult, Aged, Aged, 80 and over, Antineoplastic Agents/administration & dosage, Antineoplastic Combined Chemotherapy Protocols/adverse effects, Clinical Trials as Topic, Docetaxel/administration & dosage, Humans, Male, Meta-Analysis as Topic, Middle Aged, Models, Theoretical, Prednisone, Prognosis, Prostatic Neoplasms, Castration-Resistant/drug therapy, Time Factors, Treatment Outcome, Young Adult

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.

Original Publication Citation

Seyednasrollah F, Koestler DC, Wang T, Piccolo SR, Vega R, Greiner R, Fuchs C, Gofer E, Kumar L, Wolfinger RD, Winner KK, Bare C, Neto EC, Yu T, Shen L, Abdallah K, Norman T, Stolovitzky G, PCC-DREAM Community, Soule H, Sweeney CJ, Ryan CJ, Scher HI, Sartor O, Elo LL, Zhou FL, Guinney J, Costello JC. A DREAM Challenge to build prediction models for short-term discontinuation of docetaxel in metastatic castration-resistant prostate cancer. JCO Clinical Cancer Informatics; published online August 4, 2017. DOI: 10.1200/CCI.17.00018

Document Type

Peer-Reviewed Article

Publication Date

2017-08-04

Publisher

American Society of Clinical Oncology

Language

English

College

Life Sciences

Department

Biology

University Standing at Time of Publication

Associate Professor

Download

Included in

Biology Commons

Share

COinS