Multivariate analysis of MRI data for Alzheimer's disease, mild cognitive impairment and healthy controls

Westman, Eric; Simmons, Andrew; Zhang, Yi; Muehlboeck, J‐Sebastian; Tunnard, Catherine; Liu, Yawu; Collins, D. Louis; Evans, Alan C.; Mecocci, Patrizia; Vellas, Bruno; Tsolaki, Magda; Kłoszewska, Iwona; Soininen, Hilkka; Lovestone, Simon; Spenger, Christian; Wahlund, Lars‐Olof

doi:10.1016/j.neuroimage.2010.08.044

Cited by 131 publications

(123 citation statements)

References 50 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…The predictive accuracy of our model is comparable to that in similar previous reports: SVM used to classify patients according to disease state (vascular Parkinsonism or PD) produced an accuracy of 90.4% [21], whereas SVM used to distinguish patients with AD and those with mild cognitive impairment (MCI) from healthy control subjects had accuracy values of 94.1% and 88.9%, respectively [22]. SVM used to classify patients with AD from healthy control subjects had a reported accuracy of 82-83% [23]. The accuracy values reported in previous studies for classifying healthy control subjects versus neurological patients [24] are slightly higher than those reported in this study, which is to be expected as there are larger differences between healthy subjects and patients with neurological diseases/disorders than between patients with comparable disease states.…”

Section: A Good Model For Ad Versus Pd Classificationsupporting

confidence: 84%

Classification of Alzheimer’s disease and Parkinson’s disease using a support vector machine and probabilistic outputs

Hatabu

Harada

Takahashi³

et al. 2017

CBIJ

View full text Add to dashboard Cite

Alzheimer's disease (AD) and Parkinson's disease (PD) are both prominent central nervous system diseases that are frequently diagnosed and studied using brain single-photon emission computed tomography (SPECT). Owing to divergent clinical features, AD and PD are often considered distinct diseases; however, it is difficult to distinguish AD from PD on SPECT. Tools for objectively analyzing differences between AD and PD on SPECT images are not currently available. To construct a model for discriminating AD from PD in Japanese patients, we used a support vector machine (SVM) and SPECT images acquired at two different time points after radiotracer injection to extract the determinant regions for classification. We assessed SPECT images from 68 Japanese patients with AD or PD. After pre-processing noise voxels, a non-linear SVM classification with Gaussian kernels was adopted to construct the predictive model. The best SVM model was highly accurate for distinguishing AD from PD. The accuracy of this model was 98.1% for leave-one-out cross-validation and 78.6% for the test set. Our data showed that the temporal, sub-lobar, parietal, limbic, and frontal areas exhibited decreased regional cerebral blood flow in AD; whereas the frontal, anterior, parietal, and occipital areas exhibited decreased regional cerebral blood flow in PD. Here, we present a useful SVM model for classifying AD versus PD using SPECT images and show the utility of two-time-point SPECT imaging for AD/PD discrimination.

show abstract

Section: A Good Model For Ad Versus Pd Classificationsupporting

confidence: 84%

Classification of Alzheimer’s disease and Parkinson’s disease using a support vector machine and probabilistic outputs

Hatabu

Harada

Takahashi³

et al. 2017

CBIJ

View full text Add to dashboard Cite

show abstract

“…This new method has the advantage of simplicity and in converting MRI measures into values that can be directly added and subtracted across measures without the assumptions required of PCA and PLS methods (López, et al, 2009;Nobili, et al, 2008;Ramírez, et al, 2010;Westman, et al, 2011b). These assumptions in PCA and PLS make the data interpretation less intuitive, because the position and distance to the boundary of a testing subject in the decisional space may be difficult to quantify, especially if the decisional space is multi-dimensional.…”

Section: Discussionmentioning

confidence: 99%

“…The features extracted from biomarkers are often analyzed most often using various multivariate data analysis method such as principal component analysis (PCA) (López, et al, 2009;Nobili, et al, 2008), partial least square (PLS) (Higdon, et al, 2004;Ramírez, et al, 2010), and orthogonal partial least squares (OPLS) as exemplified in (Westman, et al, 2012a;Westman, et al, 2011b). The common objective of these techniques is to project the data into a decisional space where the total variance or variance related to class separation is maximized.…”

