A method for detection of Alzheimer's disease using ICA-enhanced EEG measurements

IoMT-Based Platform for E-Health Monitoring Based on the Blockchain

With the evolution of information technology, the use of internet of things has increased. It affects several areas such as medical field, smart cities, and information systems. In this work, we will use this technological development in the context of health, particularly e-health. We present a platform based on IoMT to allow the monitoring of patient’s health. To meet the constraint of medical secrecy and confidentiality of information, we will use the Blockchain as a secure system. Our system will use the data collected by several smart sensors such as blood pressure, SPO2 concentration, and EEG signals. These encrypted data will be collected by an embedded Raspberry PI 4 platform (working as a smart data relay) before being processed (on a backend server) and then saved in an embedded Blockchain node. The preliminary results show the effectiveness of the proposed platform as a candidate of a low-cost example of secured Electronic Health Record (EHR).

Single-Channel EEG Features Reveal an Association With Cognitive Decline in Seniors Performing Auditory Cognitive Assessment

Background

Cognitive decline remains highly underdiagnosed despite efforts to find novel cognitive biomarkers. Electroencephalography (EEG) features based on machine-learning (ML) may offer a non-invasive, low-cost approach for identifying cognitive decline. However, most studies use cumbersome multi-electrode systems. This study aims to evaluate the ability to assess cognitive states using machine learning (ML)-based EEG features extracted from a single-channel EEG with an auditory cognitive assessment.

Methods

This study included data collected from senior participants in different cognitive states (60) and healthy controls (22), performing an auditory cognitive assessment while being recorded with a single-channel EEG. Mini-Mental State Examination (MMSE) scores were used to designate groups, with cutoff scores of 24 and 27. EEG data processing included wavelet-packet decomposition and ML to extract EEG features. Data analysis included Pearson correlations and generalized linear mixed-models on several EEG variables: Delta and Theta frequency-bands and three ML-based EEG features: VC9, ST4, and A0, previously extracted from a different dataset and showed association with cognitive load.

Results

MMSE scores significantly correlated with reaction times and EEG features A0 and ST4. The features also showed significant separation between study groups: A0 separated between the MMSE < 24 and MMSE ≥ 28 groups, in addition to separating between young participants and senior groups. ST4 differentiated between the MMSE < 24 group and all other groups (MMSE 24–27, MMSE ≥ 28 and healthy young groups), showing sensitivity to subtle changes in cognitive states. EEG features Theta, Delta, A0, and VC9 showed increased activity with higher cognitive load levels, present only in the healthy young group, indicating different activity patterns between young and senior participants in different cognitive states. Consisted with previous reports, this association was most prominent for VC9 which significantly separated between all level of cognitive load.

Discussion

This study successfully demonstrated the ability to assess cognitive states with an easy-to-use single-channel EEG using an auditory cognitive assessment. The short set-up time and novel ML features enable objective and easy assessment of cognitive states. Future studies should explore the potential usefulness of this tool for characterizing changes in EEG patterns of cognitive decline over time, for detection of cognitive decline on a large scale in every clinic to potentially allow early intervention.

Trial Registration

NIH Clinical Trials Registry [https://clinicaltrials.gov/ct2/show/results/NCT04386902], identifier [NCT04386902]; Israeli Ministry of Health registry [https://my.health.gov.il/CliniTrials/Pages/MOH_2019-10-07_007352.aspx], identifier [007352].

Automatic Classification of Subjects of the PSEN1-E280A Family at Risk of Developing Alzheimer’s Disease Using Machine Learning and Resting State Electroencephalography

Background: The study of genetic variant carriers provides an opportunity to identify neurophysiological changes in preclinical stages. Electroencephalography (EEG) is a low-cost and minimally invasive technique which, together with machine learning, provide the possibility to construct systems that classify subjects that might develop Alzheimer’s disease (AD). Objective: The aim of this paper is to evaluate the capacity of the machine learning techniques to classify healthy Non-Carriers (NonCr) from Asymptomatic Carriers (ACr) of PSEN1-E280A variant for autosomal dominant Alzheimer’s disease (ADAD), using spectral features from EEG channels and brain-related independent components (ICs) obtained using independent component analysis (ICA). Methods: EEG was recorded in 27 ACr and 33 NonCr. Statistical significance analysis was applied to spectral information from channels and group ICA (gICA), standardized low-resolution tomography (sLORETA) analysis was applied over the IC as well. Strategies for feature selection and classification like Chi-square, mutual informationm and support vector machines (SVM) were evaluated over the dataset. Results: A test accuracy up to 83% was obtained by implementing a SVM with spectral features derived from gICA. The main findings are related to theta and beta rhythms, generated in the parietal and occipital regions, like the precuneus and superior parietal lobule. Conclusion: Promising models for classification of preclinical AD due to PSEN-1-E280A variant can be trained using spectral features, and the importance of the beta band and precuneus region is highlighted in asymptomatic stages, opening up the possibility of its use as a screening methodology.

