EEG-Based Classification Between Individuals with Mild Cognitive Impairment and Healthy Controls Using Conformal Kernel-Based Fuzzy Support Vector Machine

2021 ◽  
Author(s):  
Yu-Tsung Hsiao ◽  
Chien-Te Wu ◽  
Chia-Fen Tsai ◽  
Yi-Hung Liu ◽  
Thanh-Tung Trinh ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Support Vector ◽  
Healthy Controls ◽  
Fuzzy Support Vector Machine

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.

scholarly journals LINGUISTIC MEASURES OF SPOKEN UTTERANCES FOR DETECTING MILD COGNITIVE IMPAIRMENT

2019 ◽  
Vol 3 (Supplement_1) ◽  
pp. S224-S225
Author(s):  
Meysam Asgari ◽  
Jeffrey Kaye ◽  
Hiroko Dodge
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Cognitive Stimulation ◽  
Support Vector ◽  
Svm Classifier ◽  
Healthy Controls ◽  
Document Frequency ◽  
Trained Interviewer ◽  
Validation Procedure ◽  
Characteristic Area

Abstract Studies have shown that speech characteristics can aid in early-identification of those with mild cognitive impairment (MCI). We performed a linguistic analysis on spoken utterances of 41 participants (15 MCI, 26 healthy controls) from conversations with a trained interviewer using the Term Frequency-Inverse Document Frequency (TF-IDF) method. Data came from a randomized controlled behavioral clinical trial (ClinicalTrials.gov: NCT01571427) to examine effects of conversation-based cognitive stimulation on cognitive functions among older adults with normal cognition or MCI, which served as a pilot study for I-CONECT. From the collected spoken utterances we first constructed a fixed-dimensional feature vector using TF-IDF. Next, to distinguish between MCI and healthy controls, we trained a support vector machine (SVM) classifier on per-subject feature vectors according to 5-fold cross-validation procedure. Our results verify the effectiveness of TF-IDF features in this classification task with Receiver Operating Characteristic Area Under Curve of 81%, well above chance at 65%.

scholarly journals Individual Classification of Mild Cognitive Impairment Subtypes by Support Vector Machine Analysis of White Matter DTI

2012 ◽  
Vol 34 (2) ◽  
pp. 283-291 ◽  
Author(s):  
S. Haller ◽  
P. Missonnier ◽  
F.R. Herrmann ◽  
C. Rodriguez ◽  
M.-P. Deiber ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
White Matter ◽  
Support Vector ◽  
Machine Analysis

scholarly journals Combined Support Vector Machine Classifier and Brain Structural Network Features for the Individual Classification of Amnestic Mild Cognitive Impairment and Subjective Cognitive Decline Patients

2021 ◽  
Vol 13 ◽  
Author(s):  
Weijie Huang ◽  
Xuanyu Li ◽  
Xin Li ◽  
Guixia Kang ◽  
Ying Han ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Classification Performance ◽  
Amnestic Mild Cognitive Impairment ◽  
Subjective Cognitive Decline ◽  
Support Vector ◽  
Weighted Networks ◽  
Structural Network ◽  
Auc Value

ObjectiveIndividuals with subjective cognitive decline (SCD) or amnestic mild cognitive impairment (aMCI) represent important targets for the early detection and intervention of Alzheimer’s disease (AD). In this study, we employed a multi-kernel support vector machine (SVM) to examine whether white matter (WM) structural networks can be used for screening SCD and aMCI.MethodsA total of 138 right-handed participants [51 normal controls (NC), 36 SCD, 51 aMCI] underwent MRI brain scans. For each participant, three types of WM networks with different edge weights were constructed with diffusion MRI data: fiber number-weighted networks, mean fractional anisotropy-weighted networks, and mean diffusivity (MD)-weighted networks. By employing a multiple-kernel SVM, we seek to integrate information from three weighted networks to improve classification performance. The accuracy of classification between each pair of groups was evaluated via leave-one-out cross-validation.ResultsFor the discrimination between SCD and NC, an area under the curve (AUC) value of 0.89 was obtained, with an accuracy of 83.9%. Further analysis revealed that the methods using three types of WM networks outperformed other methods using single WM network. Moreover, we found that most of discriminative features were from MD-weighted networks, which distributed among frontal lobes. Similar classification performance was also reported in the differentiation between subjects with aMCI and NCs (accuracy = 83.3%). Between SCD and aMCI, an AUC value of 0.72 was obtained, with an accuracy of 72.4%, sensitivity of 74.5% and specificity of 69.4%. The highest accuracy was achieved with features only selected from MD-weighted networks.ConclusionWhite matter structural network features help machine learning algorithms accurately identify individuals with SCD and aMCI from NCs. Our findings have significant implications for the development of potential brain imaging markers for the early detection of AD.

scholarly journals Targeted Metabolic Profiling of Urine Highlights a Potential Biomarker Panel for the Diagnosis of Alzheimer’s Disease and Mild Cognitive Impairment: A Pilot Study

Metabolites ◽  
2020 ◽  
Vol 10 (9) ◽  
pp. 357
Author(s):  
Ali Yilmaz ◽  
Zafer Ugur ◽  
Halil Bisgin ◽  
Sumeyya Akyol ◽  
Ray Bahado-Singh ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Logistic Regression ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Pilot Study ◽  
Direct Result ◽  
Support Vector ◽  
Healthy Controls ◽  
Urine Metabolites

The lack of sensitive and specific biomarkers for the early detection of mild cognitive impairment (MCI) and Alzheimer’s disease (AD) is a major hurdle to improving patient management. A targeted, quantitative metabolomics approach using both 1H NMR and mass spectrometry was employed to investigate the performance of urine metabolites as potential biomarkers for MCI and AD. Correlation-based feature selection (CFS) and least absolute shrinkage and selection operator (LASSO) methods were used to develop biomarker panels tested using support vector machine (SVM) and logistic regression models for diagnosis of each disease state. Metabolic changes were investigated to identify which biochemical pathways were perturbed as a direct result of MCI and AD in urine. Using SVM, we developed a model with 94% sensitivity, 78% specificity, and 78% AUC to distinguish healthy controls from AD sufferers. Using logistic regression, we developed a model with 85% sensitivity, 86% specificity, and an AUC of 82% for AD diagnosis as compared to cognitively healthy controls. Further, we identified 11 urinary metabolites that were significantly altered to include glucose, guanidinoacetate, urocanate, hippuric acid, cytosine, 2- and 3-hydroxyisovalerate, 2-ketoisovalerate, tryptophan, trimethylamine N oxide, and malonate in AD patients, which are also capable of diagnosing MCI, with a sensitivity value of 76%, specificity of 75%, and accuracy of 81% as compared to healthy controls. This pilot study suggests that urine metabolomics may be useful for developing a test capable of diagnosing and distinguishing MCI and AD from cognitively healthy controls.

Sign in / Sign up

Export Citation Format

Share Document