Section: Introductionmentioning

confidence: 99%

“…Orthogonal partial least square to latent structures (OPLS) is a supervised multivariate data analysis method that has shown its efficiency in analyzing complex biological data (Bylesjo, et al, 2006;Ray, 2012;Trygg and Wold, 2002;Westman, et al, 2012c;Westman, et al, 2011b). For AD study, Westman et al combined manual hippocampal volume measurements with automated regional and global volume measures to discriminate AD and MCI from controls.…”

Section: Introductionmentioning

confidence: 99%

“…For AD study, Westman et al combined manual hippocampal volume measurements with automated regional and global volume measures to discriminate AD and MCI from controls. By comparing the discriminative powers of these features, they reported that OPLS showed great potential in the prediction AD and MCI and in the conversion from MCI to AD (Westman, et al, 2011b). They also compared and combined MRI data from the European AddNeuroMed and ADNI using OPLS method, and the results indicated that the two cohorts showed similar pattern of atrophy and predictive power (between 80 and 90%) (Westman, et al, 2011a).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Integrated Neuroimaging Approach for the Prediction and Analysis of Alzheimer’s Disease and its Prodromal Stages

Zhou¹

View full text Add to dashboard Cite

selected for each combination model were used to construct the classification space using support vector machines. To combine MRI and PET, orthogonal partial least squares to latent structures is used as a multivariate analysis to discriminate between AD, early and late MCI (EMCI and LMCI) from cognitively normal (CN)s. In addition, this dissertation proposes a new effective mean indicator (EMI) method for distinguishing stages of AD from CN. EMI utilizes the mean of specific top-ranked measures, determined by incremental error analysis, to achieve optimal separation of AD and CN.viii For AD vs. CN, the two most discriminative volumetric variables (right hippocampus and left inferior lateral ventricle), when combined with MMSE scores, provided an average accuracy of 92.4% (sensitivity: 84.0%; specificity: 96.1%). MMSE scores were found to improve classification accuracy by 8.2% and 12% for aMCI vs. CN and naMCI vs. CN, respectively. Brain atrophy was almost evenly seen on both sides of the brain for AD subjects, which was different from right side dominance for aMCI and left side dominance for naMCI. Findings suggest that subcortical volume need not be normalized, whereas cortical thickness should be normalized either by intracranial volume or the mean thickness. Furthermore, MRI and PET had comparable predictive power in separating AD from CN. For the EMCI prediction, cortical thickness was found to be the best predictor, even better than using all features together. Validation with an external test set demonstrated that best of feature-selected models for the LMCI group was able to classify 83% of the LMCI subjects. The EMI-based method achieved an accuracy of 92.7% using only MRI features. The performance of the EMI-based method along with its simplicity suggests great potential for its use in clinical trials.

show abstract

Differences in and correlations between cognitive abilities and brain volumes in healthy control, mild cognitive impairment, and Alzheimer disease groups

et al. 2016

View full text Add to dashboard Cite

The purpose of this study is to investigate differences in and correlations between cognitive abilities and brain volumes in healthy control (HC), mild cognitive impairment (MCI), and Alzheimer's disease (AD) groups. The Korean Version of the Consortium to Establish a Registry for Alzheimer's Disease (CERAD-K), which is used to diagnose AD, was used to measure the cognitive abilities of the study subjects, and the volumes of typical brain components related to AD diagnosis-cerebrospinal fluid (CSF), gray matter (GM), and white matter (WM)-were acquired. Of the CERAD-K subtests, the Boston Naming Test distinguished significantly among the HC, MCI, and AD groups. GM and WM volumes differed significantly among the three groups. There was a significant positive correlation between Boston Naming Test scores and GM and WM volumes. In conclusion, the Boston Naming Test and GM and WM brain volumes differentiated the three tested groups accurately, and there were strong correlations between Boston Naming Test scores and GM and WM volumes. These results will help to establish a test method that differentiates the three groups accurately and is economically feasible.

show abstract

Multivariate analysis of MRI data for Alzheimer's disease, mild cognitive impairment and healthy controls

Cited by 131 publications

References 50 publications

Classification of Alzheimer’s disease and Parkinson’s disease using a support vector machine and probabilistic outputs

Classification of Alzheimer’s disease and Parkinson’s disease using a support vector machine and probabilistic outputs

An Integrated Neuroimaging Approach for the Prediction and Analysis of Alzheimer’s Disease and its Prodromal Stages

Differences in and correlations between cognitive abilities and brain volumes in healthy control, mild cognitive impairment, and Alzheimer disease groups

Contact Info

Product

Resources

About