FGANet: fNIRS-guided Attention Network for Hybrid EEG-fNIRS Brain-Computer Interfaces

Non-invasive brain-computer interfaces (BCIs) have been widely used for neural decoding, linking neural signals to control devices. Hybrid BCI systems using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have received significant attention for overcoming the limitations of EEG- and fNIRS-standalone BCI systems. However, most hybrid EEG-fNIRS BCI studies have focused on late fusion because of discrepancies in their temporal resolutions and recording locations. Despite the enhanced performance of hybrid BCIs, late fusion methods have difficulty in extracting correlated features in both EEG and fNIRS signals. Therefore, in this study, we proposed a deep learning-based early fusion structure, which combines two signals before the fully-connected layer, called the fNIRS-guided attention network (FGANet). First, 1D EEG and fNIRS signals were converted into 3D EEG and fNIRS tensors to spatially align EEG and fNIRS signals at the same time point. The proposed fNIRS-guided attention layer extracted a joint representation of EEG and fNIRS tensors based on neurovascular coupling, in which the spatially important regions were identified from fNIRS signals, and detailed neural patterns were extracted from EEG signals. Finally, the final prediction was obtained by weighting the sum of the prediction scores of the EEG and fNIRS-guided attention features to alleviate performance degradation owing to delayed fNIRS response. In the experimental results, the FGANet significantly outperformed the EEG-standalone network. Furthermore, the FGANet has 4.0% and 2.7% higher accuracy than the state-of-the-art algorithms in mental arithmetic and motor imagery tasks, respectively.

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.

Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques

Neurodegenerative diseases have shown an increasing incidence in the older population in recent years. A significant amount of research has been conducted to characterize these diseases. Computational methods, and particularly machine learning techniques, are now very useful tools in helping and improving the diagnosis as well as the disease monitoring process. In this paper, we provide an in-depth review on existing computational approaches used in the whole neurodegenerative spectrum, namely for Alzheimer's, Parkinson's, and Huntington's Diseases, Amyotrophic Lateral Sclerosis, and Multiple System Atrophy. We propose a taxonomy of the specific clinical features, and of the existing computational methods. We provide a detailed analysis of the various modalities and decision systems employed for each disease. We identify and present the sleep disorders which are present in various diseases and which represent an important asset for onset detection. We overview the existing data set resources and evaluation metrics. Finally, we identify current remaining open challenges and discuss future perspectives.

An Overview of ICA/BSS-Based Application to Alzheimer's Brain Signal Processing

Alzheimer's disease (AD) is by far the most common cause of dementia associated with aging. Early and accurate diagnosis of AD and ability to track progression of the disease is increasingly important as potential disease-modifying therapies move through clinical trials. With the advent of biomedical techniques, such as computerized tomography (CT), electroencephalography (EEG), magnetoencephalography (MEG), positron emission tomography (PET), magnetic resonance imaging (MRI), and functional magnetic resonance imaging (fMRI), large amounts of data from Alzheimer's patients have been acquired and processed from which AD-related information or "signals" can be assessed for AD diagnosis. It remains unknown how best to mine complex information from these brain signals to aid in early diagnosis of AD. An increasingly popular technique for processing brain signals is independent component analysis or blind source separation (ICA/BSS) that separates blindly observed signals into original signals that are as independent as possible. This overview focuses on ICA/BSS-based applications to AD brain signal processing.

