Fully automated discrimination of Alzheimer's disease using resting-state electroencephalography signals

Optimal time-frequency localized wavelet filters for identification of Alzheimer's disease from EEG signals

Alzheimer's disease (AD) is a chronic disability that occurs due to the loss of neurons. The traditional methods to detect AD involve questionnaires and expensive neuro-imaging tests, which are time-consuming, subjective, and inconvenient to the target population. To overcome these limitations, Electroencephalogram (EEG) based methods have been developed to classify AD patients from normal controlled (NC) and mild cognitive impairment (MCI) subjects. Most of the EEG-based methods involved entropy-based feature extraction and discrete wavelet transform. However, the existing AD classification methods failed to provide promising classification accuracy. Here, we proposed a wavelet-machine learning (ML) framework to detect AD using a newly designed biorthogonal filter bank by optimization of frequency and time localization of triplet halfband filter banks (OTFL-THFB). The OTFL-THFB decomposes EEG signals into various EEG sub- bands. Hjorth Parameters (HP) and Higuchi's Fractal Dimension (HFD) have been investigated to extract features from each EEG subband. Subsequently, ML models are trained and tested using different features such as OTFL-THFB with HFD, OTFL-THFB with HP, and OTFL-THFB with HFD and HP used for detecting AD with 10-fold cross-validation. This method was applied to two publicly available datasets. Our model achieved an accuracy of 98.91 % for AD versus NC and 98.65 % for AD versus MCI versus NC using the least square support vector machine. Results indicate that this framework surpassed existing state-of-the-art techniques for classifying AD from NC.

An exploration of distinguishing subjective cognitive decline and mild cognitive impairment based on resting-state prefrontal functional connectivity assessed by functional near-infrared spectroscopy

Purpose

Functional near-infrared spectroscopy (fNIRS) has shown feasibility in evaluating cognitive function and brain functional connectivity (FC). Therefore, this fNIRS study aimed to develop a screening method for subjective cognitive decline (SCD) and mild cognitive impairment (MCI) based on resting-state prefrontal FC and neuropsychological tests via machine learning.

Methods

Functional connectivity data measured by fNIRS were collected from 55 normal controls (NCs), 80 SCD individuals, and 111 MCI individuals. Differences in FC were analyzed among the groups. FC strength and neuropsychological test scores were extracted as features to build classification and predictive models through machine learning. Model performance was assessed based on accuracy, specificity, sensitivity, and area under the curve (AUC) with 95% confidence interval (CI) values.

Results

Statistical analysis revealed a trend toward compensatory enhanced prefrontal FC in SCD and MCI individuals. The models showed a satisfactory ability to differentiate among the three groups, especially those employing linear discriminant analysis, logistic regression, and support vector machine. Accuracies of 94.9% for MCI vs. NC, 79.4% for MCI vs. SCD, and 77.0% for SCD vs. NC were achieved, and the highest AUC values were 97.5% (95% CI: 95.0%-100.0%) for MCI vs. NC, 83.7% (95% CI: 77.5%-89.8%) for MCI vs. SCD, and 80.6% (95% CI: 72.7%-88.4%) for SCD vs. NC.

Conclusion

The developed screening method based on resting-state prefrontal FC measured by fNIRS and machine learning may help predict early-stage cognitive impairment.

An EEG-based framework for automated discrimination of conversion to Alzheimer's disease in patients with amnestic mild cognitive impairment: an 18-month longitudinal study

Background

As a clinical precursor to Alzheimer's disease (AD), amnestic mild cognitive impairment (aMCI) bears a considerably heightened risk of transitioning to AD compared to cognitively normal elders. Early prediction of whether aMCI will progress to AD is of paramount importance, as it can provide pivotal guidance for subsequent clinical interventions in an early and effective manner.

Methods

A total of 107 aMCI cases were enrolled and their electroencephalogram (EEG) data were collected at the time of the initial diagnosis. During 18-month follow-up period, 42 individuals progressed to AD (PMCI), while 65 remained in the aMCI stage (SMCI). Spectral, nonlinear, and functional connectivity features were extracted from the EEG data, subjected to feature selection and dimensionality reduction, and then fed into various machine learning classifiers for discrimination. The performance of each model was assessed using 10-fold cross-validation and evaluated in terms of accuracy (ACC), area under the curve (AUC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), and F1-score.

Results

Compared to SMCI patients, PMCI patients exhibit a trend of "high to low" frequency shift, decreased complexity, and a disconnection phenomenon in EEG signals. An epoch-based classification procedure, utilizing the extracted EEG features and k-nearest neighbor (KNN) classifier, achieved the ACC of 99.96%, AUC of 99.97%, SEN of 99.98%, SPE of 99.95%, PPV of 99.93%, and F1-score of 99.96%. Meanwhile, the subject-based classification procedure also demonstrated commendable performance, achieving an ACC of 78.37%, an AUC of 83.89%, SEN of 77.68%, SPE of 76.24%, PPV of 82.55%, and F1-score of 78.47%.

Conclusion

Aiming to explore the EEG biomarkers with predictive value for AD in the early stages of aMCI, the proposed discriminant framework provided robust longitudinal evidence for the trajectory of the aMCI cases, aiding in the achievement of early diagnosis and proactive intervention.

Machine learning based on event-related oscillations of working memory differentiates between preclinical Alzheimer's disease and normal aging

OBJECTIVE

To apply machine learning approaches on EEG event-related oscillations (ERO) to discriminate preclinical Alzheimer's disease (AD) from age- and sex-matched controls.

METHODS

Twenty-two cognitively normal preclinical AD participants with elevated amyloid and 21 cognitively normal controls without elevated amyloid completed n-back working memory tasks (n = 0, 1, 2). The absolute and relative power of ERO was extracted using the discrete wavelet transform in the delta, theta, alpha, and beta bands. Four machine learning methods were employed, and classification performance was assessed using three metrics.

RESULTS

The low-frequency bands produced higher discriminative performances compared to high-frequency bands. The 2-back task yielded the best classification capability among the three tasks. The highest area under the curve value (0.86) was achieved in the 2-back delta band nontarget condition data. The highest accuracy (80.47%) was obtained in the 2-back delta and theta bands nontarget data. The highest F1 score (0.82) was in the 2-back theta band nontarget data. The support vector machine achieved the highest performance among tested classifiers.

CONCLUSION

This study demonstrates the promise of using machine learning on EEG ERO from working memory tasks to detect preclinical AD.

SIGNIFICANCE

EEG ERO may reveal pathophysiological differences in the earliest stage of AD when no cognitive impairments are apparent.

Towards discovery and implementation of neurophysiologic biomarkers of Alzheimer's disease using entropy methods

Alzheimer's disease (AD) is a prevalent and debilitating neurodegenerative disease that leads to substantial loss of quality of life. Therapies currently available for AD do not modify the disease course and have limited efficacy in symptom control. As such, novel and precise therapies tailored to individual patients' neurophysiologic profiles are needed. Functional neuroimaging tools have demonstrated substantial potential to provide quantifiable insight into brain function in various neurologic disorders, particularly AD. Entropy, a novel analysis for better understanding the nonlinear nature of neurophysiological data, has demonstrated consistent accuracy in disease detection. This literature review characterizes the use of entropy-based analyses from functional neuroimaging tools, including electroencephalography (EEG) and magnetoencephalography (MEG), in patients with AD for disease detection, therapeutic response measurement, and providing clinical insights.

