Format

Send to

Choose Destination
Nat Biotechnol. 2015 Jan;33(1):51-7. doi: 10.1038/nbt.3051. Epub 2014 Nov 2.

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

Author information

1
1] Institute of Bioinformatics and Systems Biology, German Research Center for Environmental Health, Munich, Germany. [2] Department of Informatics, Ludwig-Maximilians-University, Munich, Germany.
2
Prize4Life, Tel Aviv, Israel and Cambridge, Massachusetts, USA.
3
IBM T.J. Watson Research Center, Yorktown Heights, New York, USA.
4
Department of Informatics, Ludwig-Maximilians-University, Munich, Germany.
5
1] MGH Biostatistics Center, Massachusetts General Hospital, Boston, Massachusetts, USA. [2] Harvard Medical School, Charlestown, Massachusetts, USA.
6
Sentrana Inc., Washington, DC, USA.
7
Latham&Watkins LLP, Silicon Valley, California, USA.
8
Department of Statistics, Stanford University, Stanford, California, USA.
9
Department of Neuroscience, Beaumont Hospital and Trinity College Dublin, Dublin, Ireland.
10
Neurological Clinical Research Institute, Massachusetts General Hospital, Charlestown, Massachusetts, USA.
11
Luxembourg Centre for Systems Biomedicine, University of Luxembourg, Esch/Alzette, Luxembourg.
12
Max Planck Institute for Intelligent Systems, Tübingen, Germany.
13
Institute of Social- and Preventive Medicine, University of Zürich, Zürich, Switzerland.
14
Orca XL Problem Solvers, Amsterdam, the Netherlands.
15
Max Planck Institute for Biological Cybernetics and Bernstein Center for Computational Neuroscience, Tübingen, Germany.
16
Berkeley School of Public Health, University of California, Berkeley, California, USA.
17
1] Prize4Life, Tel Aviv, Israel and Cambridge, Massachusetts, USA. [2] ALS Innovation Hub, Biogen Idec, Cambridge, Massachusetts, USA.

Abstract

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.

PMID:
25362243
DOI:
10.1038/nbt.3051
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center