Is Brain Dynamics Preserved in the EEG After Automated Artifact Removal? A Validation of the Fingerprint Method and the Automatic Removal of Cardiac Interference Approach Based on Microstate Analysis

The assessment of a method for removing artifacts from electroencephalography (EEG) datasets often disregard verifying that global brain dynamics is preserved. In this study, we verified that the recently introduced optimized fingerprint method and the automatic removal of cardiac interference (ARCI) approach not only remove physiological artifacts from EEG recordings but also preserve global brain dynamics, as assessed with a new approach based on microstate analysis. We recorded EEG activity with a high-resolution EEG system during two resting-state conditions (eyes open, 25 volunteers, and eyes closed, 26 volunteers) known to exhibit different brain dynamics. After signal decomposition by independent component analysis (ICA), the independent components (ICs) related to eyeblinks, eye movements, myogenic interference, and cardiac electromechanical activity were identified with the optimized fingerprint method and ARCI approach and statistically compared with the outcome of the expert classification of the ICs by visual inspection. Brain dynamics in two different groups of denoised EEG signals, reconstructed after having removed the artifactual ICs identified by either visual inspection or the automated methods, was assessed by calculating microstate topographies, microstate metrics (duration, occurrence, and coverage), and directional predominance (based on transition probabilities). No statistically significant differences between the expert and the automated classification of the artifactual ICs were found (p > 0.05). Cronbach’s α values assessed the high test–retest reliability of microstate parameters for EEG datasets denoised by the automated procedure. The total EEG signal variance explained by the sets of global microstate templates was about 80% for all denoised EEG datasets, with no significant differences between groups. For the differently denoised EEG datasets in the two recording conditions, we found that the global microstate templates and the sequences of global microstates were very similar (p < 0.01). Descriptive statistics and Cronbach’s α of microstate metrics highlighted no significant differences and excellent consistency between groups (p > 0.5). These results confirm the ability of the optimized fingerprint method and the ARCI approach to effectively remove physiological artifacts from EEG recordings while preserving global brain dynamics. They also suggest that microstate analysis could represent a novel approach for assessing the ability of an EEG denoising method to remove artifacts without altering brain dynamics.

Electroencephalography (EEG) Technology Applications and Available Devices

The electroencephalography (EEG) sensor has become a prominent sensor in the study of brain activity. Its applications extend from research studies to medical applications. This review paper explores various types of EEG sensors and their applications. This paper is for an audience that comprises engineers, scientists and clinicians who are interested in learning more about the EEG sensors, the various types, their applications and which EEG sensor would suit a specific task. The paper also lists the details of each of the sensors currently available in the market, their technical specs, battery life, and where they have been used and what their limitations are.

EEG-Brain Activity Monitoring and Predictive Analysis of Signals Using Artificial Neural Networks

Predictive observation and real-time analysis of the values of biomedical signals and automatic detection of epileptic seizures before onset are beneficial for the development of warning systems for patients because the patient, once informed that an epilepsy seizure is about to start, can take safety measures in useful time. In this article, Daubechies discrete wavelet transform (DWT) was used, coupled with analysis of the correlations between biomedical signals that measure the electrical activity in the brain by electroencephalogram (EEG), electrical currents generated in muscles by electromyogram (EMG), and heart rate monitoring by photoplethysmography (PPG). In addition, we used artificial neural networks (ANN) for automatic detection of epileptic seizures before onset. We analyzed 30 EEG recordings 10 min before a seizure and during the seizure for 30 patients with epilepsy. In this work, we investigated the ANN dimensions of 10, 50, 100, and 150 neurons, and we found that using an ANN with 150 neurons generates an excellent performance in comparison to a 10-neuron-based ANN. However, this analyzes requests in an increased amount of time in comparison with an ANN with a lower neuron number. For real-time monitoring, the neurons number should be correlated with the response time and power consumption used in wearable devices.

Fault Diagnosis of Loader Gearbox Based on an ICA and SVM Algorithm

When a part of the loader’s gearbox fails, this can lead to equipment failure due to the complex internal structure and the interrelationship between the parts. Therefore, it is imperative to research an efficient strategy for transmission fault diagnosis. In this study, the non-contact characteristics of noise diagnosis using sound intensity probes were used to collect noise signals generated under gear breaking conditions. The independent component analysis (ICA) technique was applied for feature extraction from the original data and to reduce the correlation between the signals. The correlation coefficient between the independent components and the source data was used as the input parameters of the support vector machine (SVM) classifier. The separation of the independent components was achieved by MATLAB simulation. The misdiagnosis rate was 5% for 40 sets of test data. A 13-point test platform for noise testing of the loader gearbox was built according to Chinese national standards. Source signals under the normal and fault conditions were analyzed separately by ICA and SVM algorithms. In this case, the misdiagnosis rate was 7.5% for the 40 sets of experimental test data. This proved that the proposed method could effectively realize fault classification and recognition.

