skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Diagnosis and prognosis of Alzheimer's disease using brain morphometry and white matter connectomes

Abstract

Accurate, reliable prediction of risk for Alzheimer's disease (AD) is essential for early, disease-modifying therapeutics. Multimodal MRI, such as structural and diffusion MRI, is likely to contain complementary information of neurodegenerative processes in AD. Here we tested the utility of the multimodal MRI (T1-weighted structure and diffusion MRI), combined with high-throughput brain phenotyping—morphometry and structural connectomics—and machine learning, as a diagnostic tool for AD. We used, firstly, a clinical cohort at a dementia clinic (National Health Insurance Service-Ilsan Hospital [NHIS-IH]; N = 211; 110 AD, 64 mild cognitive impairment [MCI], and 37 cognitively normal with subjective memory complaints [SMC]) to test the diagnostic models; and, secondly, Alzheimer's Disease Neuroimaging Initiative (ADNI)-2 to test the generalizability. Our machine learning models trained on the morphometric and connectome estimates (number of features = 34,646) showed optimal classification accuracy (AD/SMC: 97% accuracy, MCI/SMC: 83% accuracy; AD/MCI: 97% accuracy) in NHIS-IH cohort, outperforming a benchmark model (FLAIR-based white matter hyperintensity volumes). In ADNI-2 data, the combined connectome and morphometry model showed similar or superior accuracies (AD/HC: 96%; MCI/HC: 70%; AD/MCI: 75% accuracy) compared with the CSF biomarker model (t-tau, p-tau, and Amyloid β, and ratios). In predicting MCI to AD progression in a smaller cohortmore » of ADNI-2 (n = 60), the morphometry model showed similar performance with 69% accuracy compared with CSF biomarker model with 70% accuracy. Our comparisons of the classifiers trained on structural MRI, diffusion MRI, FLAIR, and CSF biomarkers showed the promising utility of the white matter structural connectomes in classifying AD and MCI in addition to the widely used structural MRI-based morphometry, when combined with machine learning.« less

Authors:
ORCiD logo [1];  [2];  [2];  [3];  [4];  [5];  [6];  [7]; ORCiD logo [8]
  1. Columbia Univ., New York, NY (United States). Medical Center. Dept. of Psychiatry
  2. Stony Brook Univ., NY (United States). Dept. of Applied Mathematics
  3. Columbia Univ., New York, NY (United States). Medical Center. Dept. of Biostatistics. School of Public Health
  4. Columbia Univ., New York, NY (United States). Medical Center. Dept. of Neurology
  5. Brookhaven National Lab. (BNL), Upton, NY (United States). Computational Science Initiative
  6. National Health Insurance Service Ilsan Hospital, Goyang (Korea, Republic of). Dept. of Neurology
  7. National Health Insurance Service Ilsan Hospital, Goyang (Korea, Republic of). Dept. of Physical Medicine and Rehabilitation
  8. Columbia Univ., New York, NY (United States). Medical Center. Dept. of Psychiatry. Data Science Inst.
Publication Date:
Research Org.:
Brookhaven National Lab. (BNL), Upton, NY (United States); Columbia Univ., New York, NY (United States); National Health Insurance Service Ilsan Hospital, Goyang (Korea, Republic of)
Sponsoring Org.:
USDOE; National Inst. of Health (NIH) (United States); National Health Insurance Ilsan Hospital Research Fund (Korea, Republic of)
OSTI Identifier:
1514489
Report Number(s):
BNL-211602-2019-JAAM
Journal ID: ISSN 2213-1582
Grant/Contract Number:  
SC0012704; K01 MH109836
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
NeuroImage: Clinical
Additional Journal Information:
Journal Volume: 23; Journal ID: ISSN 2213-1582
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; Alzheimer's disease; multimodal MRI; DWI; machine learning

Citation Formats

Wang, Yun, Xu, Chenxiao, Park, Ji-Hwan, Lee, Seonjoo, Stern, Yaakov, Yoo, Shinjae, Kim, Jong Hun, Kim, Hyoung Seop, and Cha, Jiook. Diagnosis and prognosis of Alzheimer's disease using brain morphometry and white matter connectomes. United States: N. p., 2019. Web. doi:10.1016/j.nicl.2019.101859.
Wang, Yun, Xu, Chenxiao, Park, Ji-Hwan, Lee, Seonjoo, Stern, Yaakov, Yoo, Shinjae, Kim, Jong Hun, Kim, Hyoung Seop, & Cha, Jiook. Diagnosis and prognosis of Alzheimer's disease using brain morphometry and white matter connectomes. United States. doi:10.1016/j.nicl.2019.101859.
Wang, Yun, Xu, Chenxiao, Park, Ji-Hwan, Lee, Seonjoo, Stern, Yaakov, Yoo, Shinjae, Kim, Jong Hun, Kim, Hyoung Seop, and Cha, Jiook. Mon . "Diagnosis and prognosis of Alzheimer's disease using brain morphometry and white matter connectomes". United States. doi:10.1016/j.nicl.2019.101859. https://www.osti.gov/servlets/purl/1514489.
@article{osti_1514489,
title = {Diagnosis and prognosis of Alzheimer's disease using brain morphometry and white matter connectomes},
author = {Wang, Yun and Xu, Chenxiao and Park, Ji-Hwan and Lee, Seonjoo and Stern, Yaakov and Yoo, Shinjae and Kim, Jong Hun and Kim, Hyoung Seop and Cha, Jiook},
abstractNote = {Accurate, reliable prediction of risk for Alzheimer's disease (AD) is essential for early, disease-modifying therapeutics. Multimodal MRI, such as structural and diffusion MRI, is likely to contain complementary information of neurodegenerative processes in AD. Here we tested the utility of the multimodal MRI (T1-weighted structure and diffusion MRI), combined with high-throughput brain phenotyping—morphometry and structural connectomics—and machine learning, as a diagnostic tool for AD. We used, firstly, a clinical cohort at a dementia clinic (National Health Insurance Service-Ilsan Hospital [NHIS-IH]; N = 211; 110 AD, 64 mild cognitive impairment [MCI], and 37 cognitively normal with subjective memory complaints [SMC]) to test the diagnostic models; and, secondly, Alzheimer's Disease Neuroimaging Initiative (ADNI)-2 to test the generalizability. Our machine learning models trained on the morphometric and connectome estimates (number of features = 34,646) showed optimal classification accuracy (AD/SMC: 97% accuracy, MCI/SMC: 83% accuracy; AD/MCI: 97% accuracy) in NHIS-IH cohort, outperforming a benchmark model (FLAIR-based white matter hyperintensity volumes). In ADNI-2 data, the combined connectome and morphometry model showed similar or superior accuracies (AD/HC: 96%; MCI/HC: 70%; AD/MCI: 75% accuracy) compared with the CSF biomarker model (t-tau, p-tau, and Amyloid β, and ratios). In predicting MCI to AD progression in a smaller cohort of ADNI-2 (n = 60), the morphometry model showed similar performance with 69% accuracy compared with CSF biomarker model with 70% accuracy. Our comparisons of the classifiers trained on structural MRI, diffusion MRI, FLAIR, and CSF biomarkers showed the promising utility of the white matter structural connectomes in classifying AD and MCI in addition to the widely used structural MRI-based morphometry, when combined with machine learning.},
doi = {10.1016/j.nicl.2019.101859},
journal = {NeuroImage: Clinical},
issn = {2213-1582},
number = ,
volume = 23,
place = {United States},
year = {2019},
month = {5}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share: