RESUMO
Mild Cognitive Impairment (MCI) is the primary stage of acute Alzheimer's disease, and early detection is crucial for the person and those around him. It is difficult to recognize since this mild stage does not have clear clinical signs, and its symptoms are between normal aging and severe dementia. Here, we propose a tensor decomposition-based scheme for automatically diagnosing MCI using Electroencephalogram (EEG) signals. A new projection is proposed, which preserves the spatial information of the electrodes to construct a data tensor. Then, using parallel factor analysis (PARAFAC) tensor decomposition, the features are extracted, and a support vector machine (SVM) is used to discriminate MCI from normal subjects. The proposed scheme was tested on two different datasets. The results showed that the tensor-based method outperformed conventional methods in diagnosing MCI with an average classification accuracy of 93.96% and 78.65% for the first and second datasets, respectively. Therefore, it seems that maintaining the spatial topology of the signals plays a vital role in the processing of EEG signals.
RESUMO
Mild cognitive impairment (MCI) is becoming a serious problem for developing countries as the lifespan of populations increases. Exercise is known to be clinically beneficial for MCI patients. Somatosensory-evoked potentials (SEPs) may be a potential diagnostic and prognostic marker for this population. The objective of this study was to determine the acute effects of aerobic exercise on SEPs in patients with MCI, to test whether SEPs are sensitive enough to detect improvements in early somatosensory processing. The study had a randomized parallel-group design and included 28 MCI subjects (14 in the experimental group and 14 in the control group). The experimental intervention was 20 min of aerobic exercise using a stationary bicycle. The control intervention involved 20 min of movements and stretches. Subjects were assessed before and after a single intervention session. SEPs were recorded by stimulating the median nerve of the dominant hand. Analysis of normalized SEP peak amplitudes showed that a single session of aerobic activity significantly reduced the N30 peak at the F3 channel (p = 0.03). There were no significant effects of aerobic exercise on SEP peak latencies. The results indicate that 20 min of aerobic exercise has a significant effect on the N30 SEP peak amplitude in MCI patients. The results suggest that aerobic exercise is likely to provide sensory-enriching inputs that enhance sensorimotor integration. Future studies should assess the effects of aerobic exercise on somatosensory processing in progressive stages of Alzheimer's disease, longer exercise durations, and multiple exercise sessions.