STEADYNet: Spatiotemporal EEG analysis for dementia detection using convolutional neural network

Dementia is a neuro-degenerative disorder with a high death rate, mainly due to high human error, time, and cost of the current clinical diagnostic techniques. The existing dementia detection methods using hand-crafted electroencephalogram (EEG) signal features are unreliable. A convolution neural network using spatiotemporal EEG signals (STEADYNet) is presented to improve the dementia detection. The STEADYNet uses a multichannel temporal EEG signal as input. The network is grouped into feature extraction and classification components. The feature extraction comprises two convolution layers to generate complex features, a max-pooling layer to reduce the EEG signal's spatiotemporal redundancy, and a dropout layer to improve the network's generalization. The classification processes the feature extraction output nonlinearly using two fully-connected layers to generate salient features and a softmax layer to generate disease probabilities. Two publicly available multiclass datasets of dementia are used for evaluation. The STEADYNet outperforms existing automatic dementia detection methods with accuracies of 99.29 % , 99.65 % , and 92.25 % for Alzheimer's disease, mild cognitive impairment, and frontotemporal dementia, respectively. The STEADYNet has a low inference time and floating point operations, suitable for real-time applications. It may aid neurologists in efficient detection and treatment. A Python implementation of the STEADYNet is available at https://github.com/SandeepSangle12/STEADYNet.git.

LCADNet: a novel light CNN architecture for EEG-based Alzheimer disease detection

Alzheimer's disease (AD) is a progressive and incurable neurologi-cal disorder with a rising mortality rate, worsened by error-prone, time-intensive, and expensive clinical diagnosis methods. Automatic AD detection methods using hand-crafted Electroencephalogram (EEG) signal features lack accuracy and reliability. A lightweight convolution neural network for AD detection (LCADNet) is investigated to extract disease-specific features while reducing the detection time. The LCADNet uses two convolutional layers for extracting complex EEG features, two fully connected layers for selecting disease-specific features, and a softmax layer for predicting AD detection probability. A max-pooling layer interlaced between convolutional layers decreases the time-domain redundancy in the EEG signal. The efficiency of the LCADNet and four pre-trained models using transfer learning is compared using a publicly available AD detection dataset. The LCADNet shows the lowest computation complexity in terms of both the number of floating point operations and inference time and the highest classification performance across six measures. The generalization of the LCADNet is assessed by cross-testing it with two other publicly available AD detection datasets. It outperforms existing EEG-based AD detection methods with an accuracy of 98.50%. The LCADNet may be a valuable aid for neurologists and its Python implemen- tation can be found at github.com/SandeepSangle12/LCADNet.git.

Role of GABAB receptors in cognition and EEG activity in aged APP and PS1 transgenic mice

Alzheimer's disease (AD) is the most common cause of dementia in the elderly. Recent evidence suggests that gamma-aminobutyric acid B (GABAB) receptor-mediated inhibition is a major contributor to AD pathobiology, and GABAB receptors have been hypothesized to be a potential target for AD treatment. The aim of this study is to determine how GABAB regulation alters cognitive function and brain activity in an AD mouse model. Early, middle and late stage (8-23 months) amyloid precursor protein (APP) and presenilin 1 (PS1) transgenic mice were used for the study. The GABAB agonist baclofen (1 and 2.5 mg/kg, i. p.) and the antagonist phaclofen (0.5 mg/kg, i. p.) were used. Primarily, we found that GABAB activation was able to improve spatial and/or working memory performance in early and late stage AD animals. In addition, GABAB activation and inhibition could regulate global and local EEG oscillations in AD animals, with activation mainly regulating low-frequency activity (delta-theta bands) and inhibition mainly regulating mid- and high-frequency activity (alpha-gamma bands), although the regulated magnitude at some frequencies was reduced in AD. The cognitive improvements in AD animals may be explained by the reduced EEG activity in the theta frequency band (2-4 Hz). This study provides evidence for a potential therapeutic effect of baclofen in the elderly AD brain and for GABAB receptor-mediated inhibition as a potential therapeutic target for AD.

Classification of cognitive ability of healthy older individuals using resting-state functional connectivity magnetic resonance imaging and an extreme learning machine

BACKGROUND

Quantitative determination of the correlation between cognitive ability and functional biomarkers in the older brain is essential. To identify biomarkers associated with cognitive performance in the older, this study combined an index model specific for resting-state functional connectivity (FC) with a supervised machine learning method.

