Skip to main content

Cascaded Multi-view Canonical Correlation (CaMCCo) for Early Diagnosis of Alzheimer's Disease via Fusion of Clinical, Imaging and Omic Features.

Publication ,  Journal Article
Singanamalli, A; Wang, H; Madabhushi, A; Alzheimer’s Disease Neuroimaging Initiative,
Published in: Sci Rep
August 15, 2017

The introduction of mild cognitive impairment (MCI) as a diagnostic category adds to the challenges of diagnosing Alzheimer's Disease (AD). No single marker has been proven to accurately categorize patients into their respective diagnostic groups. Thus, previous studies have attempted to develop fused predictors of AD and MCI. These studies have two main limitations. Most do not simultaneously consider all diagnostic categories and provide suboptimal fused representations using the same set of modalities for prediction of all classes. In this work, we present a combined framework, cascaded multiview canonical correlation (CaMCCo), for fusion and cascaded classification that incorporates all diagnostic categories and optimizes classification by selectively combining a subset of modalities at each level of the cascade. CaMCCo is evaluated on a data cohort comprising 149 patients for whom neurophysiological, neuroimaging, proteomic and genomic data were available. Results suggest that fusion of select modalities for each classification task outperforms (mean AUC = 0.92) fusion of all modalities (mean AUC = 0.54) and individual modalities (mean AUC = 0.90, 0.53, 0.71, 0.73, 0.62, 0.68). In addition, CaMCCo outperforms all other multi-class classification methods for MCI prediction (PPV: 0.80 vs. 0.67, 0.63).

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Sci Rep

DOI

EISSN

2045-2322

Publication Date

August 15, 2017

Volume

7

Issue

1

Start / End Page

8137

Location

England

Related Subject Headings

  • Sensitivity and Specificity
  • Proteomics
  • Neuroimaging
  • Models, Theoretical
  • Male
  • Humans
  • Genomics
  • Female
  • Cognitive Dysfunction
  • Case-Control Studies
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Singanamalli, A., Wang, H., Madabhushi, A., & Alzheimer’s Disease Neuroimaging Initiative, . (2017). Cascaded Multi-view Canonical Correlation (CaMCCo) for Early Diagnosis of Alzheimer's Disease via Fusion of Clinical, Imaging and Omic Features. Sci Rep, 7(1), 8137. https://doi.org/10.1038/s41598-017-03925-0
Singanamalli, Asha, Haibo Wang, Anant Madabhushi, and Anant Alzheimer’s Disease Neuroimaging Initiative. “Cascaded Multi-view Canonical Correlation (CaMCCo) for Early Diagnosis of Alzheimer's Disease via Fusion of Clinical, Imaging and Omic Features.Sci Rep 7, no. 1 (August 15, 2017): 8137. https://doi.org/10.1038/s41598-017-03925-0.
Singanamalli A, Wang H, Madabhushi A, Alzheimer’s Disease Neuroimaging Initiative. Cascaded Multi-view Canonical Correlation (CaMCCo) for Early Diagnosis of Alzheimer's Disease via Fusion of Clinical, Imaging and Omic Features. Sci Rep. 2017 Aug 15;7(1):8137.
Singanamalli, Asha, et al. “Cascaded Multi-view Canonical Correlation (CaMCCo) for Early Diagnosis of Alzheimer's Disease via Fusion of Clinical, Imaging and Omic Features.Sci Rep, vol. 7, no. 1, Aug. 2017, p. 8137. Pubmed, doi:10.1038/s41598-017-03925-0.
Singanamalli A, Wang H, Madabhushi A, Alzheimer’s Disease Neuroimaging Initiative. Cascaded Multi-view Canonical Correlation (CaMCCo) for Early Diagnosis of Alzheimer's Disease via Fusion of Clinical, Imaging and Omic Features. Sci Rep. 2017 Aug 15;7(1):8137.

Published In

Sci Rep

DOI

EISSN

2045-2322

Publication Date

August 15, 2017

Volume

7

Issue

1

Start / End Page

8137

Location

England

Related Subject Headings

  • Sensitivity and Specificity
  • Proteomics
  • Neuroimaging
  • Models, Theoretical
  • Male
  • Humans
  • Genomics
  • Female
  • Cognitive Dysfunction
  • Case-Control Studies