scholarly journals Use of a Sparse-Response Deep Belief Network and Extreme Learning Machine to Discriminate Alzheimer's Disease, Mild Cognitive Impairment, and Normal Controls Based on Amyloid PET/MRI Images

2021 ◽  
Vol 7 ◽  
Author(s):  
Ping Zhou ◽  
Shuqing Jiang ◽  
Lun Yu ◽  
Yabo Feng ◽  
Chuxin Chen ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Extreme Learning Machine ◽  
Deep Belief Network ◽  
Support Vector ◽  
Belief Network ◽  
Learning Machine ◽  
Normal Controls

In recent years, interest has grown in using computer-aided diagnosis (CAD) for Alzheimer's disease (AD) and its prodromal stage, mild cognitive impairment (MCI). However, existing CAD technologies often overfit data and have poor generalizability. In this study, we proposed a sparse-response deep belief network (SR-DBN) model based on rate distortion (RD) theory and an extreme learning machine (ELM) model to distinguish AD, MCI, and normal controls (NC). We used [18F]-AV45 positron emission computed tomography (PET) and magnetic resonance imaging (MRI) images from 340 subjects enrolled in the ADNI database, including 116 AD, 82 MCI, and 142 NC subjects. The model was evaluated using five-fold cross-validation. In the whole model, fast principal component analysis (PCA) served as a dimension reduction algorithm. An SR-DBN extracted features from the images, and an ELM obtained the classification. Furthermore, to evaluate the effectiveness of our method, we performed comparative trials. In contrast experiment 1, the ELM was replaced by a support vector machine (SVM). Contrast experiment 2 adopted DBN without sparsity. Contrast experiment 3 consisted of fast PCA and an ELM. Contrast experiment 4 used a classic convolutional neural network (CNN) to classify AD. Accuracy, sensitivity, specificity, and area under the curve (AUC) were examined to validate the results. Our model achieved 91.68% accuracy, 95.47% sensitivity, 86.68% specificity, and an AUC of 0.87 separating between AD and NC groups; 87.25% accuracy, 79.74% sensitivity, 91.58% specificity, and an AUC of 0.79 separating MCI and NC groups; and 80.35% accuracy, 85.65% sensitivity, 72.98% specificity, and an AUC of 0.71 separating AD and MCI groups, which gave better classification than other models assessed.

Characteristics of Mild Cognitive Impairment Using the Thai Version of the Consortium to Establish a Registry for Alzheimer’s Disease Tests: A Multivariate and Machine Learning Study

2018 ◽  
Vol 45 (1-2) ◽  
pp. 38-48 ◽  
Author(s):  
Chavit Tunvirachaisakul ◽  
Thitiporn Supasitthumrong ◽  
Sookjareon Tangwongchai ◽  
Solaphat Hemrunroj ◽  
Phenphichcha Chuchuen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Support Vector ◽  
Test Machine ◽  
Characteristic Analysis ◽  
Adaptive Boosting ◽  
Normal Controls

Background: The Consortium to Establish a Registry for Alzheimer’s Disease (CERAD) developed a neuropsychological battery (CERAD-NP) to screen patients with Alzheimer’s dementia. Mild cognitive impairment (MCI) has received attention as a pre-dementia stage. Objectives: To delineate the CERAD-NP features of MCI and their clinical utility to externally validate MCI diagnosis. Methods: The study included 60 patients with MCI, diagnosed using the Clinical Dementia Rating, and 63 normal controls. Data were analysed employing receiver operating characteristic analysis, Linear Support Vector Machine, Random Forest, Adaptive Boosting, Neural Network models, and t-distributed stochastic neighbour embedding (t-SNE). Results: MCI patients were best discriminated from normal controls using a combination of Wordlist Recall, Wordlist Memory, and Verbal Fluency Test. Machine learning showed that the CERAD features learned from MCI patients and controls were not strongly predictive of the diagnosis (maximal cross-validation 77.2%), whilst t-SNE showed that there is a considerable overlap between MCI and controls. Conclusions: The most important features of the CERAD-NP differentiating MCI from normal controls indicate impairments in episodic and semantic memory and recall. While these features significantly discriminate MCI patients from normal controls, the tests are not predictive of MCI.