METHODS

Performance scores on conventional cognitive test scores and resting-state functional MRI data were obtained for 98 healthy older individuals and 90 healthy youth from two public databases. Based on the test scores, the older cohort was categorized into two groups: excellent and poor. A resting-state FC scores model (rs-FCSM) was constructed for each older individual to determine the relative differences in FC among brain regions compared with that in the youth cohort. Brain areas sensitive to test scores could then be identified using this model. To suggest the effectiveness of constructed model, the scores of these brain areas were used as feature matrix inputs for training an extreme learning machine. classification accuracy (CA) was then tested in separate groups and validated by N-fold cross-validation.

RESULTS

This learning study could effectively classify the cognitive status of healthy older individuals according to the model scores of frontal lobe, temporal lobe, and parietal lobe with a mean accuracy of 86.67%, which is higher than that achieved using conventional correlation analysis.

CONCLUSION

This classification study of the rs-FCSM may facilitate early detection of age-related cognitive decline as well as help reveal the underlying pathological mechanisms.

[EEG changes in patients with Alzheimer's disease]

The prevalence of cognitive impairment is steadily increasing compared to previous years. According to the World Health Organization, the number of people living with dementia will increase reaching 82 million in 2030 and 152 million in 2050. The most common cause is Alzheimer's disease (AD). The pathophysiological process in AD begins several years before the onset of clinical symptoms; so identifying it at an early stage would likely improve the clinical prognosis. The article presents EEG changes in patients with AD, and discusses the possibility of using EEG as a screening method for examining patients with cognitive impairment.

PLI-Based Connectivity in Resting-EEG is a Robust and Generalizable Feature for Detecting MCI and AD: A Validation on a Diverse Multisite Clinical Dataset

The high prevalence rate of Alzheimer's disease (AD) and mild cognitive impairment (MCI) has been a serious public health threat to the modern society. Recently, many studies have demonstrated the potential of using non-invasive electroencephalography (EEG) and machine learning to assist the diagnosis of AD/MCI. However, the majority of these research recorded EEG signals from a single center, leading to significant concerns regarding the generalizability of the findings in clinical settings. The current study aims to reevaluate the effectiveness of EEG-based machine learning model for the detection of AD/MCI in the case of a relatively large and diverse data set. We collected resting-state EEG data from 150 participants across six hospitals and examined the classification performances of Linear Discriminative Analysis (LDA) classifiers on the phase lag index (PLI) feature. We also compared the performance of PLI over the other commonly-used EEG features and other classifiers. The model was first tested on a training set to select the feature subset and then further validated with an independent test set. The results demonstrate that PLI performs the best compared to other features. The LDA classifier trained with the optimal PLI features can provide 82.50% leave-one-participant-out cross-validation (LOPO-CV) accuracy on the training set and maintain a good enough performance with 75.00% accuracy on the test set. Our results suggest that PLI-based functional connectivity could be considered as a reliable bio-maker to detect AD/MCI in the real-world clinical settings.

An attention-based deep learning approach for the classification of subjective cognitive decline and mild cognitive impairment using resting-state EEG

Objective. This study aims to design and implement the first deep learning (DL) model to classify subjects in the prodromic states of Alzheimer's disease (AD) based on resting-state electroencephalographic (EEG) signals.Approach. EEG recordings of 17 healthy controls (HCs), 56 subjective cognitive decline (SCD) and 45 mild cognitive impairment (MCI) subjects were acquired at resting state. After preprocessing, we selected sections corresponding to eyes-closed condition. Five different datasets were created by extracting delta, theta, alpha, beta and delta-to-theta frequency bands using bandpass filters. To classify SCDvsMCI and HCvsSCDvsMCI, we propose a framework based on the transformer architecture, which uses multi-head attention to focus on the most relevant parts of the input signals. We trained and validated the model on each dataset with a leave-one-subject-out cross-validation approach, splitting the signals into 10 s epochs. Subjects were assigned to the same class as the majority of their epochs. Classification performances of the transformer were assessed for both epochs and subjects and compared with other DL models.Main results. Results showed that the delta dataset allowed our model to achieve the best performances for the discrimination of SCD and MCI, reaching an Area Under the ROC Curve (AUC) of 0.807, while the highest results for the HCvsSCDvsMCI classification were obtained on alpha and theta with a micro-AUC higher than 0.74.Significance. We demonstrated that DL approaches can support the adoption of non-invasive and economic techniques as EEG to stratify patients in the clinical population at risk for AD. This result was achieved since the attention mechanism was able to learn temporal dependencies of the signal, focusing on the most discriminative patterns, achieving state-of-the-art results by using a deep model of reduced complexity. Our results were consistent with clinical evidence that changes in brain activity are progressive when considering early stages of AD.

