Crowdsourced analysis of clinical trial data to predict amyotrophic lateral sclerosis progression

作     者：Kueffner, Robert Zach, Neta Norel, Raquel Hawe, Johann Schoenfeld, David Wang, Liuxia Li, Guang Fang, Lilly Mackey, Lester Hardiman, Orla Cudkowicz, Merit Sherman, Alexander Ertaylan, Gokhan Grosse-Wentrup, Moritz Hothorn, Torsten van Ligtenberg, Jules Macke, Jakob H. Meyer, Timm Schoelkopf, Bernhard Tran, Linh Vaughan, Rubio Stolovitzky, Gustavo Leitner, Melanie L. 

作者机构：German Res Ctr Environm Hlth Inst Bioinformat & Syst Biol Munich Germany Univ Munich Dept Informat Munich Germany Prize4Life Tel Aviv Israel Prize4Life Cambridge MA USA IBM TJ Watson Res Ctr Yorktown Hts NY USA Massachusetts Gen Hosp MGH Biostat Ctr Boston MA 02114 USA Harvard Univ Sch Med Charlestown MA USA Sentrana Inc Washington DC USA Latham&Watkins LLP Silicon Valley CA USA Stanford Univ Dept Stat Stanford CA 94305 USA Beaumont Hosp Dept Neurosci Dublin 9 Ireland Trinity Coll Dublin Dublin Ireland Massachusetts Gen Hosp Neurol Clin Res Inst Charlestown MA USA Univ Luxembourg Esch Alzette Luxembourg Ctr Syst Biomed Luxembourg Luxembourg Max Planck Inst Intelligent Syst Tubingen Germany Univ Zurich Inst Social & Prevent Med Zurich Switzerland Orca XL Problem Solvers Amsterdam Netherlands Max Planck Inst Biol Cybernet Tubingen Germany Bernstein Ctr Computat Neurosci Tubingen Germany Univ Calif Berkeley Berkeley Sch Publ Hlth Berkeley CA USA Biogen Idec Inc ALS Innovat Hub Cambridge MA USA 

出 版 物：《NATURE BIOTECHNOLOGY》 (自然生物技术)

年 卷 期：2015年第33卷第1期

页      面：51-U292页

核心收录：

学科分类：0710[理学-生物学] 071010[理学-生物化学与分子生物学] 07[理学] 0836[工学-生物工程] 

主　　题：AMYOTROPHIC lateral sclerosis PROGNOSIS DISEASE progression BLOOD pressure CLINICAL trials CREATININE CROWDSOURCING COMPUTER algorithms 

摘      要：Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease with substantial heterogeneity in its clinical presentation. This makes diagnosis and effective treatment difficult, so better tools for estimating disease progression are needed. Here, we report results from the DREAM-Phil Bowen ALS Prediction Prize4Life challenge. In this crowdsourcing competition, competitors developed algorithms for the prediction of disease progression of 1,822 ALS patients from standardized, anonymized phase 2/3 clinical trials. The two best algorithms outperformed a method designed by the challenge organizers as well as predictions by ALS clinicians. We estimate that using both winning algorithms in future trial designs could reduce the required number of patients by at least 20%. The DREAM-Phil Bowen ALS Prediction Prize4Life challenge also identified several potential nonstandard predictors of disease progression including uric acid, creatinine and surprisingly, blood pressure, shedding light on ALS pathobiology. This analysis reveals the potential of a crowdsourcing competition that uses clinical trial data for accelerating ALS research and development.