Nigel R. Hudson

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 Alzheimers 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.

Improving the Quality of EEG Data in Patients with Alzheimer's Disease Using ICA

Does Independent Component Analysis (ICA) denature EEG signals? We applied ICA to two groups of subjects (mild Alzheimer patients and control subjects). The aim of this study was to examine whether or not the ICA method can reduce both group differences and within-subject variability. We found that ICA diminished Leave-One-Out root mean square error (RMSE) of validation (from 0.32 to 0.28), indicative of the reduction of group difference. More interestingly, ICA reduced the inter-subject variability within each group (?= 2.54 in the ? range before ICA, ?= 1.56 after, Bartlett p = 0.046 after Bonferroni correction). Additionally, we present a method to limit the impact of human error (? 13.8%, with 75.6% inter-cleaner agreement) during ICA cleaning, and reduce human bias. These findings suggests the novel usefulness of ICA in clinical EEG in Alzheimers disease for reduction of subject variability.

New online method for removing ocular artefacts from EEG signals

A method for online removal of ocular artefacts from the human electroencephalogram (EEG) is described. It uses numerically stable algorithms based on the efficient recursive least-squares algorithm. The method is shown to give similar results to its offline equivalents from which it has been developed. Compared with the present online methods our approach is superior, requiring no subjective manual adjustment and processing all signals digitally. An automatic online microcomputer-based ocular artefact remover has been built and successfully tested.

Characterization of EEGs in Alzheimer's Disease using Information Theoretic Methods

The number of people that now go on to develop Alzheimers disease (AD) and other types of dementia is rapidly rising. For maximum benefits from new treatments, the disease should be diagnosed as early as possible, but this is difficult with current clinical criteria. Potentially, the EEG can serve as an objective, first line of decision support tool to improve diagnosis. It is non-invasive, widely available, low-cost and could be carried out rapidly in the high-risk age group that will develop AD. Changes in the EEG due to the dementing process could be quantified as an index or marker. In this paper, we investigate two information theoretic methods (Tsallis entropy and universal compression algorithm) as a way to generate potentially robust markers from the EEG. The hypothesis is that the information theoretic makers for AD are significantly different to those of normal subjects. An attraction of the information theoretic approach is that, unlike most existing methods, there may be a natural link between the underlying ideas of information theoretic methods, the physiology of AD and its impact on brain functions. Data compression has not been investigated as a means of generating EEG markers before and is attractive because it does not require a priori knowledge of the source model. In this paper, we focus on the LZW algorithm because of its sound theoretical foundation. We used the LZW algorithm and Tsallis model to compute the markers (compression ratios and normalized entropies, respectively) from two EEG datasets. The results show that the information theoretic methods can be used to compute EEG markers for AD.

Investigation and comparison of some models for removing ocular artefacts from EEG signals

An investigation of ocular artefacts (OAs) in the human electroencephalogram (EEG) to quantify the effectiveness of OA removal and to find the most effective model for removing OAs online is described. In Part 1, the models used in the investigation are described and the data analysed. The analysis showed that the ‘true’ EEG exhibited a high degree of serial correlation and so the ordinary least-squares (OLS) method employed to remove OA was inefficient. Efficient alternative methods based on autoregressive models of the ‘true’ EEG are discussed. It is also shown that the EOGs are linearly dependent making some of them redundant. In Part 2, the models are compared.

Nonlinear methods for biopattern analysis: role and challenges

An important trend in medical technology is towards support for personalised healthcare, fuelled by developments in genomic-based medicine. New computational intelligent techniques for biodata analysis will be needed to fully exploit the vast amounts of data that are being generated. Non-linear signal processing methods will form an important part of such computational intelligent techniques. This paper introduces some non-linear methods which are likely to play a role in the emerging area of biopattern and bioprofile analysis that will underpin personalized healthcare. We highlight their application to clinical problems involving EEG and fetal ECG and heart rate analysis, and issues that arise when they are applied to real world problems. The clinical problems include dementia assessment, drug administration and fetal monitoring. The potential role and challenges in the application of non-linear signal analysis of biopattern and bioprofile are highlighted within the context of a major EU project, BIOPATTERN.

Expert system approach to electroencephalogram signal processing

The human electroencephalogram (EEG) is often corrupted by ocular artefacts (OAs) caused by the movement of the eyes and/or the eyelids, making the recognition of abnormal EEG signals more difficult. The removal of OAs using conventional signal processing is complicated by the similarity between abnormal EEGs and OAs, which can lead to corruption of the EEG signal. The paper describes the development of a novel approach that uses expert system techniques to differentiate OAs from genuine EEG signals, enabling OA removal to be applied only where appropriate, and ensuring that clinically relevant EEG information is left unaffected.

Performance Evaluation and Fusion of Methods for Early Detection of Alzheimer Disease

The number of people that develop Alzheimers Disease (AD) is rapidly rising, while the initial diagnosis and care of AD patients typically falls on non-specialist and still taking up to 3-5 years before being referred to specialists. An urgent need thus exists to develop methods to extract accurate and robust biomarkers from low-cost and non intrusive modalities such as electroencephalograms (EEGs). Contributions of this paper are three-fold. First we review 8 promising methods for early diagnosis of AD and undertake a performance evaluation using ROC analysis. We find that fractal dimension (AUC = 0.989), zero crossing interval (AUC = 0.980) and spectrum analysis of power alpha/theta ratio (Pwralpha,thetas)(AUC = 0.975) perform best, with all three having sensitivity and specificity higher than 94%. We plot ROC curve with 95% confidence contours because of the small size of our data set (17 AD and 24 NOLD). Second, we investigate a fusion approach to combine these methods, using a logistic regression model, into one single more accurate biomarker (AUC = 1.0). Thirdly, to help support the distribution and use of these methods for early detection and care of AD, we developed them as web-services, integrated into online tools available from the BIOPATTERN project portal (www.biopattern.org).

Investigation and comparison of some models for removing ocular artefacts from EEG signals. Part 2. Quantitative and pictorial comparison of models.

An investigation of ocular artefacts (OAs) in the human electroencephalogram (EEG) to quantify the effectiveness of OA removal, and to find the most effective model for removing OAs online is described. It was found unnecessary to use the vertical and horizontal EOGs of both eyes, although more than one EOG signal is required for adequate OA removal. The model using the vertical right EOG and the two horizontal EOGs was the best overall, but in most cases the use of only the vertical and horizontal right EOGs was sufficient. OAs were not completely removed by any of the models investigated, suggesting that more complex models are necessary.

Dynamical Nonstationarity Analysis of Resting EEGs in Alzheimer's Disease

The understanding of nonstationarity, from both a dynamical and a statistical point of view, has turned from a constraint on application of a specific type of analysis (e.g. spectral analysis), into a new insight into complex system behavior. The application of nonstationarity detection in an EEG time series plays an important role in the characterization of brain processes and the prediction of brain state and behavior such as seizure prediction. In this study, we report a very significant difference in the mean stationarity duration of an EEG over the frontal and temporal regions of the brain, comparing 22 healthy subjects and 16 patients with mild Alzheimers disease (AD). The findings help illuminate the interpretation of the EEGs duration of dynamical stationarity and proposes to be useful for distinguishing AD patients from control patients. This study supports the idea of a compensatory activation of the fronto-temporal region of the brain in the early stages of Alzheimers disease.