Journal article
Using high-dimensional machine learning methods to estimate an anatomical risk factor for Alzheimer's disease across imaging databases
NeuroImage (Orlando, Fla.), Vol.183, pp.401-411
12/2018
DOI: 10.1016/j.neuroimage.2018.08.040
PMCID: PMC6457113
PMID: 30130645
Abstract
The main goal of this work is to investigate the feasibility of estimating an anatomical index that can be used as an Alzheimer's disease (AD) risk factor in the Women's Health Initiative Magnetic Resonance Imaging Study (WHIMS-MRI) using MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), a well-characterized imaging database of AD patients and cognitively normal subjects. We called this index AD Pattern Similarity (AD-PS) scores. To demonstrate the construct validity of the scores, we investigated their associations with several AD risk factors. The ADNI and WHIMS imaging databases were collected with different goals, populations and data acquisition protocols: it is important to demonstrate that the approach to estimating AD-PS scores can bridge these differences.
MRI data from both studies were processed using high-dimensional warping methods. High-dimensional classifiers were then estimated using the ADNI MRI data. Next, the classifiers were applied to baseline and follow-up WHIMS-MRI GM data to generate the GM AD-PS scores. To study the validity of the scores we investigated associations between GM AD-PS scores at baseline (Scan 1) and their longitudinal changes (Scan 2 –Scan 1) with: 1) age, cognitive scores, white matter small vessel ischemic disease (WM SVID) volume at baseline and 2) age, cognitive scores, WM SVID volume longitudinal changes respectively. In addition, we investigated their associations with time until classification of independently adjudicated status in WHIMS-MRI.
Higher GM AD-PS scores from WHIMS-MRI baseline data were associated with older age, lower cognitive scores, and higher WM SVID volume. Longitudinal changes in GM AD-PS scores (Scan 2 – Scan 1) were also associated with age and changes in WM SVID volumes and cognitive test scores. Increases in the GM AD-PS scores predicted decreases in cognitive scores and increases in WM SVID volume. GM AD-PS scores and their longitudinal changes also were associated with time until classification of cognitive impairment. Finally, receiver operating characteristic curves showed that baseline GM AD-PS scores of cognitively normal participants carried information about future cognitive status determined during follow-up.
We applied a high-dimensional machine learning approach to estimate a novel AD risk factor for WHIMS-MRI study participants using ADNI data. The GM AD-PS scores showed strong associations with incident cognitive impairment and cross-sectional and longitudinal associations with age, cognitive function, cognitive status and WM SVID volume lending support to the ongoing validation of the GM AD-PS score.
•AD-PS scores of AD anatomical risk were estimated for the WHIMS-MRI cohort.•The scores and their change were associated with age and cognitive function.•The scores and their change were associated with white matter lesion volumes.•The scores and their change were associated with incident cognitive impairment.
Details
- Title: Subtitle
- Using high-dimensional machine learning methods to estimate an anatomical risk factor for Alzheimer's disease across imaging databases
- Creators
- Ramon Casanova - Wake Forest UniversityRyan T. Barnard - Wake Forest UniversitySarah A. Gaussoin - Wake Forest UniversitySantiago Saldana - Wake Forest UniversityKathleen M. Hayden - Wake Forest UniversityJoAnn E. Manson - Brigham and Women's HospitalRobert B. Wallace - University of IowaStephen R. Rapp - Wake Forest UniversitySusan M. Resnick - National Institute on AgingMark A. Espeland - Wake Forest UniversityJiu-Chiuan Chen - University of Southern CaliforniaWHIMS-MRI Study Group and the Alzheimer's disease Neuroimaging Initiative
- Resource Type
- Journal article
- Publication Details
- NeuroImage (Orlando, Fla.), Vol.183, pp.401-411
- DOI
- 10.1016/j.neuroimage.2018.08.040
- PMID
- 30130645
- PMCID
- PMC6457113
- NLM abbreviation
- Neuroimage
- ISSN
- 1053-8119
- eISSN
- 1095-9572
- Publisher
- Elsevier Inc
- Grant note
- DOI: 10.13039/100000002, name: NIH, award: R21AG051113; name: Wake Forest Alzheimer's Disease Core Center, award: P30AG049638–01A1; DOI: 10.13039/100000050, name: National Heart, Lung, and Blood Institute, National Institutes of Health, U.S. Department of Health and Human Services, award: HHSN268201600018C, HHSN268201600001C, HHSN268201600002C, HHSN268201600003C, HHSN268201600004C, HHSN271200002C; DOI: 10.13039/100007333, name: Alzheimer's Disease Neuroimaging Initiative; DOI: 10.13039/100000002, name: National Institutes of Health, award: U01 AG024904; DOI: 10.13039/100014041, name: DOD ADNI; DOI: 10.13039/100000005, name: Department of Defense, award: W81XWH-12-2-0012; DOI: 10.13039/100000049, name: National Institute on Aging; DOI: 10.13039/100000070, name: National Institute of Biomedical Imaging and Bioengineering; DOI: 10.13039/100006483, name: AbbVie; DOI: 10.13039/100000957, name: Alzheimer's Association; DOI: 10.13039/100002565, name: Alzheimer's Drug Discovery Foundation; name: Araclon Biotech; DOI: 10.13039/100007742, name: BioClinica, Inc.; DOI: 10.13039/100005614, name: Biogen; DOI: 10.13039/100002491, name: Bristol-Myers Squibb Company; name: CereSpir, Inc.; name: Cogstate; DOI: 10.13039/501100003769, name: Eisai Inc.; DOI: 10.13039/501100003037, name: Elan Pharmaceuticals, Inc.; DOI: 10.13039/100004312, name: Eli Lilly and Company; name: EuroImmun; DOI: 10.13039/100007013, name: F. Hoffmann-La Roche Ltd; DOI: 10.13039/100004328, name: Genentech, Inc.; DOI: 10.13039/501100005062, name: Fujirebio; DOI: 10.13039/100006775, name: GE Healthcare; DOI: 10.13039/501100015725, name: IXICO Ltd.; name: Janssen Alzheimer Immunotherapy Research & Development, LLC.; DOI: 10.13039/100004331, name: Johnson & Johnson Pharmaceutical Research & Development LLC.; name: Lumosity; DOI: 10.13039/501100003554, name: Lundbeck; DOI: 10.13039/100004334, name: Merck & Co., Inc.; DOI: 10.13039/100007054, name: Meso Scale Diagnostics, LLC.; name: NeuroRx Research; name: Neurotrack Technologies; DOI: 10.13039/100008272, name: Novartis Pharmaceuticals Corporation; DOI: 10.13039/100004319, name: Pfizer Inc.; name: Piramal Imaging; DOI: 10.13039/501100011725, name: Servier; DOI: 10.13039/100008373, name: Takeda Pharmaceutical Company; name: Transition Therapeutics; DOI: 10.13039/501100000024, name: Canadian Institutes of Health Research
- Language
- English
- Date published
- 12/2018
- Academic Unit
- Epidemiology; Injury Prevention Research Center; Internal Medicine
- Record Identifier
- 9984363644402771
Metrics
11 Record Views