Alzheimer's Disease Diagnosis and Severity Level Detection Based on Electroencephalography Modulation Spectral "Patch" Features

EEG Amplitude Modulation Analysis across Mental Tasks: Towards Improved Active BCIs

Brain-computer interface (BCI) technology has emerged as an influential communication tool with extensive applications across numerous fields, including entertainment, marketing, mental state monitoring, and particularly medical neurorehabilitation. Despite its immense potential, the reliability of BCI systems is challenged by the intricacies of data collection, environmental factors, and noisy interferences, making the interpretation of high-dimensional electroencephalogram (EEG) data a pressing issue. While the current trends in research have leant towards improving classification using deep learning-based models, our study proposes the use of new features based on EEG amplitude modulation (AM) dynamics. Experiments on an active BCI dataset comprised seven mental tasks to show the importance of the proposed features, as well as their complementarity to conventional power spectral features. Through combining the seven mental tasks, 21 binary classification tests were explored. In 17 of these 21 tests, the addition of the proposed features significantly improved classifier performance relative to using power spectral density (PSD) features only. Specifically, the average kappa score for these classifications increased from 0.57 to 0.62 using the combined feature set. An examination of the top-selected features showed the predominance of the AM-based measures, comprising over 77% of the top-ranked features. We conclude this paper with an in-depth analysis of these top-ranked features and discuss their potential for use in neurophysiology.

Using CNN Saliency Maps and EEG Modulation Spectra for Improved and More Interpretable Machine Learning-Based Alzheimer's Disease Diagnosis

Biomarkers based on resting-state electroencephalography (EEG) signals have emerged as a promising tool in the study of Alzheimer's disease (AD). Recently, a state-of-the-art biomarker was found based on visual inspection of power modulation spectrograms where three "patches" or regions from the modulation spectrogram were proposed and used for AD diagnostics. Here, we propose the use of deep neural networks, in particular convolutional neural networks (CNNs) combined with saliency maps, trained on power modulation spectrogram inputs to find optimal patches in a data-driven manner. Experiments are conducted on EEG data collected from fifty-four participants, including 20 healthy controls, 19 patients with mild AD, and 15 moderate-to-severe AD patients. Five classification tasks are explored, including the three-class problem, early-stage detection (control vs. mild-AD), and severity level detection (mild vs. moderate-to-severe). Experimental results show the proposed biomarkers outperform the state-of-the-art benchmark across all five tasks, as well as finding complementary modulation spectrogram regions not previously seen via visual inspection. Lastly, experiments are conducted on the proposed biomarkers to test their sensitivity to age, as this is a known confound in AD characterization. Across all five tasks, none of the proposed biomarkers showed a significant relationship with age, thus further highlighting their usefulness for automated AD diagnostics.

Automatic detection of abnormal EEG signals using multiscale features with ensemble learning

Electroencephalogram (EEG) is an economical and convenient auxiliary test to aid in the diagnosis and analysis of brain-related neurological diseases. In recent years, machine learning has shown great potential in clinical EEG abnormality detection. However, existing methods usually fail to consider the issue of feature redundancy when extracting the relevant EEG features. In addition, the importance of utilizing the patient age information in EEG detection is ignored. In this paper, a new framework is proposed for distinguishing an unknown EEG recording as either normal or abnormal by identifying different types of EEG-derived significant features. In the proposed framework, different hierarchical salient features are extracted using a time-wise multi-scale aggregation strategy, based on a selected group of statistical characteristics calculated from the optimum discrete wavelet transform coefficients. We also fuse the age information with multi-scale features for further improving discrimination. The integrated features are classified using three ensemble learning classifiers, CatBoost, LightGBM, and random forest. Experimental results show that our method with CatBoost classifier can yield superior performance vis-a-vis competing techniques, which indicates the great promise of our methodology in EEG pathology detection.

Modulation Spectral Signal Representation for Quality Measurement and Enhancement of Wearable Device Data: A Technical Note

Wearable devices are burgeoning, and applications across numerous verticals are emerging, including human performance monitoring, at-home patient monitoring, and health tracking, to name a few. Off-the-shelf wearables have been developed with focus on portability, usability, and low-cost. As such, when deployed in highly ecological settings, wearable data can be corrupted by artifacts and by missing data, thus severely hampering performance. In this technical note, we overview a signal processing representation called the modulation spectrum. The representation quantifies the rate-of-change of different spectral magnitude components and is shown to separate signal from noise, thus allowing for improved quality measurement, quality enhancement, and noise-robust feature extraction, as well as for disease characterization. We provide an overview of numerous applications developed by the authors over the last decade spanning different wearable modalities and list the results obtained from experimental results alongside comparisons with various state-of-the-art benchmark methods. Open-source software is showcased with the hope that new applications can be developed. We conclude with a discussion on possible future research directions, such as context awareness, signal compression, and improved input representations for deep learning algorithms.

