PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Jo, T.* ; Kim, J.* ; Bice, P.* ; Huynh, K.* ; Wang, T.* ; Arnold, M. ; Meikle, P.J.* ; Giles, C.* ; Kaddurah-Daouk, R.* ; Saykin, A.J.* ; Nho, K.* ; Kueider-Paisley, A.* ; Doraiswamy, P.M.* ; Blach, C.* ; Moseley, A.* ; Thompson, W.* ; St John-Williams, L.* ; Mahmoudiandehkhordi, S.* ; Tenenbaum, J.* ; Welsh-Balmer, K.* ; Plassman, B.* ; Risacher, S.L.* ; Alzheimer's Disease Metabolomics Consortium (ADMC) (Kastenmüller, G.) ; Han, X.* ; Baillie, R.* ; Knight, R.* ; Dorrestein, P.* ; Brewer, J.* ; Mayer, E.* ; Labus, J.* ; Baldi, P.* ; Gupta, A.* ; Fiehn, O.* ; Barupal, D.* ; Meikle, P.* ; Mazmanian, S.* ; Rader, D.* ; Kling, M.* ; Shaw, L.* ; Trojanowski, J.* ; van Duijin, C.* ; Nevado-Holgado, A.* ; Bennett, D.* ; Krishnan, R.* ; Keshavarzian, A.* ; Vogt, R.* ; Ikram, A.* ; Hankemeier, T.* ; Price, N.* ; Funk, C.* ; Baloni, P.* ; Jia, W.* ; Wishart, D.* ; Brinton, R.* ; Chang, R.* ; Farrer, L.* ; Au, R.* ; Qiu, W.* ; Würtz, P.* ; Koal, T.* ; Mangravite, L.* ; Suhre, K.* ; Newman, J.* ; Moreno, H.* ; Foroud, T.* ; Sacks, F.* ; Jansson, J.* ; Weiner, M.W.* ; Aisen, P.* ; Petersen, R.* ; Jack, C.R.* ; Jagust, W.* ; Trojanowki, J.Q.* ; Toga, A.W.* ; Beckett, L.* ; Green, R.C.* ; Morris, J.C.* ; Perrin, R.J.* ; Shaw, L.M.* ; Khachaturian, Z.* ; Carrillo, M.* ; Potter, W.* ; Barnes, L.* ; Bernard, M.* ; Gonzalez, H.* ; Ho, C.* ; Hsiao, J.K.* ; Jackson, J.* ; Masliah, E.* ; Masterman, D.* ; Okonkwo, O.* ; Perrin, R.* ; Ryan, L.* ; Silverberg, N.* ; Fleisher, A.* ; Sacrey, D.T.* ; Fockler, J.* ; Conti, C.*

Circular-SWAT for deep learning based diagnostic classification of Alzheimer's disease: Application to metabolome data.

EBioMedicine 97:104820 (2023)
Publ. Version/Full Text DOI PMC
Open Access Gold
Creative Commons Lizenzvertrag
Background: Deep learning has shown potential in various scientific domains but faces challenges when applied to complex, high-dimensional multi-omics data. Alzheimer's Disease (AD) is a neurodegenerative disorder that lacks targeted therapeutic options. This study introduces the Circular-Sliding Window Association Test (c-SWAT) to improve the classification accuracy in predicting AD using serum-based metabolomics data, specifically lipidomics. Methods: The c-SWAT methodology builds upon the existing Sliding Window Association Test (SWAT) and utilizes a three-step approach: feature correlation analysis, feature selection, and classification. Data from 997 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) served as the basis for model training and validation. Feature correlations were analyzed using Weighted Gene Co-expression Network Analysis (WGCNA), and Convolutional Neural Networks (CNN) were employed for feature selection. Random Forest was used for the final classification. Findings: The application of c-SWAT resulted in a classification accuracy of up to 80.8% and an AUC of 0.808 for distinguishing AD from cognitively normal older adults. This marks a 9.4% improvement in accuracy and a 0.169 increase in AUC compared to methods without c-SWAT. These results were statistically significant, with a p-value of 1.04 × 10ˆ-4. The approach also identified key lipids associated with AD, such as Cer(d16:1/22:0) and PI(37:6). Interpretation: Our results indicate that c-SWAT is effective in improving classification accuracy and in identifying potential lipid biomarkers for AD. These identified lipids offer new avenues for understanding AD and warrant further investigation. Funding: The specific funding of this article is provided in the acknowledgements section.
Impact Factor
Scopus SNIP
Altmetric
11.100
0.000
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Journal article
Document type Scientific Article
Keywords Alzheimer's Disease ; Deep Learning ; Lipidomics ; Machine Learning ; Metabolomics; Neural-networks
Language english
Publication Year 2023
HGF-reported in Year 2023
ISSN (print) / ISBN 2352-3964
e-ISSN 2352-3964
Journal EBioMedicine
Quellenangaben Volume: 97, Issue: , Pages: , Article Number: 104820 Supplement: ,
Publisher Elsevier
Publishing Place Amsterdam [u.a.]
Reviewing status Peer reviewed
Institute(s) Institute of Computational Biology (ICB)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-503891-001
Grants NIA NIH HHS
DOI 10.1016/j.ebiom.2023.104820
WOS ID 001100934400001
Scopus ID 85173462324
PubMed ID 37806288
Erfassungsdatum 2023-10-18
[➜Report correction]