2016
DOI: 10.1016/j.jalz.2016.02.006
|View full text |Cite
|
Sign up to set email alerts
|

Crowdsourced estimation of cognitive decline and resilience in Alzheimer's disease

Abstract: Identifying accurate biomarkers of cognitive decline is essential for advancing early diagnosis and prevention therapies in Alzheimer’s Disease. The Alzheimer’s Disease DREAM Challenge was designed as a computational crowdsourced project to benchmark the current state-of-the-art in predicting cognitive outcomes in Alzheimer’s Disease based on high-dimensional, publicly available genetic and structural imaging data. This meta-analysis failed to identify a meaningful predictor developed from either data modality… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
68
0

Year Published

2016
2016
2023
2023

Publication Types

Select...
5
4

Relationship

5
4

Authors

Journals

citations
Cited by 81 publications
(70 citation statements)
references
References 33 publications
1
68
0
Order By: Relevance
“…Two Challenges have established community efforts to build predictive models based on single-nucleotide polymorphism (SNP) data, including the prediction of clinical non-response following anti-TNF (tumour necrosis factor) treatment in patients with rheumatoid arthritis 37 or the prediction of Alzheimer disease diagnosis 61 . The outcomes of these Challenges demonstrated that the genetic contribution to overall performance was minimal, suggesting that current methodologies are not able to identify and compile genetic signals given existing sample collections.…”
Section: What Have Challenges Taught Us?mentioning
confidence: 99%
See 1 more Smart Citation
“…Two Challenges have established community efforts to build predictive models based on single-nucleotide polymorphism (SNP) data, including the prediction of clinical non-response following anti-TNF (tumour necrosis factor) treatment in patients with rheumatoid arthritis 37 or the prediction of Alzheimer disease diagnosis 61 . The outcomes of these Challenges demonstrated that the genetic contribution to overall performance was minimal, suggesting that current methodologies are not able to identify and compile genetic signals given existing sample collections.…”
Section: What Have Challenges Taught Us?mentioning
confidence: 99%
“…Clinical measures of disease state that represent the complex interactions of human biology aggregated across multiple genetic and non-genetic factors tend to provide the greatest contribution to predictions. In the Alzheimer’s Disease Big Data DREAM Challenge 61 , cognitive measures of brain function greatly outperformed SNP genotypes for predicting disease status. In the Rheumatoid Arthritis Responder Challenge 37 , clinical measures of pretreatment disease severity had the greatest contribution to prediction of anti-TNF treatment response.…”
Section: What Have Challenges Taught Us?mentioning
confidence: 99%
“…Although prior studies have shown that the synaptic density and brain expression levels of multiple proteins in various biochemical pathways are correlated with resilient cognition [14,15], the molecular and genetic underpinnings of the dissociation of cognition and pathology remain poorly understood, and currently there are no known genetic or epigenetic determinants of the cognition–pathology discordance [16]. …”
Section: Introductionmentioning
confidence: 99%
“…These data underwent extensive QC as part of the AD Big Data DREAM Challenge (Allen et al, 2016) (https://www.synapse.org/#!Synapse:syn2290704/wiki/60828). Briefly, samples from Illumina Human610-Quad BeadChip and Illumina HumanOmniExpress BeadChip arrays were mapped to hg19, converted to the positive strand and filtered for minor allele frequency (removed MAF<0.05), SNP call rate (<0.98), sample call rate (<0.98), Hardy-Weinberg equilibrium (p<0.001) and relatedness.…”
Section: Methodsmentioning
confidence: 99%