Spectral and complexity analysis of scalp EEG characteristics for mild cognitive impairment and early Alzheimer's disease

Abstract

Amnestic mild cognitive impairment (aMCI) often is an early stage of Alzheimer’s disease (AD). MCI is characterized by cognitive decline departing from normal cognitive aging but that does not significantly interfere with daily activities. This study explores the potential of scalp EEG for early detection of alterations from cognitively normal status of older adults signifying MCI and AD. Resting 32-channel EEG records from 48 age-matched participants (mean age 75.7 years)–15 normal controls (NC), 16 early MCI, and 17 early stage AD–are examined. Regional spectral and complexity features are computed and used in a support vector machine model to discriminate between groups. Analyses based on three-way classifications demonstrate discrimination accuracies of 83.9%–96.8% for MCI vs. NC (p-value<0.0029), 71.9%–96.9% for AD vs. NC (p-value<0.0333), and 87.9%–90.9% for AD vs. MCI (pvalue<0.0136), depending on the EEG protocol condition employed. These results demonstrate the great promise for scalp EEG spectral and complexity features as noninvasive biomarkers for detection of MCI and early AD.

On the early diagnosis of Alzheimer's Disease from multimodal signals: A survey

“…The results for the three classification problems are very promising. It is evident that [196,35,199,197] Delta, theta, alpha, beta and gamma bands' spectrum power densities, total spectral power, specific spectral power ratios (see [35] diagnostic rates in real life using these methods would not be as high as the ones that have been achieved in laboratory experiments because in real life there is much more variety of diseases, and probably, also much more variation in the progression of dementia. However, these results verify that automatic signal and image processing methods have the potential for both AD diagnosis and early AD diagnosis (or MCI) when they are combined with other methods.…”

“…The accumulation of ˇA on the brain is considered a necessary but not sufficient condition to produce the clinical symptoms of MCI and dementia [34]. The presence of these plaques and tangles is eventually accompanied by the damage and death of neurons [3], and in fact, one of the most favourable hypothesis about the origin of AD nowadays is the abnormal deposition of these proteins [35][36][37]. Cerebral hypoperfusion has also been found to be more evident in AD patients than in normal adults, so other hypothesis blaming the vascular and cardiovascular problems to be the cause of this hypoperfusion which in turn could trigger dementia have been developed [38].…”

“…Individual models were also tested by analysing for each one of the subjects the ratio between the number of correctly classified EEG epochs and the total number of EEG epochs, resulting in higher accuracies of up to 87%. In the study carried out by McBride et al [35], EEG signals have been used to discriminate control, MCI and AD patients. Spectral and complexity features were used for three SVM classifiers, that aimed to solve three two class classification problems: control vs MCI, control vs AD and MCI vs AD.…”

Complexity Measures for Quantifying Changes in Electroencephalogram in Alzheimer’s Disease

“…AD causes a reduction in neuronal activity of the brain [52] resulting in decreased capability of the brain to process information [53][54][55] and this may be reflected in the EEG signals [52]. EEG complexity can potentially be a good biomarker for AD diagnosis [38] as AD patients have a significant reduction in EEG complexity [38,40,41,52,56,57]. Several studies have investigated EEG complexity as a potential AD biomarker using whole EEG record with the objective of achieving a high performance.…”

Spectral and brain mapping analysis of EEG based on Pwelch in schizophrenic patients

“…In the previous study, the power spectral analysis was used for classification of patients with brain damage asymmetric signal [2], the classification of EEG signals for automatic detection of epileptic seizure [3] also early detection of mild cognitive impairment and Alzheimer's disease [4]. In this study, EEG signals of schizophrenics analyzed and quantified using power spectral analysis through Welch periodogram approach with Hamming window, in an attempt to identify the components of the delta, theta, alpha, beta and gamma wave.…”