Alzheimer's disease (AD) is the most common neurodegenerative disorder. Although a definite diagnosis is only possible by necropsy, a differential diagnosis with other types of dementia and with major depression should be attempted. The aim of this study was to analyse the electroencephalogram (EEG) background activity of AD patients to test the hypothesis that the regularity of the AD patients' EEG is higher than that of age-matched controls. We recorded the EEG from 19 scalp electrodes in 11 AD patients and 11 age-matched controls. Two different methods were used to estimate the regularity of the EEG background activity: spectral entropy (SpecEn) and sample entropy (SampEn). We did not find significant differences between AD patients and control subjects' EEGs with SpecEn. On the other hand, AD patients had significantly lower SampEn values than control subjects (p < 0.01) at electrodes P3, P4, O1 and O2. Our results show an increase of EEG regularity in AD patients. These findings suggest that nonlinear analysis of the EEG with SampEn could yield essential information and may contribute to increasing the insight into brain dysfunction in AD in ways which are not possible with more classical and conventional statistical methods.

The discrimination of early Alzheimer’s disease (AD) and its prodromal form (i.e., mild cognitive impairment, MCI) from cognitively healthy control (HC) subjects is crucial since the treatment is more effective in the first stages of the dementia. The aim of our study is to evaluate the usefulness of a methodology based on electroencephalography (EEG) to detect AD and MCI. EEG rhythms were recorded from 37 AD patients, 37 MCI subjects and 37 HC subjects. Artifact-free trials were analyzed by means of several spectral and nonlinear features: relative power in the conventional frequency bands, median frequency, individual alpha frequency, spectral entropy, Lempel–Ziv complexity, central tendency measure, sample entropy, fuzzy entropy, and auto-mutual information. Relevance and redundancy analyses were also conducted through the fast correlation-based filter (FCBF) to derive an optimal set of them. The selected features were used to train three different models aimed at classifying the trials: linear discriminant analysis (LDA), quadratic discriminant analysis (QDA) and multi-layer perceptron artificial neural network (MLP). Afterwards, each subject was automatically allocated in a particular group by applying a trial-based majority vote procedure. After feature extraction, the FCBF method selected the optimal set of features: individual alpha frequency, relative power at delta frequency band, and sample entropy. Using the aforementioned set of features, MLP showed the highest diagnostic performance in determining whether a subject is not healthy (sensitivity of 82.35% and positive predictive value of 84.85% for HC vs. all classification task) and whether a subject does not suffer from AD (specificity of 79.41% and negative predictive value of 84.38% for AD vs. all comparison). Our findings suggest that our methodology can help physicians to discriminate AD, MCI and HC.

We present an automatic image processing algorithm to detect hard exudates. Automatic detection of hard exudates from retinal images is an important problem since hard exudates are associated with diabetic retinopathy and have been found to be one of the most prevalent earliest signs of retinopathy. The algorithm is based on Fisher's linear discriminant analysis and makes use of colour information to perform the classification of retinal exudates. We prospectively assessed the algorithm performance using a database containing 58 retinal images with variable colour, brightness, and quality. Our proposed algorithm obtained a sensitivity of 88% with a mean number of 4.83+/-4.64 false positives per image using the lesion-based performance evaluation criterion, and achieved an image-based classification accuracy of 100% (sensitivity of 100% and specificity of 100%).

In this study, we explored the ability of several spectral based measures to summarize the information of the power spectral density (PSD) function from spontaneous magnetoencephalographic (MEG) activity in Alzheimer's disease (AD). The MEGs of 20 AD patients and 21 elderly controls were recorded with eyes closed at rest during 5 min from 148 channels. Five spectral parameters were estimated from PSD: mean frequency (MF), individual alpha frequency (IAF), transition frequency (TF), 95% spectral edge frequency (SEF95) and spectral entropy (SE). To reduce the dimensionality of the problem, we applied a principal component analysis. According to our results, MF was the best discriminating index between both groups (85.00% sensitivity, 85.71% specificity) indicating a shift to the left of the power spectrum in AD. A significant MEG slowing was also observed using both IAF (p < 0.001) and TF (p < 0.01). The lowest classification statistics (65% sensitivity, 66.67% specificity) were obtained with SEF95. However, these results were also significant (p < 0.05). This fact points out that there is a variation in the spectral content at high frequencies of AD patients and controls. Finally, a significant decrease of irregularity in the AD group was observed with SE, with results close to those obtained with MF (90.00% sensitivity, 76.19% specificity). In conclusion, a complete description of PSD can help to increase our insight into brain dysfunction in AD and to extract spectral patterns specific to the disease.