Inter-Hospital Advanced and Mild Alzheimer's Disease Classification Based on Electroencephalogram Measurements via Classical Machine Learning Algorithms

BACKGROUND

In pursuit of diagnostic tools capable of targeting distinct stages of Alzheimer's disease (AD), this study explores the potential of electroencephalography (EEG) combined with machine learning (ML) algorithms to identify patients with mild or moderate AD (ADM) and advanced AD (ADA).

OBJECTIVE

This study aims to assess the classification accuracy of six classical ML algorithms using a dataset of 668 patients from multiple hospitals.

METHODS

The dataset comprised measurements obtained from 668 patients, distributed among control, ADM, and ADA groups, collected from five distinct hospitals between 2011 and 2022. For classification purposes, six classical ML algorithms were employed: support vector machine, Bayesian linear discriminant analysis, decision tree, Gaussian Naïve Bayes, K-nearest neighbor and random forest.

RESULTS

The RF algorithm exhibited outstanding performance, achieving a remarkable balanced accuracy of 93.55% for ADA classification and 93.25% for ADM classification. The consistent reliability in distinguishing ADA and ADM patients underscores the potential of the EEG-based approach for AD diagnosis.

CONCLUSIONS

By leveraging a dataset sourced from multiple hospitals and encompassing a substantial patient cohort, coupled with the straightforwardness of the implemented models, it is feasible to attain notably robust results in AD classification.

Classification of mild cognitive impairment based on handwriting dynamics and qEEG

Subtle changes in fine motor control and quantitative electroencephalography (qEEG) in patients with mild cognitive impairment (MCI) are important in screening for early dementia in primary care populations. In this study, an automated, non-invasive and rapid detection protocol for mild cognitive impairment based on handwriting kinetics and quantitative EEG analysis was proposed, and a classification model based on a dual fusion of feature and decision layers was designed for clinical decision-marking. Seventy-nine volunteers (39 healthy elderly controls and 40 patients with mild cognitive impairment) were recruited for this study, and the handwritten data and the EEG signals were performed using a tablet and MUSE under four designed handwriting tasks. Sixty-eight features were extracted from the EEG and handwriting parameters of each test. Features selected from both models were fused using a late feature fusion strategy with a weighted voting strategy for decision making, and classification accuracy was compared using three different classifiers under handwritten features, EEG features and fused features respectively. The results show that the dual fusion model can further improve the classification accuracy, with the highest classification accuracy for the combined features and the best classification result of 96.3% using SVM with RBF kernel as the base classifier. In addition, this not only supports the greater significance of multimodal data for differentiating MCI, but also tests the feasibility of using the portable EEG headband as a measure of EEG in patients with cognitive impairment.

Brain signal complexity in adults with Down syndrome: Potential application in the detection of mild cognitive impairment

Background

Down syndrome (DS) is considered the most frequent cause of early-onset Alzheimer’s disease (AD), and the typical pathophysiological signs are present in almost all individuals with DS by the age of 40. Despite of this evidence, the investigation on the pre-dementia stages in DS is scarce. In the present study we analyzed the complexity of brain oscillatory patterns and neuropsychological performance for the characterization of mild cognitive impairment (MCI) in DS.

Materials and methods

Lempel-Ziv complexity (LZC) values from resting-state magnetoencephalography recordings and the neuropsychological performance in 28 patients with DS [control DS group (CN-DS) (n = 14), MCI group (MCI-DS) (n = 14)] and 14 individuals with typical neurodevelopment (CN-no-DS) were analyzed.

