Alzheimers Disease Big Data DREAM Challenge 1

Created By Mette Peters Mette
Leave us your input on future AD Challenges Welcome to the AD Challenge #1:Over 5 million Americans and almost 40 million people globally are currently afflicted with Alzheimer?s disease (AD). These numbers are growing rapidly as demography drives population aging around the world, yet there are no disease-modifying therapies available. Much of the potential for interrogating disparate but intersecting datasets in AD-related epidemiological, biological, imaging, clinical and genetics data remains untapped. While significant efforts have been made to collect and generate large comprehensive datasets walled gardens inhibits the pooling of data from different sources and cross discipline collaboration. Experts on genetics, imaging, systems biology, neurobiology, or disease pathology rarely work together, even when they are studying the same organ, the same disease or the same pathological process. Likewise, the ability to pool multiple datasets remains a large hurdle that leaves the combined value of AD datasets something that has not yet been fully exploited. In order to take full advantage of both data and human expertise we need to enable an open diverse community where data access is simple and people are incentivized to share. To address the global burden of AD and encourage collaboration in finding solutions, the Global CEO Initiative on Alzheimer?s Disease has joined with Sage/DREAM to initiate an AD Challenge to identify better predictors of AD risk in pre-clinical populations. This is a multi-phase effort to identify early accurate predictive bio-markers that can inform the scientific, industrial and regulatory communities about the disease. We invite you to participate in AD Challenge #1 will by considering one or both of the following questions: Subchallenge 1: What model best predicts change over time in AD cognitive scores using all available test and adjacent data? Subchallenge 2: What model best predicts discordance between biomarkers suggestive of amyloid perturbations and lack of cognitive impairment? This Challenge is expected to open spring 2014 Should you have any questions related to the challenge, please visit our Alzheimer's Disease Big Data DREAM Challenge #1 Community Forum. The Data: The training data is from the Alzheimer?s Disease Neuroimaging Initiative (ADNI). This is a longitudinal study with biannual assessments. Data consist of cognitive evaluations, clinical and demographic information, multiple imaging modalities, biomarkers, SNP and Whole Genome Sequencing data on subjects who range from cognitively normal to mild cognitive impairment and AD. The specific ADNI data files needed for each subchallenge will be posted before the Challenge is launched. Information about the test data will be coming. Participation:Challenge organizers expect to open this Challenge spring 2014, but we invite you to sign up for the Challenge any time. Once the Challenge is launched you will be sent a message with further instructions. Registration: Interested participants must first register for this Challenge following these steps: Click the "JOIN" button at the top of this page. Create a Synapse account (unless you already have one). Review and agree to the DREAM8.5 Challenge Rules. Once you have completed these steps a message will pop-up on your screen confirming that you are registered for the Challenge. Registration for the challenge will place you on a Synapse Team containing all registered users. You can view the list on the Alzheimer's Challenge #1 Participants team page, also accessible from the "My Teams" section of your home page. You may review the DREAM8.5 Challenge rules here: syn2295117 Accessing the data: Access to the training data will take place through a request to ADNI. Challenge participants must agree to the terms of the ADNI Data Use Agreement and are encouraged to use the statement below to described their proposed analysis in the ADNI Data Access Application. I request access to the ADNI data in order to participate in the Alzheimer?s Disease Big Data DREAM Challenge #1. The goal of this Challenge is to use a crowd-based competition framework to develop validated molecular predictors of cognitive decline in Alzheimer's disease and predictors of discordance between amyloid perturbation and cognitive function. Please note that a curated version of the ADNI data with the specific files relevant to answering the proposed questions will be created. These files will be made available in LONI, but not until just before the Challenge launch. You will be notified when the Challenge launches how to identify these files Funders: