Artykuł w czasopiśmie
Brak miniatury
Licencja
ClosedAccessDostęp zamknięty
 

Prediction of overall survival for patients with metastatic castration-resistant prostate cancer: development of a prognostic model through a crowdsourced challenge with open clinical trial data

Uproszczony widok
dc.abstract.enSummary Background Improvements to prognostic models in metastatic castration-resistant prostate cancer have the potential to augment clinical trial design and guide treatment strategies. In partnership with Project Data Sphere, a not-for-profit initiative allowing data from cancer clinical trials to be shared broadly with researchers, we designed an open-data, crowdsourced, DREAM (Dialogue for Reverse Engineering Assessments and Methods) challenge to not only identify a better prognostic model for prediction of survival in patients with metastatic castration-resistant prostate cancer but also engage a community of international data scientists to study this disease. Methods Data from the comparator arms of four phase 3 clinical trials in first-line metastatic castration-resistant prostate cancer were obtained from Project Data Sphere, comprising 476 patients treated with docetaxel and prednisone from the ASCENT2 trial, 526 patients treated with docetaxel, prednisone, and placebo in the MAINSAIL trial, 598 patients treated with docetaxel, prednisone or prednisolone, and placebo in the VENICE trial, and 470 patients treated with docetaxel and placebo in the ENTHUSE 33 trial. Datasets consisting of more than 150 clinical variables were curated centrally, including demographics, laboratory values, medical history, lesion sites, and previous treatments. Data from ASCENT2, MAINSAIL, and VENICE were released publicly to be used as training data to predict the outcome of interest—namely, overall survival. Clinical data were also released for ENTHUSE 33, but data for outcome variables (overall survival and event status) were hidden from the challenge participants so that ENTHUSE 33 could be used for independent validation. Methods were evaluated using the integrated time-dependent area under the curve (iAUC). The reference model, based on eight clinical variables and a penalised Cox proportional-hazards model, was used to compare method performance. Further validation was done using data from a fifth trial—ENTHUSE M1—in which 266 patients with metastatic castration-resistant prostate cancer were treated with placebo alone. Findings 50 independent methods were developed to predict overall survival and were evaluated through the DREAM challenge. The top performer was based on an ensemble of penalised Cox regression models (ePCR), which uniquely identified predictive interaction effects with immune biomarkers and markers of hepatic and renal function. Overall, ePCR outperformed all other methods (iAUC 0·791; Bayes factor >5) and surpassed the reference model (iAUC 0·743; Bayes factor >20). Both the ePCR model and reference models stratified patients in the ENTHUSE 33 trial into high-risk and low-risk groups with significantly different overall survival (ePCR: hazard ratio 3·32, 95% CI 2·39–4·62, p<0·0001; reference model: 2·56, 1·85–3·53, p<0·0001). The new model was validated further on the ENTHUSE M1 cohort with similarly high performance (iAUC 0·768). Meta-analysis across all methods confirmed previously identified predictive clinical variables and revealed aspartate aminotransferase as an important, albeit previously under-reported, prognostic biomarker. Interpretation Novel prognostic factors were delineated, and the assessment of 50 methods developed by independent international teams establishes a benchmark for development of methods in the future. The results of this effort show that data-sharing, when combined with a crowdsourced challenge, is a robust and powerful framework to develop new prognostic models in advanced prostate cancer. Funding Sanofi US Services, Project Data Sphere.