Resting State EEG Multiscale Entropy Dynamics in Mild Cognitive Impairment and Early Alzheimer’s Disease

2014 ◽  
Author(s):  
Joseph McBride ◽  
Xiaopeng Zhao ◽  
Nancy Munro ◽  
Gregory Jicha ◽  
Charles Smith ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Multiscale Entropy ◽  
Support Vector ◽  
P Value ◽  
Early Alzheimer’S Disease ◽  
Leave One Out ◽  
Normal Controls

Mild cognitive impairment (MCI) is a neurological condition related to early stages of dementia such as Alzheimer’s disease (AD). This study explores non-event-related multiscale entropy (MSE) measures as features for effectively discriminating between normal aging, MCI, and AD participants. Resting EEG records from 48 age-matched participants (mean age 75.7 years) — 15 normal controls (NC), 16 MCI, and 17 early AD — are examined. Multiscale entropy curves are computed for short EEG segments and averaged over the segments. Binary discriminations among the three groups are conducted using support vector machine models. Leave-one-out cross-validation accuracies of 80.7% (p-value <0.0018) for MCI vs. NC, 87.5% (p-value <1.322E−4) for AD vs. NC, and 90.9% (p-value <2.788E−5) for MCI vs. AD are achieved. Results demonstrate influence of cognitive deficits on multiscale entropy dynamics of non-event-related EEG.

Subjective Spatial Navigation Complaints - A Frequent Symptom Reported by Patients with Subjective Cognitive Decline, Mild Cognitive Impairment and Alzheimer's Disease

2018 ◽  
Vol 15 (3) ◽  
pp. 219-228 ◽  
Author(s):  
Jiri Cerman ◽  
Ross Andel ◽  
Jan Laczo ◽  
Martin Vyhnalek ◽  
Zuzana Nedelska ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Cognitive Decline ◽  
Spatial Navigation ◽  
Subjective Cognitive Decline ◽  
Great Effort ◽  
Frequent Symptom ◽  
Normal Controls

Background: Great effort has been put into developing simple and feasible tools capable to detect Alzheimer's disease (AD) in its early clinical stage. Spatial navigation impairment occurs very early in AD and is detectable even in the stage of mild cognitive impairment (MCI). Objective: The aim was to describe the frequency of self-reported spatial navigation complaints in patients with subjective cognitive decline (SCD), amnestic and non-amnestic MCI (aMCI, naMCI) and AD dementia and to assess whether a simple questionnaire based on these complaints may be used to detect early AD. Method: In total 184 subjects: patients with aMCI (n=61), naMCI (n=27), SCD (n=63), dementia due to AD (n=20) and normal controls (n=13) were recruited. The subjects underwent neuropsychological examination and were administered a questionnaire addressing spatial navigation complaints. Responses to the 15 items questionnaire were scaled into four categories (no, minor, moderate and major complaints). Results: 55% of patients with aMCI, 64% with naMCI, 68% with SCD and 72% with AD complained about their spatial navigation. 38-61% of these complaints were moderate or major. Only 33% normal controls expressed complaints and none was ranked as moderate or major. The SCD, aMCI and AD dementia patients were more likely to express complaints than normal controls (p's<0.050) after adjusting for age, education, sex, depressive symptoms (OR for SCD=4.00, aMCI=3.90, AD dementia=7.02) or anxiety (OR for SCD=3.59, aMCI=3.64, AD dementia=6.41). Conclusion: Spatial navigation complaints are a frequent symptom not only in AD, but also in SCD and aMCI and can potentially be detected by a simple and inexpensive questionnaire.

scholarly journals To Explore the Predictive Power of Visuomotor Network Dysfunctions in Mild Cognitive Impairment and Alzheimer’s Disease

2021 ◽  
Vol 15 ◽  
Author(s):  
Justine Staal ◽  
Francesco Mattace-Raso ◽  
Hennie A. M. Daniels ◽  
Johannes van der Steen ◽  
Johan J. M. Pel
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Support Vector Machine ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Predictive Power ◽  
Area Under The Curve ◽  
Classification Performance ◽  
Support Vector ◽  
Potential Biomarker

BackgroundResearch into Alzheimer’s disease has shifted toward the identification of minimally invasive and less time-consuming modalities to define preclinical stages of Alzheimer’s disease.MethodHere, we propose visuomotor network dysfunctions as a potential biomarker in AD and its prodromal stage, mild cognitive impairment with underlying the Alzheimer’s disease pathology. The functionality of this network was tested in terms of timing, accuracy, and speed with goal-directed eye-hand tasks. The predictive power was determined by comparing the classification performance of a zero-rule algorithm (baseline), a decision tree, a support vector machine, and a neural network using functional parameters to classify controls without cognitive disorders, mild cognitive impaired patients, and Alzheimer’s disease patients.ResultsFair to good classification was achieved between controls and patients, controls and mild cognitive impaired patients, and between controls and Alzheimer’s disease patients with the support vector machine (77–82% accuracy, 57–93% sensitivity, 63–90% specificity, 0.74–0.78 area under the curve). Classification between mild cognitive impaired patients and Alzheimer’s disease patients was poor, as no algorithm outperformed the baseline (63% accuracy, 0% sensitivity, 100% specificity, 0.50 area under the curve).Comparison with Existing Method(s)The classification performance found in the present study is comparable to that of the existing CSF and MRI biomarkers.ConclusionThe data suggest that visuomotor network dysfunctions have potential in biomarker research and the proposed eye-hand tasks could add to existing tests to form a clear definition of the preclinical phenotype of AD.

