Paulo Afonso Medeiros Kanda

Improving Alzheimer's Disease Diagnosis with Machine Learning Techniques:

There is not a specific test to diagnose Alzheimers disease (AD). Its diagnosis should be based upon clinical history, neuropsychological and laboratory tests, neuroimaging and electroencephalography (EEG). Therefore, new approaches are necessary to enable earlier and more accurate diagnosis and to follow treatment results. In this study we used a Machine Learning (ML) technique, named Support Vector Machine (SVM), to search patterns in EEG epochs to differentiate AD patients from controls. As a result, we developed a quantitative EEG (qEEG) processing method for automatic differentiation of patients with AD from normal individuals, as a complement to the diagnosis of probable dementia. We studied EEGs from 19 normal subjects (14 females/5 males, mean age 71.6 years) and 16 probable mild to moderate symptoms AD patients (14 females/2 males, mean age 73.4 years. The results obtained from analysis of EEG epochs were accuracy 79.9% and sensitivity 83.2%. The analysis considering the diagnosis of each individual patient reached 87.0% accuracy and 91.7% sensitivity.

Characterizing Alzheimer’s Disease Severity via Resting-Awake EEG Amplitude Modulation Analysis

Changes in electroencephalography (EEG) amplitude modulations have recently been linked with early-stage Alzheimer’s disease (AD). Existing tools available to perform such analysis (e.g., detrended fluctuation analysis), however, provide limited gains in discriminability power over traditional spectral based EEG analysis. In this paper, we explore the use of an innovative EEG amplitude modulation analysis technique based on spectro-temporal signal processing. More specifically, full-band EEG signals are first decomposed into the five well-known frequency bands and the envelopes are then extracted via a Hilbert transform. Each of the five envelopes are further decomposed into four so-called modulation bands, which were chosen to coincide with the delta, theta, alpha and beta frequency bands. Experiments on a resting-awake EEG dataset collected from 76 participants (27 healthy controls, 27 diagnosed with mild-AD, and 22 with moderate-AD) showed significant differences in amplitude modulations between the three groups. Most notably, i) delta modulation of the beta frequency band disappeared with an increase in disease severity (from mild to moderate AD), ii) delta modulation of the theta band appeared with an increase in severity, and iii) delta modulation of the beta frequency band showed to be a reliable discriminant feature between healthy controls and mild-AD patients. Taken together, it is hoped that the developed tool can be used to assist clinicians not only with early detection of Alzheimer’s disease, but also to monitor its progression.

The effects of automated artifact removal algorithms on electroencephalography-based Alzheimer's disease diagnosis

Over the last decade, electroencephalography (EEG) has emerged as a reliable tool for the diagnosis of cortical disorders such as Alzheimers disease (AD). EEG signals, however, are susceptible to several artifacts, such as ocular, muscular, movement, and environmental. To overcome this limitation, existing diagnostic systems commonly depend on experienced clinicians to manually select artifact-free epochs from the collected multi-channel EEG data. Manual selection, however, is a tedious and time-consuming process, rendering the diagnostic system “semi-automated.” Notwithstanding, a number of EEG artifact removal algorithms have been proposed in the literature. The (dis)advantages of using such algorithms in automated AD diagnostic systems, however, have not been documented; this paper aims to fill this gap. Here, we investigate the effects of three state-of-the-art automated artifact removal (AAR) algorithms (both alone and in combination with each other) on AD diagnostic systems based on four different classes of EEG features, namely, spectral, amplitude modulation rate of change, coherence, and phase. The three AAR algorithms tested are statistical artifact rejection (SAR), blind source separation based on second order blind identification and canonical correlation analysis (BSS-SOBI-CCA), and wavelet enhanced independent component analysis (wICA). Experimental results based on 20-channel resting-awake EEG data collected from 59 participants (20 patients with mild AD, 15 with moderate-to-severe AD, and 24 age-matched healthy controls) showed the wICA algorithm alone outperforming other enhancement algorithm combinations across three tasks: diagnosis (control vs. mild vs. moderate), early detection (control vs. mild), and disease progression (mild vs. moderate), thus opening the doors for fully-automated systems that can assist clinicians with early detection of AD, as well as disease severity progression assessment.

Estudo da coerência do eletrencefalograma para a banda de frequência alfa em indivíduos adultos normais e com provável demência do tipo Alzheimer

We studied the occiptal inter-hemispheric coherence (IHCoh) of EEG (electrodes O1-O2) for alpha band (alpha1 - 8,0 to 10,0 Hz and alpha2 - 10,1 to 12,5 Hz) in healthy adults and Alzheimers type dementia (ATD) subjects, to observe if there is any significant difference between these two groups that could help in the early diagnosis of ATD. We found a decrease of occipital IHCoh in ATD group for both alpha sub-bands. We believe that Coh analysis of EEG is a powerful auxiliary method in ATD diagnosis.

Index of Alpha/Theta Ratio of the Electroencephalogram: A New Marker for Alzheimer’s Disease

Objective: We evaluated quantitative EEG measures to determine a screening index to discriminate Alzheimer’s disease (AD) patients from normal individuals. Methods: Two groups of individuals older than 50 years, comprising a control group of 57 normal volunteers and a study group of 50 patients with probable AD, were compared. EEG recordings were obtained from subjects in a wake state with eyes closed at rest for 30 min. Logistic regression analysis was conducted. Results: Spectral potentials of the alpha and theta bands were computed for all electrodes and the alpha/theta ratio calculated. Logistic regression of alpha/theta of the mean potential of the C3 and O1 electrodes was carried out. A formula was calculated to aid the diagnosis of AD yielding 76.4% sensitivity and 84.6% specificity for AD with an area under the ROC curve of 0.92. Conclusion: Logistic regression of alpha/theta of the spectrum of the mean potential of EEG represents a good marker discriminating AD patients from normal controls.

