Diagnosis of Alzheimer's disease from EEG by means of synchrony measures in optimized frequency bands

Gallego-Jutglà, Esteve; Elgendi, Mohamed; Vialatte, François; Solé-Casals, Jordi; Cichocki, Andrzej; Latchoumane, Charles; Jeong, Jaesung; Dauwels, Justin

doi:10.1109/embc.2012.6346909

Cited by 36 publications

(28 citation statements)

References 17 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another study where this signal filtering was applied was that by Gallego-Jutgla et al [6]. Their findings too showed the improvement in distinction that this filtering method could obtain with a range of linear methods including synchrony and coherence methods.…”

Section: Discussion and Conclutionsmentioning

confidence: 97%

“…A third order Butterworth filter, chosen due to its clear transition properties [7] was used to filter the signal in the range F to F+W Hz with F in the range 1,2,…,30Hz and W in the range 1,2,…,30Hz. This method has already been applied to another signal database [6]. This and all other signal manipulation, calculation and result analysis presented in this study was carried out using Matlab® [8].…”

Section: B Signal Filteringmentioning

confidence: 99%

“…LZC has been chosen for this pilot study due to its rigorous scientific basis [4] and previously published success in differentiating EEG AD and control signals [5]. Furthermore, the reduction in signal frequency range has shown an increase in statistically significant changes in a paper by Gallego-Jutgla et al [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigation of Alzheimer’s Disease EEG Frequency Components with Lempel-Ziv Complexity

2015

View full text Add to dashboard Cite

Abstract-This pilot study applied Lempel-Ziv Complexity (LZC) to 22 resting EEG signals, collected using the 10-20 international system, from 11 patients with Alzheimer's disease (AD) and 11 age-matched controls. This allowed for frequency band analysis as the EEG signals were first prefiltered with a third order Hamming window in the ranges F to F+WHz with both F and W equal to 1-30Hz respectively. Control subjects were found to have a greater signal complexity than AD patients with statistically significant bands seen at various ranges in all 16 electrodes. The maximum statistical significance (Student's t test, p<0.01) was increased over the findings with traditional signal filtering techniques allowing the whole range, with a maximum significance of p=3.50e -6 at electrode T4 between 7-18Hz. Electrode F4 also showed significantly high statistically significant differences. The maximum accuracy, both controls and AD patients correctly identified, found with Receiver Operating Characteristic Curves was 95.45% (21 of 22 subjects correctly classified) at T4 (7-18Hz and 7-20Hz), Fp2 (8-32Hz) and F4 (6-21Hz), which is significantly more accurate than the most accurate methods previously applied to this dataset. The beta band (13-30Hz) was found to be most influential in separating the two test groups in this study with the best range suggested to be 5-26Hz, combining traditional theta, alpha and beta bands. These findings suggest pre-filtering has a significant effect on method outcomes and can be successfully tailored to improve the statistical effectiveness of LZC at distinguishing between these two EEG groups. However, more testing is required to investigate the effectiveness at distinguishing other signal dynamics.

show abstract

Section: Discussion and Conclutionsmentioning

confidence: 97%

Section: B Signal Filteringmentioning

confidence: 99%

See 1 more Smart Citation

Investigation of Alzheimer’s Disease EEG Frequency Components with Lempel-Ziv Complexity

2015

View full text Add to dashboard Cite

show abstract

“…Some studies have analysed all the frequency bands between 1 and 30 Hz, for instance, using a power measure [13] or a set of synchrony measures [14]. The present study investigates whether the diagnosis of AD can be improved by analysing all possible frequency ranges in the 1-30Hz frequency range (e.g., 1-2 Hz, 1-3Hz, 1-4Hz….…”

Section: Compared To Other Systems Like Functional Magnetic Resonancementioning

confidence: 99%

A hybrid feature selection approach for the early diagnosis of Alzheimer’s disease

Gallego-Jutglà¹,

Solé-Casals²,

Vialatte³

et al. 2015

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Recently, significant advances have been made in the early diagnosis of Alzheimer's disease from EEG. However, choosing suitable measures is a challenging task. Among other measures, frequency Relative Power and loss of complexity have been used with promising results. In the present study we investigate the early diagnosis of AD using synchrony measures and frequency Relative Power on EEG signals, examining the changes found in different frequency ranges. Approach. We first explore the use of a single feature for computing the classification rate, looking for the best frequency range. Then, we present a multiple feature classification system that outperforms all previous results using a feature selection strategy.These two approaches are tested in two different databases, one containing MCI and healthy subjects (patients age: 71.9 ± 10.2, healthy subjects age: 71.7 ± 8.3), and the other containing Mild AD and healthy subjects (patients age: 77.6 ± 10.0; healthy subjects age: 69.4± 11.5).Main Results. Using a single feature to compute classification rates we achieve a performance of 78.33% for the MCI data set and of 97.56 % for Mild AD. Results are clearly improved using the multiple feature classification, where a classification rate of 95% is found for the MCI data set using 11 features, and 100% for the Mild AD data set using 4 features. Significance. The new features selection method described in this work may be a reliable tool that could help to design a realistic system that does not require prior knowledge of a patient's status. With that aim, we explore the standardization of features for MCI and Mild AD data sets with promising results.

show abstract

“…We demonstrated the use of Discrete Cosine Transform (DCT) as feature extraction technique coupled with KNN classifier, and were able to obtain 72% accuracy in classifying EEG that correlated to human stress. Despite the EEG data were collected using a single electrode BCI -NeuroSky MindWave, yet the classification outcome were not far behind than multi electrode BCI [15], [18], [20], [25], [37], [38]. With proper choice of classifier and feature extraction components, it is possible to employ a single electro BCI in EEG research and recognizes human stress.…”

Section: Discussionmentioning

confidence: 99%

Analysis of Single-Electrode EEG Rhythms Using MATLAB to Elicit Correlation with Cognitive Stress

Lim¹,

Chia²

2015

IJCTE

View full text Add to dashboard Cite

Abstract-This paper demonstrates electroencephalogram (EEG) analysis in MATLAB environment with the objective to investigate effectiveness of cognitive stress recognition algorithm using EEG from single-electrode BCI. 25 subjects' EEG were recorded in MATLAB with the use of Stroop color-word test as stress inducer. Questionnaire on subjects' self-perceived stress scale during Stroop test were gathered as classification's target output. The main analysis tool used were MATLAB, coupled with the use of Discrete Cosine Transform (DCT) as dimension reduction technique to reduce data size down to 2% of the origin. Three pattern classification algorithms' -Artificial Neural Network (ANN), k-Nearest Neighbor (KNN) and Linear Discriminant Analysis (LDA) were trained using the resulted 2% DCT coefficients. Our study discovered the use of DCT along with KNN offers highest average classification rate of 72% compared to ANN and LDA.

show abstract

Diagnosis of Alzheimer's disease from EEG by means of synchrony measures in optimized frequency bands

Cited by 36 publications

References 17 publications

Investigation of Alzheimer’s Disease EEG Frequency Components with Lempel-Ziv Complexity

Investigation of Alzheimer’s Disease EEG Frequency Components with Lempel-Ziv Complexity

A hybrid feature selection approach for the early diagnosis of Alzheimer’s disease

Analysis of Single-Electrode EEG Rhythms Using MATLAB to Elicit Correlation with Cognitive Stress

Contact Info

Product

Resources

About