Low Complexity Automatic Stationary Wavelet Transform for Elimination of Eye Blinks from EEG

The electroencephalogram signal (EEG) often suffers from various artifacts and noises that have physiological and non-physiological origins. Among these artifacts, eye blink, due to its amplitude is considered to have the most influence on EEG analysis. In this paper, a low complexity approach based on Stationary Wavelet Transform (SWT) and skewness is proposed to remove eye blink artifacts from EEG signals. The proposed method is compared against Automatic Wavelet Independent Components Analysis (AWICA) and Enhanced AWICA. Normalized Root Mean Square Error (NRMSE), Peak Signal-to-Noise Ratio (PSNR), and correlation coefficient ( ρ ) between filtered and pure EEG signals are utilized to quantify artifact removal performance. The proposed approach shows smaller NRMSE, larger PSNR, and larger correlation coefficient values compared to the other methods. Furthermore, the speed of execution of the proposed method is considerably faster than other methods, which makes it more suitable for real-time processing.

Analysis of long range dependence in the EEG signals of Alzheimer patients

Alzheimer's disease (AD), a cognitive disability is analysed using a long range dependence parameter, hurst exponent (HE), calculated based on the time domain analysis of the measured electrical activity of brain. The electroencephalogram (EEG) signals of controls and mild cognitive impairment (MCI)-AD patients are evaluated under normal resting and mental arithmetic conditions. Simultaneous low pass filtering and total variation denoising algorithm is employed for preprocessing. Larger values of HE observed in the right hemisphere of the brain for AD patients indicated a decrease in irregularity of the EEG signal under cognitive task conditions. Correlations between HE and the neuropsychological indices are analysed using bivariate correlation analysis. The observed reduction in the values of Auto mutual information and cross mutual information in the local antero-frontal and distant regions in the brain hemisphere indicates the loss of information transmission in MCI-AD patients.

Analysis of long range dependence in the EEG signals of Alzheimer patients

Alzheimer's disease (AD), a cognitive disability is analysed using a long range dependence parameter, hurst exponent (HE), calculated based on the time domain analysis of the measured electrical activity of brain. The electroencephalogram (EEG) signals of controls and mild cognitive impairment (MCI)-AD patients are evaluated under normal resting and mental arithmetic conditions. Simultaneous low pass filtering and total variation denoising algorithm is employed for preprocessing. Larger values of HE observed in the right hemisphere of the brain for AD patients indicated a decrease in irregularity of the EEG signal under cognitive task conditions. Correlations between HE and the neuropsychological indices are analysed using bivariate correlation analysis. The observed reduction in the values of Auto mutual information and cross mutual information in the local antero-frontal and distant regions in the brain hemisphere indicates the loss of information transmission in MCI-AD patients.

Medical informatics research trend analysis: A text mining approach

The objective of this research is to identify major subject areas of medical informatics and explore the time-variant changes therein. As such it can inform the field about where medical informatics research has been and where it is heading. Furthermore, by identifying subject areas, this study identifies the development trends and the boundaries of medical informatics as an academic field. To conduct the study, first we identified 26,307 articles in PubMed archives which were published in the top medical informatics journals within the timeframe of 2002 to 2013. And then, employing a text mining -based semi-automated analytic approach, we clustered major research topics by analyzing the most frequently appearing subject terms extracted from the abstracts of these articles. The results indicated that some subject areas, such as biomedical, are declining, while other research areas such as health information technology (HIT), Internet-enabled research, and electronic medical/health records (EMR/EHR), are growing. The changes within the research subject areas can largely be attributed to the increasing capabilities and use of HIT. The Internet, for example, has changed the way medical research is conducted in the health care field. While discovering new medical knowledge through clinical and biological experiments is important, the utilization of EMR/EHR enabled the researchers to discover novel medical insight buried deep inside massive data sets, and hence, data analytics research has become a common complement in the medical field, rapidly growing in popularity.

