Connectionists: Fwd: ADHD-200 Global Competition

[Francisco Pereira]

I think this may be of interest to some of the members of the list, my
apologies if you receive this multiple times.

Francisco


---------- Forwarded message ----------
From: Michael Milham <milham01 at gmail.com>
Date: Wed, Apr 6, 2011 at 10:20 AM
Subject: [ML-news] ADHD-200 Global Competition
To: ml-news at googlegroups.com


Despite advances in understanding aspects of the etiology of some
developmental neuropsychiatric disorders, translating these insights
into clinical practice has remained daunting. Significant obstacles
include the lack of reliable and valid biomarkers and an insufficient
understanding of the underlying pathophysiology. We believe that a
community-wide effort focused on advancing functional and structural
imaging examinations of the developing brain will accelerate the rate
at which neuroscience can inform clinical practice.

To recruit the global scientific community to address childhood
psychiatric illness, we are pleased to announce the 'ADHD-200 Global
Competition.' Investigators across all disciplines and at all levels
of training are invited to participate in a competition to identify:

1) The Highest Performance Imaging-Based Diagnostic Classification
Algorithm for ADHD. Participants will develop and train a diagnostic
classifier (ADHD-Combined type, ADHD-Inattentive type, typically
developing control) based on the ADHD-200 datasets
(http://fcon_1000.projects.nitrc.org/indi/adhd200/index.html) that
contain structural and resting-state fMRI datasets for 285 individuals
diagnosed with ADHD and 491 typically developing individuals. On July
1, 2011 a test set comprised of previously unreleased datasets will be
distributed via NITRC, without diagnostic labels. Participants will be
asked to submit their diagnostic classifications for the unlabeled
datasets by August 15th, 2011, along with a brief report outlining
their analytic approach. The winning entry will be chosen based upon
prediction accuracy. Note: The test set will include unreleased
datasets from sites included in the ADHD-200 release, as well as
additional sites whose data were not included in the release.

2) The Most Innovative Neuroscientific Examination of ADHD.
Participants are invited to use the ADHD-200 datasets released on
March 1st to address the pathophysiology of ADHD, and to submit a
novel manuscript reporting their findings by August 1, 2011. Each
entry will be independently scored by five 'blind' judges based upon
innovation, potential impact, and elegance of analytic approach. A
single winning entry will be selected based upon their composite
score.

Eligibility: Individuals from all disciplines and training levels are
invited to participate. Team-based and single-person entries are
allowed. For team-based entries, a team representative should be
specified for the purpose of communications and travel to Washington
D.C. if selected as the winning entry. Individuals or teams interested
in participating should notify Michael Milham of their intent by July
1, 2011 (MMilham at NKI.RFMH.ORG); entry submission directions will be
provided at that time.

Award: ADHD-200 global competition winners will be invited to attend
the National Institute on Drug Abuse (NIDA) pre-conference symposium
preceding the Society for Neuroscience Annual Meeting in Washington
D.C., where they will be publicly recognized for their accomplishment
and given the opportunity to present their work. Travel costs for a
representative from each winning entry will be covered courtesy of
NIDA.

Award Notification Date: September 1, 2011


Sincerely,

Mike

-----------------------------------------------------------------------------------------
Michael P. Milham, MD, PhD

Research Psychiatrist
Nathan S. Kline Institute for Psychiatric Research

Leon Levy Assistant Professor of Child and Adolescent Psychiatry
NYU Langone Medical Center

Associate Director, Phyllis Green and Randolph Cowen Institute for
Pediatric Neuroscience, NYU Child Study Center

--
You received this message because you are subscribed to the Google
Groups "Machine Learning News" group.
To post to this group, send email to ml-news at googlegroups.com.
To unsubscribe from this group, send email to
ml-news+unsubscribe at googlegroups.com.
For more options, visit this group at
http://groups.google.com/group/ml-news?hl=en.