Results

Lempel-Ziv complexity was lowest in the frontal region within the MCI-DS group, while the CN-DS group showed reduced values in parietal areas when compared with the CN-no-DS group. Also, the CN-no-DS group exhibited the expected pattern of significant increase of LZC as a function of age, while MCI-DS cases showed a decrease. The combination of reduced LZC values and a divergent trajectory of complexity evolution with age, allowed the discrimination of CN-DS vs. MCI-DS patients with a 92.9% of sensitivity and 85.7% of specificity. Finally, a pattern of mnestic and praxic impairment was significantly associated in MCI-DS cases with the significant reduction of LZC values in frontal and parietal regions (p = 0.01).

Conclusion

Brain signal complexity measured with LZC is reduced in DS and its development with age is also disrupted. The combination of both features might assist in the detection of MCI within this population.

Dysfunction of Emotion Regulation in Mild Cognitive Impairment Individuals Combined With Depressive Disorder: A Neural Mechanism Study

Depression increases the risk of progression from mild cognitive impairment (MCI) to dementia, where impaired emotion regulation is a core symptom of depression. However, the neural mechanisms underlying the decreased emotion regulation in individuals with MCI combined with depressive symptoms are not precise. We assessed the behavioral performance by emotion regulation tasks and recorded event-related electroencephalography (EEG) signals related to emotion regulation tasks simultaneously. EEG analysis, including event-related potential (ERP), event-related spectral perturbation (ERSP), functional connectivity and graph theory, was used to compare the difference between MCI individuals and MCI depressed individuals in behavioral performance, the late positive potential (LPP) amplitudes, neural oscillations and brain networks during the processing of emotional stimuli. We found that MCI depressed individuals have negative preferences and are prone to allocate more attentional resources to negative stimuli. Results suggested that theta and alpha oscillations activity is increased, and gamma oscillations activity is decreased during negative stimulus processing in MCI depressed individuals, thus indicating that the decreased emotion regulation in MCI depressed individuals may be associated with enhanced low-frequency and decreased high-frequency oscillations activity. Functional connectivity analysis revealed a decrease in functional connectivity in the left cerebral hemisphere of the alpha band and an increase in functional connectivity in the right cerebral hemisphere of the alpha band in MCI depressed individuals. Graph theory analysis suggested that global network metrics, including clustering coefficients and disassortative, decreased, while nodal and modular network metrics regarding local nodal efficiency, degree centrality, and betweenness centrality were significantly increased in the frontal lobe and decreased in the parieto-occipital lobe, which was observed in the alpha band, further suggesting that abnormal alpha band network connectivity may be a potential marker of depressive symptoms. Correlational analyses showed that depressive symptoms were closely related to emotion regulation, power oscillations and functional connectivity. In conclusion, the dominant processing of negative stimuli, the increased low-frequency oscillations activity and decreased high-frequency activity, so as the decrease in top-down information processing in the frontal parieto-occipital lobe, results in the abnormality of alpha-band network connectivity. It is suggested that these factors, in turn, contribute to the declined ability of MCI depressed individuals in emotion regulation.

Alzheimer's Disease Analysis Algorithm Based on No-threshold Recurrence Plot Convolution Network

Alzheimer's disease is a neurological disorder characterized by progressive cognitive dysfunction and behavioral impairment that occurs in old. Early diagnosis and treatment of Alzheimer's disease is great significance. Electroencephalography (EEG) signals can be used to detect Alzheimer's disease due to its non-invasive advantage. To solve the problem of insufficient analysis by single-channel EEG signal, we analyze the relationship between multiple channels and build PLV framework. To solve the problem of insufficient representation of 1D signal, a threshold-free recursive plot convolution network was constructed to realize 2D representation. To solve the problem of insufficient EEG signal characterization, a fusion algorithm of clinical features and imaging features was proposed to detect Alzheimer's disease. Experimental results show that the algorithm has good performance and robustness.