Sleep EEG-Based Approach to Detect Mild Cognitive Impairment

Mild Cognitive Impairment (MCI) is an early stage of dementia, which may lead to Alzheimer's disease (AD) in older adults. Therefore, early detection of MCI and implementation of treatment and intervention can effectively slow down or even inhibit the progression of the disease, thus minimizing the risk of AD. Currently, we know that published work relies on an analysis of awake EEG recordings. However, recent studies have suggested that changes in the structure of sleep may lead to cognitive decline. In this work, we propose a sleep EEG-based method for MCI detection, extracting specific features of sleep to characterize neuroregulatory deficit emergent with MCI. This study analyzed the EEGs of 40 subjects (20 MCI, 20 HC) with the developed algorithm. We extracted sleep slow waves and spindles features, combined with spectral and complexity features from sleep EEG, and used the SVM classifier and GRU network to identify MCI. In addition, the classification results of different feature sets (including with sleep features from sleep EEG and without sleep features from awake EEG) and different classification methods were evaluated. Finally, the MCI classification accuracy of the GRU network based on features extracted from sleep EEG was the highest, reaching 93.46%. Experimental results show that compared with the awake EEG, sleep EEG can provide more useful information to distinguish between MCI and HC. This method can not only improve the classification performance but also facilitate the early intervention of AD.

Multimodal Prediction of Alzheimer's Disease Severity Level Based on Resting-State EEG and Structural MRI

While several biomarkers have been developed for the detection of Alzheimer's disease (AD), not many are available for the prediction of disease severity, particularly for patients in the mild stages of AD. In this paper, we explore the multimodal prediction of Mini-Mental State Examination (MMSE) scores using resting-state electroencephalography (EEG) and structural magnetic resonance imaging (MRI) scans. Analyses were carried out on a dataset comprised of EEG and MRI data collected from 89 patients diagnosed with minimal-mild AD. Three feature selection algorithms were assessed alongside four machine learning algorithms. Results showed that while MRI features alone outperformed EEG features, when both modalities were combined, improved results were achieved. The top-selected EEG features conveyed information about amplitude modulation rate-of-change, whereas top-MRI features comprised information about cortical area and white matter volume. Overall, a root mean square error between predicted MMSE values and true MMSE scores of 1.682 was achieved with a multimodal system and a random forest regression model.

Lacsogram: A New EEG Tool to Diagnose Alzheimer's Disease

This work proposes the application of a new electroencephalogram (EEG) signal processing tool - the lacsogram - to characterize the Alzheimer's disease (AD) activity and to assist on its diagnosis at different stages: Mild Cognitive Impairment (MCI), Mild and Moderate AD (ADM) and Advanced AD (ADA). Statistical analyzes are performed to lacstral distances between conventional EEG subbands to find measures capable of discriminating AD in all stages and characterizing the AD activity in each electrode. Cepstral distances are used for comparison. Comparing all AD stages and Controls (C), the most important significances are the lacstral distances between subbands θ and α ( p = 0.0014 0.05). The topographic maps show significant differences in parietal, temporal and frontal regions as AD progresses. Machine learning models with a leave-one-out cross-validation process are applied to lacstral/cepstral distances to develop an automatic method for diagnosing AD. The following classification accuracies are obtained with an artificial neural network: 95.55% for All vs All, 98.06% for C vs MCI, 95.99% for C vs ADM, 93.85% for MCI vs ADM-ADA. In C vs MCI, C vs ADM and MCI vs ADM-ADA, the proposed method outperforms the state-of-art methods by 5%, 1%, and 2%, respectively. In All vs All, it outperforms the state-of-art EEG and non-EEG methods by 6% and 2%, respectively. These results indicate that the proposed method represents an improvement in diagnosing AD.

Quantitative Assessment of Friedreich Ataxia via Self-Drinking Activity

Effective monitoring of the progression of neurodegenerative conditions can be significantly improved by objective assessments. Clinical assessments of conditions such as Friedreich's Ataxia (FA), currently rely on subjective measures commonly practiced in clinics as well as the ability of the affected individual to perform conventional tests of the neurological examination. In this study, we propose an ataxia measuring device, in the form of a pressure canister capable of sensing certain kinetic and kinematic parameters of interest to quantify the impairment levels of participants particularly when engaged in an activity that is closely associated with daily living. In particular, the functional task of simulated drinking was utilised to capture characteristic features of disability manifestation in terms of diagnosis (separation of individuals with FA and controls) and severity assessment of individuals diagnosed with the debilitating condition of FA. Time and frequency domain analysis of these biomarkers enabled the classification of individuals with FA and control subjects to reach an accuracy of 98% and a correlation level reaching 96% with the clinical scores.

Interval-based features of auditory ERPs for diagnosis of early Alzheimer's disease

INTRODUCTION

It has been demonstrated that event-related potentials (ERPs) mirror the neurodegenerative process of Alzheimer's disease (AD) and may therefore qualify as diagnostic markers. The aim of this study was to explore the potential of interval-based features as possible ERP biomarkers for early detection of AD patients.

METHODS

The current results are based on 7-channel ERP recordings of 95 healthy controls (HCs) and 75 subjects with mild AD acquired during a three-stimulus auditory oddball task. To evaluate interval-based features as diagnostic biomarkers in AD, two classifiers were applied to the selected features to distinguish AD and healthy control ERPs: RBFNN (radial basis function neural network) and MLP (multilayer perceptron).

RESULTS

Using extracted features and a radial basis function neural network, a high overall diagnostic accuracy of 98.3% was achieved.

DISCUSSION

Our findings demonstrate the great promise for scalp ERP and interval-based features as non-invasive, objective, and low-cost biomarkers for early AD detection.