dc.affiliationUniwersytet Warszawski
dc.contributor.authorRudnicki, Witold
dc.contributor.authorAbdallah, Kald
dc.contributor.authorAirola, Antti
dc.contributor.authorAittokallio, Tero
dc.contributor.authorAnghel, Catalina
dc.contributor.authorAnkerst, Donna P
dc.contributor.authorAzima, Helia
dc.contributor.authorBaertsch, Robert
dc.contributor.authorBallester, Pedro J
dc.contributor.authorBare, J Christopher
dc.contributor.authorDunbar, Maria Bekker-Nielsen
dc.contributor.authorBhandari, Vinayak
dc.contributor.authorBot, Brian M
dc.contributor.authorBuchardt, Ann-Sophie
dc.contributor.authorButurovic, Ljubomir
dc.contributor.authorCao, Da
dc.contributor.authorChalise, Prabhakar
dc.contributor.authorChang, Billy HW
dc.contributor.authorCho, Junwoo
dc.contributor.authorChu, Tzu-Ming
dc.contributor.authorColey, R Yates
dc.contributor.authorConjeti, Sailesh
dc.contributor.authorCorreia, Sara
dc.contributor.authorCostello, James C
dc.contributor.authorDai, Junqiang
dc.contributor.authorDai, Ziwei
dc.contributor.authorDang, Cuong C
dc.contributor.authorDargatz, Philip
dc.contributor.authorDelavarkhan, Sam
dc.contributor.authorDeng, Detian
dc.contributor.authorDhanik, Ankur
dc.contributor.authorDu, Yu
dc.contributor.authorElangovan, Aparna
dc.contributor.authorEllis, Shellie
dc.contributor.authorElo, Laura L
dc.contributor.authorEspiritu, Shadrielle M
dc.contributor.authorFan, Fan
dc.contributor.authorFarshi, Ashkan B
dc.contributor.authorFreitas, Ana
dc.contributor.authorFridley, Brooke
dc.contributor.authorFriend, Stephen
dc.contributor.authorFuchs, Christiane
dc.contributor.authorGofer, Eyal
dc.contributor.authorGolińska, Agnieszka
dc.contributor.authorGraw, Stefan
dc.contributor.authorGreiner, Russ
dc.contributor.authorGuan, Yuanfang
dc.contributor.authorGuinney, Justin
dc.contributor.authorGuo, Jing
dc.contributor.authorGupta, Pankaj
dc.contributor.authorGuyer, Anna I
dc.contributor.authorHan, Jiawei
dc.contributor.authorHansen, Niels R
dc.contributor.authorHirvonen, Outi
dc.contributor.authorHuang, Barbara
dc.contributor.authorHuang, Chao
dc.contributor.authorHwang, Jinseub
dc.contributor.authorIbrahim, Joseph G
dc.contributor.authorJayaswal, Vivek
dc.contributor.authorJeon, Jouhyun
dc.contributor.authorJi, Zhicheng
dc.contributor.authorJuvvadi, Deekshith
dc.contributor.authorJyrkkiö, Sirkku
dc.contributor.authorKanigel-Winner, Kimberly
dc.contributor.authorKatouzian, Amin
dc.contributor.authorKazanov, Marat D
dc.contributor.authorKhan, Suleiman A
dc.contributor.authorKhayyer, Shahin
dc.contributor.authorKim, Dalho
dc.contributor.authorKoestler, Devin
dc.contributor.authorKokowicz, Fernanda
dc.contributor.authorKondofersky, Ivan
dc.contributor.authorKrautenbacher, Norbert
dc.contributor.authorKrstajic, Damjan
dc.contributor.authorKumar, Luke
dc.contributor.authorKurz, Christoph
dc.contributor.authorKyan, Matthew
dc.contributor.authorLaajala, Teemu D
dc.contributor.authorLaimighofer, Michael
dc.contributor.authorLee, Eunjee
dc.contributor.authorLesiński, Wojciech
dc.contributor.authorLi, Miaozhu
dc.contributor.authorLi, Ye
dc.contributor.authorLian, Qiuyu
dc.contributor.authorLiang, Xiaotao
dc.contributor.authorLim, Minseong
dc.contributor.authorLin, Henry
dc.contributor.authorLin, Xihui
dc.contributor.authorLu, Jing
dc.contributor.authorMahmoudian, Mehrad
dc.contributor.authorManshaei, Roozbeh
dc.contributor.authorMeier, Richard
dc.contributor.authorMiljkovic, Dejan
dc.contributor.authorMirtti, Tuomas