Recomendaçöes para o registro/interpretaçäo do mapeamento topográfico do eletrencefalograma e potenciais evocados: parte II: correlaçöes clínicas

Digital EEG (DEEG) and quantitative EEG (QEEG) are recently developed tools present in many clinical situations. Besides showing didactic and research utility, they may also have a clinical role. Although a considerable amount of scientific literature has been published related to QEEG, many controversies still subsist regarding its clinical utilization. Clinical applications are: 1. DEEG is already an established substitute for conventional EEG, representing a clear technical advance. 2. Certain QEEG techniques are an established addition to DEEG for: 2a) screening for epileptic spikes or seizures in long-term recordings; 2b) Operation room and intensive care unit EEG monitoring. 3. Certain QEEG techniques are considered possible useful additions to DEEG: 3a) topographic voltage and dipole analysis in epilepsy evaluations; 3b) frequency analysis in cerebrovascular disease and dementia, mostly when other tests have been inconclusive. 4. QEEG remains investigational for clinical use in postconcussion syndrome, learning disability, attention disorders, schizophrenia, depression, alcoholism and drug abuse. EEG brain mapping and other QEEG techniques should be clinically used only by physicians highly skilled in clinical EEG interpretation and as an adjunct to traditional EEG work.

Clinician’s Road Map to Wavelet EEG as an Alzheimer’s disease Biomarker:

Alzheimer’s disease (AD) is considered the main cause of dementia in Western countries. Consequently, there is a need for an accurate, universal, specific and cost-effective biomarker for early AD diagnosis, to follow disease progression and therapy response. This article describes a new diagnostic approach to quantitative electroencephalogram (QEEG) diagnosis of mild and moderate AD. The data set used in this study was composed of EEG signals recorded from 2 groups: (S1) 74 normal subjects, 33 females and 41 males (mean age 67 years, standard deviation = 8) and (S2) 88 probable AD patients (NINCDS-ADRDA criteria), 55 females and 33 males (mean age 74.7 years, standard deviation = 7.8) with mild to moderate symptoms (DSM-IV-TR). Attention is given to sample size and the use of state of the art open source tools (LetsWave and WEKA) to process the EEG data. This innovative technique consists in associating Morlet wavelet filter with a support vector machine technique. A total of 111 EEG features (attributes) were obtained for 162 probands. The results were accuracy of 92.72% and area under the curve of 0.92 (percentage split test). Most important, comparing a single patient versus the total data set resulted in accuracy of 84.56% (leave-one-patient-out test). Particular emphasis was on clinical diagnosis and feasibility of implementation of this low-cost procedure, because programming knowledge is not required. Consequently, this new method can be useful to support AD diagnosis in resource-limited settings.

Towards an EEG-based biomarker for Alzheimer's disease: Improving amplitude modulation analysis features

In this paper, an EEG-based biomarker for automated Alzheimers disease (AD) diagnosis is described, based on extending a recently-proposed “percentage modulation energy” (PME) metric. More specifically, to improve the signal-to-noise ratio of the EEG signal, PME features were averaged over different durations prior to classification. Additionally, two variants of the PME features were developed: the “percentage raw energy” (PRE) and the “percentage envelope energy” (PEE). Experimental results on a dataset of 88 participants (35 controls, 31 with mild-AD and 22 with moderate AD) show that over 98% accuracy can be achieved with a support vector classifier when discriminating between healthy and mild AD patients, thus significantly outperforming the original PME biomarker. Moreover, the proposed system can achieve over 94% accuracy when discriminating between mild and moderate AD, thus opening doors for very early diagnosis.

Alzheimer's disease qEEG: spectral analysis versus coherence. which is the best measurement?

There is evidence in electroencephalography that alpha, theta and delta band oscillations reflect cognitive and memory performances and that quantitative techniques can improve the electroencephalogram (EEG) sensitivity. This paper presents the results of comparative analysis of qEEG variables as reliable markers for Alzheimers disease (AD). We compared the sensitivity and specificity between spectral analysis (spectA) and coherence (Coh) within the same group of AD patients. SpectA and Coh were calculated from EEGs of 40 patients with mild to moderate AD and 40 healthy elderly controls. The peak of spectA was smaller in the AD group than in controls. AD group showed predominance of slow spectA in theta and delta bands and a significant reduction of inter-hemispheric Coh for occipital alpha 2 and beta 1 and for frontal delta sub-band. ROC curve supported that alpha band spectA was more sensitive than coherence to differentiate controls from AD.

The clinical use of quantitative EEG in cognitive disorders

The primary diagnosis of most cognitive disorders is clinically based, but the EEG plays a role in evaluating, classifying and following some of these disorders. There is an ongoing debate over routine use of qEEG. Although many findings regarding the clinical use of quantitative EEG are awaiting validation by independent investigators while confirmatory clinical follow-up studies are also needed, qEEG can be cautiously used by a skilled neurophysiologist in cognitive dysfunctions to improve the analysis of background activity, slow/fast focal activity, subtle asymmetries, spikes and waves, as well as in longitudinal follow-ups.