Alzheimers Disease Big Data DREAM Challenge 1
Created By Mette Peters Mette
Alzheimer's Disease Big Data DREAM Challenge #1 Launched: June 2, 2014 Closed: October 17, 2014 midnight Pacific Time See Description of Final Results The data that was provided for this challenge is not available The goal of the Alzheimer's Disease Big Data DREAM Challenge #1 (AD#1) was to apply an open science approach to rapidly identify accurate predictive AD biomarkers that can be used by the scientific, industrial and regulatory communities to improve AD diagnosis and treatment. AD#1 will be the first in a series of AD Data Challenges to leverage genetics and brain imaging in combination with cognitive assessments, biomarkers and demographic information from cohorts ranging from cognitively normal to mild cognitively impaired to individuals with AD. The Challenge considered the following questions: >Subchallenge 1: Predict the change in cognitive scores 24 months after initial assessment. >Scientific Rationale: Answers to this question will help predict cognitive trajectory and potentially provide new approaches for early diagnosis of AD. This earlier identification would allow for more efficient selection of samples for clinical trials and possibilities for earlier disease treatment. >Subchallenge 2: Predict the set of cognitively normal individuals whose biomarkers are suggestive of amyloid perturbation. >Scientific Rationale: Answers to this question will help us understand how some people maintain normal cognitive function in the presence of amyloid pathology. The biological basis of this resilience to pathology will provide important insights into the development of prevention and therapy. >Subchallenge 3: Classify individuals into diagnostic groups using MR imaging. >Scientific Rationale: If a single MR image could be used to differentiate AD patients from people with mild cognitive impairment or from healthy individuals, research can focus on the specific anatomical structures that are different between the groups. Currently, MRI data are acquired routinely in hospitals: thus a winning algorithm could potentially be retrospectively applied to existing archives of clinical data as well as to future scans without requiring additional resources or expertise. For questions about the Challenge design please contact the Challenge Organizers through the Challenge Forum The scientific aspects of this Challenge were overseen by a Scientific Advisory Board including members from the following institutions: Brigham Young University, Columbia University, G??teborg University, Harvard University, NIH-NIA, McGill University, Rush Alzheimer's Disease Center, The Alzheimer's Foundation, UCLA, UCSF, University of Cambridge, University of Oxford, University of Toronto, University of Washington and USAgainstAlzheimer's. Data Contributors Funders and Sponsors Journal Partner
Access to "Leaderboard and Final Test Data" and "Ancillary Data"
syn2665222
syn2484881