dc.contributor.authorMnich, Krzysztof
dc.contributor.authorNavab, Nassir
dc.contributor.authorNeto, Elias Chaibub
dc.contributor.authorNewton, Yulia
dc.contributor.authorNorman, Thea
dc.contributor.authorPahikkala, Tapio
dc.contributor.authorPal, Subhabrata
dc.contributor.authorPark, Byeongju
dc.contributor.authorPatel, Jaykumar
dc.contributor.authorPathak, Swetabh
dc.contributor.authorPattin, Alejandrina
dc.contributor.authorPeddinti, Gopal
dc.contributor.authorPeng, Jian
dc.contributor.authorPetersen, Anne H
dc.contributor.authorPhilip, Robin
dc.contributor.authorPiccolo, Stephen R
dc.contributor.authorPolewko-Klim, Aneta
dc.contributor.authorPölsterl, Sebastian
dc.contributor.authorRao, Karthik
dc.contributor.authorRen, Xiang
dc.contributor.authorRocha, Miguel
dc.contributor.authorRyan, Charles J
dc.contributor.authorRyu, Hyunnam
dc.contributor.authorSartor, Oliver
dc.contributor.authorScher, Howard I
dc.contributor.authorScherb, Hagen
dc.contributor.authorSehgal, Raghav
dc.contributor.authorSeyednasrollah, Fatemeh
dc.contributor.authorShang, Jingbo
dc.contributor.authorShao, Bin
dc.contributor.authorShen, Liji
dc.contributor.authorSher, Howard
dc.contributor.authorShiga, Motoki
dc.contributor.authorSokolov, Artem
dc.contributor.authorSong, Lei
dc.contributor.authorSoule, Howard
dc.contributor.authorStolovitzky, Gustavo
dc.contributor.authorStuart, Josh
dc.contributor.authorSun, Ren
dc.contributor.authorSweeney, Christopher J
dc.contributor.authorSöllner, Julia F
dc.contributor.authorTahmasebi, Nazanin
dc.contributor.authorTan, Kar-Tong
dc.contributor.authorTomaziu, Lisbeth
dc.contributor.authorUsset, Joseph
dc.contributor.authorVang, Yeeleng S
dc.contributor.authorVega, Roberto
dc.contributor.authorVieira, Vitor
dc.contributor.authorWang, David
dc.contributor.authorWang, Difei
dc.contributor.authorWang, Junmei
dc.contributor.authorWang, Lichao
dc.contributor.authorWang, Sheng
dc.contributor.authorWang, Tao
dc.contributor.authorWang, Yue
dc.contributor.authorWolfinger, Russ
dc.contributor.authorWong, Chris
dc.contributor.authorWu, Zhenke
dc.contributor.authorXiao, Jinfeng
dc.contributor.authorXiaohui, Xie
dc.contributor.authorXie, Yang
dc.contributor.authorXin, Doris
dc.contributor.authorYang, Hojin
dc.contributor.authorYu, Nancy
dc.contributor.authorYu, Thomas
dc.contributor.authorYu, Xiang
dc.contributor.authorZahedi, Sulmaz
dc.contributor.authorZanin, Massimiliano
dc.contributor.authorZhang, Chihao
dc.contributor.authorZhang, Jingwen
dc.contributor.authorZhang, Shihua
dc.contributor.authorZhang, Yanchun
dc.contributor.authorZhou, Fang Liz
dc.contributor.authorZhu, Hongtu
dc.contributor.authorZhu, Shanfeng
dc.contributor.authorZhu, Yuxin
dc.date.accessioned2024-01-25T17:32:58Z
dc.date.available2024-01-25T17:32:58Z
dc.date.issued2017
dc.description.financeNie dotyczy
dc.description.number1
dc.description.volume18
dc.identifier.doi10.1016/S1470-2045(16)30560-5
dc.identifier.issn1470-2045
dc.identifier.urihttps://repozytorium.uw.edu.pl//handle/item/116916
dc.identifier.weblinkhttp://www.sciencedirect.com/science/article/pii/S1470204516305605
dc.languageeng
dc.relation.ispartofThe Lancet Oncology
dc.relation.pages132-142
dc.rightsClosedAccess
dc.sciencecloudnosend
dc.titlePrediction of overall survival for patients with metastatic castration-resistant prostate cancer: development of a prognostic model through a crowdsourced challenge with open clinical trial data
dc.typeJournalArticle
dspace.entity.typePublication