조태호 (Indiana University School of Medicine) | 한빛사논문 > 한빛사

한빛사논문

조회519

Indiana University School of Medicine

CV File 175 kb

EBioMedicine, Oct 06 2023, 97 S2352-3964(23)00386-9 | https://doi.org/10.1016/j.ebiom.2023.104820 Circular-SWAT for deep learning based diagnostic classification of Alzheimer's disease: application to metabolome data.

Taeho Jo ^a,b, Junpyo Kim ^a,c, Paula Bice ^a,b, Kevin Huynh ^d,e,k, Tingting Wang ^d,e,k, Matthias Arnold ^f,g, Peter J. Meikle ^d,e,k,h, Corey Giles ^d, Rima Kaddurah-Daouk ^f,i,j, Andrew J. Saykin ^a,b,j, Kwangsik Nho ^a,b,l ; Alzheimer's Disease Metabolomics Consortium (ADMC); Alzheimer's Disease Neuroimaging Initiative (ADNI)

^aDepartment of Radiology and Imaging Sciences, Indiana University School of Medicine, Indianapolis, IN, 46202, USA

^bIndiana Alzheimer Disease Research Center, Indiana University School of Medicine, Indianapolis, IN, 46202, USA

^cMedical Research Institute, Sungkyunkwan University, School of Medicine, Seoul, South Korea

^dBaker Heart and Diabetes Institute, Melbourne, 3004, Victoria, Australia

^eBaker Department of Cardiometabolic Health, University of Melbourne, Parkville, 3010, Victoria, Australia

^fInstitute of Computational Biology, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, 85764, Germany

^gBaker Department of Cardiovascular Research Translation and Implementation, La Trobe University, Bundoora, 3086, Victoria, Australia

^hDuke Institute of Brain Sciences, Duke University, Durham, NC, 27710, USA

ⁱDepartment of Medicine, Duke University, Durham, NC, 27710, USA

^jDepartment of Medical and Molecular Genetics, Indiana University School of Medicine, Indianapolis, IN, 46202, USA

^kDepartment of Psychiatry and Behavioral Sciences, Duke University, Durham, NC, 27710, USA

^lCenter for Computational Biology and Bioinformatics, Indiana University School of Medicine, Indianapolis, IN, 46202, USA

Corresponding authors: Andrew J. Saykin, Kwangsik Nho

Abstract

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.

논문정보

형식Research article
게재일2023년 10월 (BRIC 등록일 2023-10-12)
연구진국내+국외 연구진
분야 생명과학 > 생명과학 기타

댓글 작성 로그인

CV 열람하기

연락처 보기