An Embedded Feature Selection and Multi-Class Classification Method for Detection of the Progression from Mild Cognitive Impairment to Alzheimer's Disease

2020 ◽  
Vol 10 (2) ◽  
pp. 370-379 ◽  
Author(s):  
Jie Cai ◽  
Lingjing Hu ◽  
Zhou Liu ◽  
Ke Zhou ◽  
Huailing Zhang
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Feature Selection ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Treatment Plan ◽  
Feature Selection Method ◽  
Selection Method ◽  
Support Vector ◽  
Feature Subset

Background: Mild cognitive impairment (MCI) patients are a high-risk group for Alzheimer's disease (AD). Each year, the diagnosed of 10–15% of MCI patients are converted to AD (MCI converters, MCI_C), while some MCI patients remain relatively stable, and unconverted (MCI stable, MCI_S). MCI patients are considered the most suitable population for early intervention treatment for dementia, and magnetic resonance imaging (MRI) is clinically the most recommended means of imaging examination. Therefore, using MRI image features to reliably predict the conversion from MCI to AD can help physicians carry out an effective treatment plan for patients in advance so to prevent or slow down the development of dementia. Methods: We proposed an embedded feature selection method based on the least squares loss function and within-class scatter to select the optimal feature subset. The optimal subsets of features were used for binary classification (AD, MCI_C, MCI_S, normal control (NC) in pairs) based on a support vector machine (SVM), and the optimal 3-class features were used for 3-class classification (AD, MCI_C, MCI_S, NC in triples) based on one-versus-one SVMs (OVOSVMs). To ensure the insensitivity of the results to the random train/test division, a 10-fold cross-validation has been repeated for each classification. Results: Using our method for feature selection, only 7 features were selected from the original 90 features. With using the optimal subset in the SVM, we classified MCI_C from MCI_S with an accuracy, sensitivity, and specificity of 71.17%, 68.33% and 73.97%, respectively. In comparison, in the 3-class classification (AD vs. MCI_C vs. MCI_S) with OVOSVMs, our method selected 24 features, and the classification accuracy was 81.9%. The feature selection results were verified to be identical to the conclusions of the clinical diagnosis. Our feature selection method achieved the best performance, comparing with the existing methods using lasso and fused lasso for feature selection. Conclusion: The results of this study demonstrate the potential of the proposed approach for predicting the conversion from MCI to AD by identifying the affected brain regions undergoing this conversion.

Multi-Objective Genetic Algorithms to Find Most Relevant Volumes of the Brain Related to Alzheimer's Disease and Mild Cognitive Impairment

2018 ◽  
Vol 28 (09) ◽  
pp. 1850022 ◽  
Author(s):  
Olga Valenzuela ◽  
Xiaoyi Jiang ◽  
Antonio Carrillo ◽  
Ignacio Rojas
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Genetic Algorithms ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Support Vector ◽  
Significant Information ◽  
Multi Objective ◽  
3D Dwt ◽  
The Brain

Computer-Aided Diagnosis (CAD) represents a relevant instrument to automatically classify between patients with and without Alzheimer's Disease (AD) using several actual imaging techniques. This study analyzes the optimization of volumes of interest (VOIs) to extract three-dimensional (3D) textures from Magnetic Resonance Image (MRI) in order to diagnose AD, Mild Cognitive Impairment converter (MCIc), Mild Cognitive Impairment nonconverter (MCInc) and Normal subjects. A relevant feature of the proposed approach is the use of 3D features instead of traditional two-dimensional (2D) features, by using 3D discrete wavelet transform (3D-DWT) approach for performing feature extraction from T-1 weighted MRI. Due to the high number of coefficients when applying 3D-DWT to each of the VOIs, a feature selection algorithm based on mutual information is used, as is the minimum Redundancy Maximum Relevance (mRMR) algorithm. Region optimization has been performed in order to discover the most relevant regions (VOIs) in the brain with the use of Multi-Objective Genetic Algorithms, being one of the objectives to be optimize the accuracy of the system. The error index of the system is computed by the confusion matrix obtained by the multi-class support vector machine (SVM) classifier. Principal Component Analysis (PCA) is used with the purpose of reducing the number of features to the classifier. The cohort of subjects used in the study consisted of 296 different patients. A first group of 206 patients was used to optimize VOI selection and another group of 90 independent subjects (that did not belong to the first group) was used to test the solutions yielded by the genetic algorithm. The proposed methodology obtains excellent results in multi-class classification achieving accuracies of 94.4% and also extracting significant information on the location of the most relevant points of the brain. This suggests that the proposed method could aid in the research of other neurodegenerative diseases, improving the accuracy of the diagnosis and finding the most relevant regions of the brain associated with them.

Sign in / Sign up

Export Citation Format

Share Document