Resting State EEG in Children With Learning Disabilities: An Independent Component Analysis Approach

In this study, the neurophysiological underpinnings of learning disabilities (LD) in children are examined using resting state EEG. We were particularly interested in the neurophysiological differences between children with learning disabilities not otherwise specified (LD-NOS), learning disabilities with verbal disabilities (LD-Verbal), and healthy control (HC) children. We applied 2 different approaches to examine the differences between the different groups. First, we calculated theta/beta and theta/alpha ratios in order to quantify the relationship between slow and fast EEG oscillations. Second, we used a recently developed method for analyzing spectral EEG, namely the group independent component analysis (gICA) model. Using these measures, we identified substantial differences between LD and HC children and between LD-NOS and LD-Verbal children in terms of their spectral EEG profiles. We obtained the following findings: (a) theta/beta and theta/alpha ratios were substantially larger in LD than in HC children, with no difference between LD-NOS and LD-Verbal children; (b) there was substantial slowing of EEG oscillations, especially for gICs located in frontal scalp positions, with LD-NOS children demonstrating the strongest slowing; (c) the estimated intracortical sources of these gICs were mostly located in brain areas involved in the control of executive functions, attention, planning, and language; and (d) the LD-Verbal children demonstrated substantial differences in EEG oscillations compared with LD-NOS children, and these differences were localized in language-related brain areas. The general pattern of atypical neurophysiological activation found in LD children suggests that they suffer from neurophysiological dysfunction in brain areas involved with the control of attention, executive functions, planning, and language functions. LD-Verbal children also demonstrate atypical activation, especially in language-related brain areas. These atypical neurophysiological activation patterns might provide a helpful guide for rehabilitation strategies to treat the deficiencies in these children with LD.

Multiway array decomposition analysis of EEGs in Alzheimer's disease

Methods for the extraction of features from physiological datasets are growing needs as clinical investigations of Alzheimer's disease (AD) in large and heterogeneous population increase. General tools allowing diagnostic regardless of recording sites, such as different hospitals, are essential and if combined to inexpensive non-invasive methods could critically improve mass screening of subjects with AD. In this study, we applied two state of the art multiway array decomposition (MAD) methods to extract unique features from electroencephalograms (EEGs) of AD patients obtained from multiple sites. In comparison to MAD, spectral-spatial average filter (SSFs) of control and AD subjects were used as well as a common blind source separation method, algorithm for multiple unknown signal extraction (AMUSE), and singular value decomposition (SVD) coupled to tensor unfolding. We trained a feed-forward multilayer perceptron (MLP) to validate and optimize AD classification from two independent databases. Using a third EEG dataset, we demonstrated that features extracted from MAD outperformed features obtained from SSFs AMUSE in terms of root mean squared error (RMSE) and reaching up to 100% of accuracy in test condition. We propose that MAD maybe a useful tool to extract features for AD diagnosis offering great generalization across multi-site databases and opening doors to the discovery of new characterization of the disease.

EEG spectro-temporal modulation energy: a new feature for automated diagnosis of Alzheimer's disease

There is recent indication that Alzheimer's disease (AD) can be characterized by atypical modulation of electrophysiological brain activity caused by fibrillar amyloid deposition in specific regions of the brain, such as those related to cognition and memory. In this paper, we propose to objectively characterize EEG sub-band modulation in an attempt to develop an automated noninvasive AD diagnostics tool. First, multi-channel full-band EEG signals are decomposed into five well-known frequency sub-bands: delta, theta, alpha, beta, and gamma. The temporal amplitude envelope of each sub-band is then computed via a Hilbert transformation. The proposed 'spectro-temporal modulation energy' feature measures the rate with which each sub-band is modulated. Modulation energy features are computed for 19 referential EEG signals and seven bipolar signals. Salient features are then selected and used to train four different classifiers, namely, support vector machines, logistic regression, classification and regression trees, and neural networks. Experiments with a database of 34 participants, 22 of which have been clinically diagnosed with probable-AD, show a neural network classifier achieving over 91% accuracy, thus significantly outperforming a classifier trained with conventional spectral-based features.

