PUB - Publikationen an der Universität Bielefeld

PurposeDocetaxel has a demonstrated survival benefit for patients with metastatic castration-resistantprostate cancer (mCRPC); however, 10% to 20% of patients discontinue docetaxel prematurely be-cause of toxicity-induced adverse events, and the management of risk factors for toxicity remains achallenge.PatientsandMethodsThecomparatorarmsoffourphaseIIIclinicaltrialsinfirst-linemCRPCwerecollected,annotated, and compiled, with a total of 2,070 patients. Early discontinuation was defined as treatmentstoppagewithin3monthsasaresultofadversetreatmenteffects;10%ofpatientsdiscontinuedtreatment.Wedesigned an open-data, crowd-sourced DREAM Challenge for developing models with which to predict earlydiscontinuation of docetaxel treatment. Clinical features for all four trials and outcomes for three of the fourtrials were made publicly available, with the outcomes of the fourth trial held back for unbiased modelevaluation. 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.ResultsIn total, 34 separate teams submitted predictions. Seven models with statistically similar areaunderprecision-recallcurves(Bayesfactor£3)outperformedallothermodels.Apostchallengeanalysisofrisk prediction using these seven models revealed three patient subgroups: high risk, low risk, or dis-cordant risk. Early discontinuation events were two times higher in the high-risk subgroup compared withthe low-risk subgroup. Simulation studies demonstrated that use of patient discontinuation predictionmodels could reduce patient enrollment in clinical trials without the loss of statistical power.ConclusionThisworkrepresentsasuccessfulcollaborationbetween34internationalteamsthatleveragedopen clinical trial data. Our results demonstrate that routinely collected clinical features can be used toidentify patients with mCRPC who are likely to discontinue treatment because of adverse events andestablishes a robust benchmark with implications for clinical trial design.