Format

Send to

Choose Destination
Sci Rep. 2018 Mar 7;8(1):4161. doi: 10.1038/s41598-018-22277-x.

Machine Learning-based Individual Assessment of Cortical Atrophy Pattern in Alzheimer's Disease Spectrum: Development of the Classifier and Longitudinal Evaluation.

Lee JS1,2,3, Kim C4, Shin JH5, Cho H6, Shin DS7, Kim N7, Kim HJ1,2, Kim Y1,2, Lockhart SN8,9, Na DL1,2,10, Seo SW11,12,13,14, Seong JK15,16.

Author information

1
Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, 06351, Korea.
2
Neuroscience Center, Samsung Medical Center, 06351, Seoul, Korea.
3
Department of Neurology, Kyung Hee University Hospital, Seoul, Korea.
4
Department of Preventive Medicine, Yonsei University College of Medicine, Seoul, South Korea.
5
Department of Bio-convergence Engineering, Korea University, Seoul, Korea.
6
Department of Neurology, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, Korea.
7
MIDAS Information Technology Co., Ltd, Seoul, Korea.
8
Helen Wills Neuroscience Institute, University of California Berkeley, Berkeley, CA, 94720, USA.
9
Department of Internal Medicine, Division of Gerontology and Geriatric Medicine, Wake Forest School of Medicine, Winston-Salem, NC, 27157, USA.
10
Department of Health Sciences and Technology, Sungkyunkwan University, Seoul, 06351, Korea.
11
Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, 06351, Korea. sangwonseo@empal.com.
12
Neuroscience Center, Samsung Medical Center, 06351, Seoul, Korea. sangwonseo@empal.com.
13
Department of Health Sciences and Technology, Sungkyunkwan University, Seoul, 06351, Korea. sangwonseo@empal.com.
14
Clinical Research Design and Evaluation, SAIHST, Sungkyunkwan University, Seoul, 06351, Korea. sangwonseo@empal.com.
15
Department of Bio-convergence Engineering, Korea University, Seoul, Korea. jkseong@korea.ac.kr.
16
School of Biomedical Engineering, Korea University, Seoul, Korea. jkseong@korea.ac.kr.

Abstract

To develop a new method for measuring Alzheimer's disease (AD)-specific similarity of cortical atrophy patterns at the individual-level, we employed an individual-level machine learning algorithm. A total of 869 cognitively normal (CN) individuals and 473 patients with probable AD dementia who underwent high-resolution 3T brain MRI were included. We propose a machine learning-based method for measuring the similarity of an individual subject's cortical atrophy pattern with that of a representative AD patient cohort. In addition, we validated this similarity measure in two longitudinal cohorts consisting of 79 patients with amnestic-mild cognitive impairment (aMCI) and 27 patients with probable AD dementia. Surface-based morphometry classifier for discriminating AD from CN showed sensitivity and specificity values of 87.1% and 93.3%, respectively. In the longitudinal validation study, aMCI-converts had higher atrophy similarity at both baseline (p < 0.001) and first year visits (p < 0.001) relative to non-converters. Similarly, AD patients with faster decline had higher atrophy similarity than slower decliners at baseline (p = 0.042), first year (p = 0.028), and third year visits (p = 0.027). The AD-specific atrophy similarity measure is a novel approach for the prediction of dementia risk and for the evaluation of AD trajectories on an individual subject level.

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center