Evidence-based evaluation of diagnostic accuracy of resting EEG in dementia and mild cognitive impairment

Cognitive impairment is the most frequent chronic condition in the elderly, and dementia is the most disabling form of cognitive impairment in elderly. In the absence of specific and reliable markers of etiologically different dementia syndromes and their preclinical stages, diagnosis in living patients is probabilistic and based on standardized clinical diagnostic criteria. There is still not enough information on the validity of the EEG method in dementia work-up, and an updated evidence-based consensus on appropriateness of this method in the initial evaluation of patients with suspected cognitive disorder and dementia is missing. Using an evidence-based technique we searched for articles on diagnostic accuracy of spontaneous EEG in dementia disorders published from 1980 until June 2008. Inclusion criteria were: original article published in English with 10 or more subjects per diagnostic group, diagnosed according to the established consensus clinical diagnostic criteria used as a "gold standard." In addition, it should have been possible to calculate from the reported results indexes of diagnostic test accuracy: sensitivity, specificity, likelihood ratios and diagnostic odds ratios. Forty-six articles were retrieved that satisfied eligibility criteria. Thirty-four (74%) studies employed case-control design where study population was recruited from consecutive patients at specialist clinic settings, 12 (26%) were prospective in terms of reported clinical followup of study population. Four (9%) studies used population-based samples and 5 (11%) studies stated in methods the recruitment procedures for patients and healthy subjects. Number of patients included in diagnostic groups and healthy subjects varied in included studies between 10 and 180 and 10 and 171, respectively. Figures on sensitivity and specificity across the studies varied widely. Positive likelihood ratio in studies reporting classification accuracies between Alzheimer's disease and controls ranged between 2.3 and 38.5, and diagnostic odds ratios consequently showed large variations between 7 and 219. In conclusion, despite the wealth of published research and reported high indexes of diagnostic accuracy of EEG, and qEEG in particular, in individual studies, evidence of diagnostic utility of resting EEG in dementia and mild cognitive impairment (MCI) is still not sufficient to establish this method for the initial evaluation of subjects with cognitive impairment in the routine clinical practice. Joint effort of preferably multicenter studies using uniform standards should develop optimized methods, investigate added diagnostic value of EEG in clinically established dementia diagnosis and predictive utility of EEG in MCI and questionable dementia.

Assessment of classification improvement in patients with Alzheimer's disease based on magnetoencephalogram blind source separation

OBJECTIVES

In this pilot study, we intended to assess whether a procedure based on blind source separation (BSS) and subsequent partial reconstruction of magnetoencephalogram (MEG) recordings might enhance the differences between MEGs from Alzheimer's disease (AD) patients and elderly control subjects.

MATERIALS AND METHODS

We analysed MEG background activity recordings acquired with a 148-channel whole-head magnetometer from 21 AD patients and 21 control subjects. Artefact-free epochs of 20 s were blindly decomposed using the algorithm for multiple unknown signals extraction (AMUSE), which arranges the extracted components by decreasing linear predictability. Thus, the components of diverse epochs and subjects could be easily compared. Every component was characterised with its median frequency and spectral entropy (denoted by fmedian and SpecEn, respectively). The differences between subject groups in these variables were statistically evaluated to find out which components could improve the subject classification. Then, these significant components were used to partially reconstruct the MEG recordings.

RESULTS

The statistical analysis showed that the AMUSE components which provided the largest differences between demented patients and control subjects were ordered together. Considering this analysis, we defined two subsets, denoted by BSS-{15,35} and BSS-{20,30}, which included 21 components (15-35) and 11 components (20-30), respectively. We partially reconstructed the MEGs with these subsets. Then, the classification performance was computed with a leave-one-out cross-validation procedure for the case where no BSS was applied and for the partial reconstructions BSS-{15,35} and BSS-{20,30}. The BSS and component selection procedure improved the classification accuracy from 69.05% to 83.33% using f(median) with BSS-{15,35} and from 61.91% to 73.81% using SpecEn with BSS-{20,30}.

CONCLUSION

These preliminary results lead us to think that the proposed procedure based on BSS and selection of significant components may improve the classification of AD patients using straightforward features from MEG recordings.

The IFAST model, a novel parallel nonlinear EEG analysis technique, distinguishes mild cognitive impairment and Alzheimer's disease patients with high degree of accuracy

OBJECTIVE

This paper presents the results obtained with the innovative use of special types of artificial neural networks (ANNs) assembled in a novel methodology named IFAST (implicit function as squashing time) capable of compressing the temporal sequence of electroencephalographic (EEG) data into spatial invariants. The aim of this study is to assess the potential of this parallel and nonlinear EEG analysis technique in distinguishing between subjects with mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients with a high degree of accuracy in comparison with standard and advanced nonlinear techniques. The principal aim of the study was testing the hypothesis that automatic classification of MCI and AD subjects can be reasonably correct when the spatial content of the EEG voltage is properly extracted by ANNs.

METHODS AND MATERIAL

Resting eyes-closed EEG data were recorded in 180 AD patients and in 115 MCI subjects. The spatial content of the EEG voltage was extracted by IFAST step-wise procedure using ANNs. The data input for the classification operated by ANNs were not the EEG data, but the connections weights of a nonlinear auto-associative ANN trained to reproduce the recorded EEG tracks. These weights represented a good model of the peculiar spatial features of the EEG patterns at scalp surface. The classification based on these parameters was binary (MCI versus AD) and was performed by a supervised ANN. Half of the EEG database was used for the ANN training and the remaining half was utilised for the automatic classification phase (testing).

RESULTS

The best results distinguishing between AD and MCI reached to 92.33%. The comparative results obtained with the best method so far described in the literature, based on blind source separation and Wavelet pre-processing, were 80.43% (p<0.001).

CONCLUSION

The results confirmed the working hypothesis that a correct automatic classification of MCI and AD subjects can be obtained extracting spatial information content of the resting EEG voltage by ANNs and represent the basis for research aimed at integrating spatial and temporal information content of the EEG.

The implicit function as squashing time model: a novel parallel nonlinear EEG analysis technique distinguishing mild cognitive impairment and Alzheimer's disease subjects with high degree of accuracy

Objective. This paper presents the results obtained using a protocol based on special types of artificial neural networks (ANNs) assembled in a novel methodology able to compress the temporal sequence of electroencephalographic (EEG) data into spatial invariants for the automatic classification of mild cognitive impairment (MCI) and Alzheimer's disease (AD) subjects. With reference to the procedure reported in our previous study (2007), this protocol includes a new type of artificial organism, named TWIST. The working hypothesis was that compared to the results presented by the workgroup (2007); the new artificial organism TWIST could produce a better classification between AD and MCI. Material and methods. Resting eyes-closed EEG data were recorded in 180 AD patients and in 115 MCI subjects. The data inputs for the classification, instead of being the EEG data, were the weights of the connections within a nonlinear autoassociative ANN trained to generate the recorded data. The most relevant features were selected and coincidently the datasets were split in the two halves for the final binary classification (training and testing) performed by a supervised ANN. Results. The best results distinguishing between AD and MCI were equal to 94.10% and they are considerable better than the ones reported in our previous study ( approximately 92%) (2007). Conclusion. The results confirm the working hypothesis that a correct automatic classification of MCI and AD subjects can be obtained by extracting spatial information content of the resting EEG voltage by ANNs and represent the basis for research aimed at integrating spatial and temporal information content of the EEG.

Recovering EEG brain signals: artifact suppression with wavelet enhanced independent component analysis

Independent component analysis (ICA) has been proven useful for suppression of artifacts in EEG recordings. It involves separation of measured signals into statistically independent components or sources, followed by rejection of those deemed artificial. We show that a "leak" of cerebral activity of interest into components marked as artificial means that one is going to lost that activity. To overcome this problem we propose a novel wavelet enhanced ICA method (wICA) that applies a wavelet thresholding not to the observed raw EEG but to the demixed independent components as an intermediate step. It allows recovering the neural activity present in "artificial" components. Employing semi-simulated and real EEG recordings we quantify the distortions of the cerebral part of EEGs introduced by the ICA and wICA artifact suppressions in the time and frequency domains. In the context of studying cortical circuitry we also evaluate spectral and partial spectral coherences over ICA/wICA-corrected EEGs. Our results suggest that ICA may lead to an underestimation of the neural power spectrum and to an overestimation of the coherence between different cortical sites. wICA artifact suppression preserves both spectral (amplitude) and coherence (phase) characteristics of the underlying neural activity.